Append native SDK 0.2.7 varying-coordinate feature evidence with partial outcomes
Browse files- research/unfixed-native-feature-pilot-20261001/README.md +5 -0
- research/unfixed-native-feature-pilot-20261001/evidence.tar.gz +3 -0
- research/unfixed-native-feature-pilot-20261001/publication-manifest.json +560 -0
- research/unfixed-native-feature-pilot-20261001/runs/unfixed-native-feature-pilot-20261001/audit.json +1097 -0
- research/unfixed-native-feature-pilot-20261001/runs/unfixed-native-feature-pilot-20261001/report.json +1097 -0
- research/unfixed-native-feature-pilot-20261001/studies/compound-path-v1/cohort.jsonl +0 -0
- research/unfixed-native-feature-pilot-20261001/studies/compound-path-v1/manifest.json +32 -0
research/unfixed-native-feature-pilot-20261001/README.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Native Gooo varying-coordinate feedback pilot
|
| 2 |
+
|
| 3 |
+
Actual native SDK 0.2.7 pilot using own frozen models, six reused bilingual contradictory views and 24 legacy-first pairs. The explicit --path-feedback-unfixed option ranks varying typed coordinates. Raw native bodies, resource sidecars, derived skip receipts, partial finite outcomes and actual emitted-Go values are retained. Caller PASS is unauthenticated context; source CI/GoProof is separate. Feature/main edition is explicit in the prefix and captured compiler SHA. This does not establish arbitrary natural-language accuracy, causal wall speedup, host CPU growth or all-input ordering equivalence. Core weights/card and prior appendices are preserved. No training, GPU work, upstream Laya calls or model/native/Go calls during packaging or offline verification.
|
| 4 |
+
|
| 5 |
+
See report.json for actual measured counts. The deterministic archive preserves raw captures, resource sidecars and actual Go execution values; per-entry hashes and byte sizes are in publication-manifest.json. Methods and limitations: https://github.com/kimjooyoon/gooo-neural-decision-experiments/blob/main/docs/native-unfixed-pilot.md .
|
research/unfixed-native-feature-pilot-20261001/evidence.tar.gz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c24b18fd52a7735f355833b301c92fb81011405cde7726a1d744bb9868e38df
|
| 3 |
+
size 369474
|
research/unfixed-native-feature-pilot-20261001/publication-manifest.json
ADDED
|
@@ -0,0 +1,560 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema": "gooo/native-unfixed-publication/v1",
|
| 3 |
+
"repository": "asketeddy/gooo-feedback-path-tiny-v1",
|
| 4 |
+
"prefix": "research/unfixed-native-feature-pilot-20261001/",
|
| 5 |
+
"archive_entries": [
|
| 6 |
+
{
|
| 7 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/audit.json",
|
| 8 |
+
"sha256": "4dba2dab42c17af2c069a442b18053fc804bc50a32f5b4276799ddf3f96d3962",
|
| 9 |
+
"bytes": 52460
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_fp32-false.json",
|
| 13 |
+
"sha256": "003e8ed5cae6ededb76d2f061f98272de4df40fdb683b658309e12fc4932f76b",
|
| 14 |
+
"bytes": 53667
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_fp32-true.json",
|
| 18 |
+
"sha256": "005733445ba7fe5584ab93ee1b80d2ccfbd0705e1c8d18b414cd881e034c7d48",
|
| 19 |
+
"bytes": 53026
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_ptq-false.json",
|
| 23 |
+
"sha256": "01dfc82c3e81dc1186e246526bc044d4a1092e7edbf37f245bd4435515133590",
|
| 24 |
+
"bytes": 53579
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_ptq-true.json",
|
| 28 |
+
"sha256": "db55540635d3d03ed9c9f3859fe63a46667cf255c09237a4d80a31360fd5d1fd",
|
| 29 |
+
"bytes": 52933
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_qat-false.json",
|
| 33 |
+
"sha256": "795ac720128705d0087952e7576431c9bc0014d793a5ea5c4aead68fcd88d1a1",
|
| 34 |
+
"bytes": 53626
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-feedback_qat-true.json",
|
| 38 |
+
"sha256": "bed58b193820a4a56ae28d6fdb76180ed72592633292eb933b453cf94264254f",
|
| 39 |
+
"bytes": 52976
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-parent_fp32-false.json",
|
| 43 |
+
"sha256": "96f440b6cba0ae66082f3b7dc7d7b4c99825e9b19432f72214907cd577fceaca",
|
| 44 |
+
"bytes": 53575
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-en-contradictory-parent_fp32-true.json",
|
| 48 |
+
"sha256": "d249bcc23bd3adc671e229448709abef2e7c3ecfe0491e8fff00fe3adee68587",
|
| 49 |
+
"bytes": 52939
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_fp32-false.json",
|
| 53 |
+
"sha256": "83b9e8319e84a8c618c86a52262f34c900e11874baa91ea3d16783dc3b0aa3bf",
|
| 54 |
+
"bytes": 53642
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_fp32-true.json",
|
| 58 |
+
"sha256": "3dcfec9ce945c2d79ac318b39b614a1732e4f82e96897226ce405b8069e9d5a2",
|
| 59 |
+
"bytes": 52990
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_ptq-false.json",
|
| 63 |
+
"sha256": "3cbd5fdf27d60d9955011af5d01a31845f5064c4ab6b9e1d10747192868bd76c",
|
| 64 |
+
"bytes": 53559
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_ptq-true.json",
|
| 68 |
+
"sha256": "29767e5fadd38eaf741ad2b52a155b370979ffc57d0223307eaca94cb9a21bb7",
|
| 69 |
+
"bytes": 52913
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_qat-false.json",
|
| 73 |
+
"sha256": "3201402e635fc9dd9e1e5391ac9184216dc38e16dc88b678d86b3ea35f451ae1",
|
| 74 |
+
"bytes": 53660
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-feedback_qat-true.json",
|
| 78 |
+
"sha256": "e73f643dc5cfc4ec96d9b43fd7c2664b83daa6a3bea0e36d2f94d0d8f1762c77",
|
| 79 |
+
"bytes": 53004
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-parent_fp32-false.json",
|
| 83 |
+
"sha256": "c1d0235ec32a594888e09a241a9f9f143cf9c9fe29cdd0ed4ab85b4b5cf32085",
|
| 84 |
+
"bytes": 53531
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/operand_branch-0-ko-contradictory-parent_fp32-true.json",
|
| 88 |
+
"sha256": "380d81badb208d7acc69774c7db015a2e8464bb1de0269f4da3954a0dcf6c2c6",
|
| 89 |
+
"bytes": 52887
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_fp32-false.json",
|
| 93 |
+
"sha256": "45edd1410f838650c7a6b4430f4cbf6b0ac133632bbfe6d11aee45a97e24a26c",
|
| 94 |
+
"bytes": 53588
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_fp32-true.json",
|
| 98 |
+
"sha256": "5d315109df8b1bdd81d3b7ad379946d149c6dcdd139a6ff6ecc998206933067a",
|
| 99 |
+
"bytes": 52940
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_ptq-false.json",
|
| 103 |
+
"sha256": "bf74ef6a30536f95f93744c7eb127427d8bb5c7e5f8b63887a277c90a568da37",
|
| 104 |
+
"bytes": 53341
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_ptq-true.json",
|
| 108 |
+
"sha256": "4d5fb4cba03f34ae84bdb2e8ac5fdcdbbc50e88676e39b28c4e799123c5381da",
|
| 109 |
+
"bytes": 52695
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_qat-false.json",
|
| 113 |
+
"sha256": "393aa2300be6ecfd16f791b871dd80d908ed5cb5bc70caea92c5097d829d2090",
|
| 114 |
+
"bytes": 53561
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-feedback_qat-true.json",
|
| 118 |
+
"sha256": "18ec11e5226b969fe7c64c253fd1c075eefea42fb1eec63299422ba11c83c8b7",
|
| 119 |
+
"bytes": 52916
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-parent_fp32-false.json",
|
| 123 |
+
"sha256": "483e5b80f2f5d7149fb89fe05436e4e7c756a8f0100a4ba6424ddb09e153206d",
|
| 124 |
+
"bytes": 53392
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-en-contradictory-parent_fp32-true.json",
|
| 128 |
+
"sha256": "2c5739db35d5a28f6fd21fcaa5cc01eb7a2367b43a6fb70fbf8e8dafb0ed47d4",
|
| 129 |
+
"bytes": 52749
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_fp32-false.json",
|
| 133 |
+
"sha256": "d4bc53f9b7485c8bbc2a8c6fc2a3ff0c562520bf967033119ae119f6a8b8fb0d",
|
| 134 |
+
"bytes": 53587
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_fp32-true.json",
|
| 138 |
+
"sha256": "90d3f115b51277055c2ba5c7aa7ca195199b86d1b0be75df877789c0e4d06b6c",
|
| 139 |
+
"bytes": 52930
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_ptq-false.json",
|
| 143 |
+
"sha256": "dd8c07106e6152e862fb00d527120e84c7d680f2196579316de443eb607fd597",
|
| 144 |
+
"bytes": 53352
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_ptq-true.json",
|
| 148 |
+
"sha256": "e3374ff32a28f68999dc7d1cff2d45fe1cfc26d973d4b07c02951a038f42e3fb",
|
| 149 |
+
"bytes": 52706
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_qat-false.json",
|
| 153 |
+
"sha256": "983bb76c6765cf8a3127785625563d69da51bb882c2d5f01ea9859b7d6b36836",
|
| 154 |
+
"bytes": 53657
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-feedback_qat-true.json",
|
| 158 |
+
"sha256": "69914d48dfe113f155a0599e9fe6fd4b80bb6f3f641f5936399e2d7e77f0103c",
|
| 159 |
+
"bytes": 53001
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-parent_fp32-false.json",
|
| 163 |
+
"sha256": "365e00f0da6f380972f9d05eb3c158eefd353142f2c8219c25e39c866d826fc2",
|
| 164 |
+
"bytes": 53398
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_assignment-0-ko-contradictory-parent_fp32-true.json",
|
| 168 |
+
"sha256": "28cdfccd187c18bce6a89198df16406658103710c9b9a15ed9f9cdc2867a0d6f",
|
| 169 |
+
"bytes": 52747
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_fp32-false.json",
|
| 173 |
+
"sha256": "d965ef6240448cabc0b07a4de45251db37e92c9b7b1687b6ca525b635e0df67e",
|
| 174 |
+
"bytes": 53728
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_fp32-true.json",
|
| 178 |
+
"sha256": "95f39c2961a5104797090979ad51505d9d4142ca7c7601579c7f59f0de9a9180",
|
| 179 |
+
"bytes": 53081
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_ptq-false.json",
|
| 183 |
+
"sha256": "a8f921873c0a02bb6d6627791e533048599a2cc9d8af7493703a8908d23c78a3",
|
| 184 |
+
"bytes": 53532
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_ptq-true.json",
|
| 188 |
+
"sha256": "132c3c64509325f74d412d7fdcbe82b26fae63263283da0a2236d085206dd0fd",
|
| 189 |
+
"bytes": 52899
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_qat-false.json",
|
| 193 |
+
"sha256": "0ab759c3016e7e03a31dfbf3af04394577d03b6d30e55c910ff0496ae8a81e59",
|
| 194 |
+
"bytes": 53701
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-feedback_qat-true.json",
|
| 198 |
+
"sha256": "ee6a1f02091dec3cd072597e90f21af9d0156473972f5dde102bb8c3111eb790",
|
| 199 |
+
"bytes": 53056
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-parent_fp32-false.json",
|
| 203 |
+
"sha256": "cf7e4c8441f90f1f401d39ed42451243c4fd120e15a6890c3595e95edd3ae404",
|
| 204 |
+
"bytes": 53541
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-en-contradictory-parent_fp32-true.json",
|
| 208 |
+
"sha256": "1be13d26e7ba4b31175e5c414213d94a3b417ea1b0cb78512acbd2e54dc1b423",
|
| 209 |
+
"bytes": 52900
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_fp32-false.json",
|
| 213 |
+
"sha256": "a33c04afa05bd6403aa50e4eb8a1a02d448bea6a276d84e135e94394bfc6f653",
|
| 214 |
+
"bytes": 53634
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_fp32-true.json",
|
| 218 |
+
"sha256": "1a8bf50e18662ab8ab44fc788e9382917295d1b6a4e91ce0766f3f31969a244c",
|
| 219 |
+
"bytes": 52959
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_ptq-false.json",
|
| 223 |
+
"sha256": "17aa26501b2f5df7cac081e9c3f3f3c9f0d741cbf7e48ab476e9e12cacddf7cc",
|
| 224 |
+
"bytes": 53567
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_ptq-true.json",
|
| 228 |
+
"sha256": "15c8ea4843767eb6bbe3f9599e6c24b14c9dfd2bd3b6c9dd06a31572bc61a72a",
|
| 229 |
+
"bytes": 52919
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_qat-false.json",
|
| 233 |
+
"sha256": "9d02b37e1cb655634daf2bda8220749fef177492ec12cffa8da3ddddb3540cb3",
|
| 234 |
+
"bytes": 53672
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-feedback_qat-true.json",
|
| 238 |
+
"sha256": "013aeb8e575a069868b577efce263e1226f5baa9789a4a0bf68b89ab5bc55467",
|
| 239 |
+
"bytes": 53004
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-parent_fp32-false.json",
|
| 243 |
+
"sha256": "fed8a744f010717c195b35628f847ba879ae7af385a70181115ad897ac418224",
|
| 244 |
+
"bytes": 53509
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/captures/reference_schedule-0-ko-contradictory-parent_fp32-true.json",
|
| 248 |
+
"sha256": "437e963896e4c0057c30a25ad9acb7eb6b928826e972e8e577c0bb4090474791",
|
| 249 |
+
"bytes": 52869
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/executions/465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81.json",
|
| 253 |
+
"sha256": "53b274355168c76e1f78878249d34addc8610aa36bff927558955c2dbaa345fd",
|
| 254 |
+
"bytes": 52
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/executions/62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6.json",
|
| 258 |
+
"sha256": "c0409168c097b3050fb89ccb2d202bda3f501af64ac0512ff7ad560693c16049",
|
| 259 |
+
"bytes": 68
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/executions/fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4.json",
|
| 263 |
+
"sha256": "5cc1236302b066935711f61756705568c0fb1c995a3245ee8e4d9125fa86af3b",
|
| 264 |
+
"bytes": 55
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_fp32-false.json",
|
| 268 |
+
"sha256": "6967e95c9c5f70ee7672594c68a39b131cfe05fea552c2c67dc39aabd4dee7af",
|
| 269 |
+
"bytes": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_fp32-true.json",
|
| 273 |
+
"sha256": "4332926a07e991601f722dd88ce70a898200aabf94e325c09649f8e680b35ef1",
|
| 274 |
+
"bytes": 180
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_ptq-false.json",
|
| 278 |
+
"sha256": "a19afc29890770a04e979baceabd7e1bc74f263d87a9fcbefa14a7f2659250a1",
|
| 279 |
+
"bytes": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_ptq-true.json",
|
| 283 |
+
"sha256": "1832ddd08c35d96ff287a9a93ef6a3e70eba4a27eb933299dff5ad65389541eb",
|
| 284 |
+
"bytes": 180
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_qat-false.json",
|
| 288 |
+
"sha256": "4bc4df4d83bcc7ba95582b447f5df0b1c131e26c609a4f5c0fa0abfd6d2ad49e",
|
| 289 |
+
"bytes": 179
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-feedback_qat-true.json",
|
| 293 |
+
"sha256": "49aae2fc9e349dfa208f306b23fe417f8cd5eed63c69dd7d0f9c692e8ab41d6e",
|
| 294 |
+
"bytes": 180
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-parent_fp32-false.json",
|
| 298 |
+
"sha256": "756ea958e139aefad52c71435baa7f2e5b9f157bb176166c05ce238671781ca0",
|
| 299 |
+
"bytes": 180
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-en-contradictory-parent_fp32-true.json",
|
| 303 |
+
"sha256": "c40a259422e0524354f13765cabe130ede819a98eac9d9afd44083e1a3ef018e",
|
| 304 |
+
"bytes": 180
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_fp32-false.json",
|
| 308 |
+
"sha256": "fed1c5e6a03f85700047f2f79b45d7cbf276697dd726f247bf030058647b2644",
|
| 309 |
+
"bytes": 180
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_fp32-true.json",
|
| 313 |
+
"sha256": "d211ba66c11ba892971adb3383e15c71ca214b2190db6ab4a4b4e24a54d7e575",
|
| 314 |
+
"bytes": 180
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_ptq-false.json",
|
| 318 |
+
"sha256": "fb863ef774c7ab51378cdf85b16956a14fe26177447dda4267a71694217b7963",
|
| 319 |
+
"bytes": 180
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_ptq-true.json",
|
| 323 |
+
"sha256": "51094d13b83213142f2ba7d269a57ee1c9e1753af824a919386ece6471e83630",
|
| 324 |
+
"bytes": 180
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_qat-false.json",
|
| 328 |
+
"sha256": "c80e6e97a05a623313b24b74966695cda4cbd62de5cd181632cf902e1b259010",
|
| 329 |
+
"bytes": 180
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-feedback_qat-true.json",
|
| 333 |
+
"sha256": "bbf94be41fa1b1e5b04d0e185e26a925e7edf6ac522cf1eb5db02b6bd070598e",
|
| 334 |
+
"bytes": 180
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-parent_fp32-false.json",
|
| 338 |
+
"sha256": "95b1299531571db46f107a6dbe314fe78739804c72cf08285409b0449ffd4a1d",
|
| 339 |
+
"bytes": 180
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/operand_branch-0-ko-contradictory-parent_fp32-true.json",
|
| 343 |
+
"sha256": "66664bc981b81ca4cb2a6902e89e9fc167417081ec962fdff32593e35a6e220e",
|
| 344 |
+
"bytes": 180
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_fp32-false.json",
|
| 348 |
+
"sha256": "4ed218b979871a1e05e4010664cf99f3920e7e84281ca95c9e050d258912bd05",
|
| 349 |
+
"bytes": 180
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_fp32-true.json",
|
| 353 |
+
"sha256": "2f13ce76cea8e08290de6aaa026ce080be7c3826a0e3d369da8ff5742bfaead0",
|
| 354 |
+
"bytes": 180
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_ptq-false.json",
|
| 358 |
+
"sha256": "aea67403569b4590e37f993099c8d810e1106a4dbf5abb348a654949a78c9b4a",
|
| 359 |
+
"bytes": 180
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_ptq-true.json",
|
| 363 |
+
"sha256": "9f3a415e23f5b183c30b2a70b3d1aafc8d4c16a77237aa4e8fb36cdeee096c30",
|
| 364 |
+
"bytes": 179
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_qat-false.json",
|
| 368 |
+
"sha256": "f6b4207f12d15aadaefb8224319a9a27fd7cba821ac644c036552cf37dc35459",
|
| 369 |
+
"bytes": 180
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-feedback_qat-true.json",
|
| 373 |
+
"sha256": "5a794fa3466be9b38cb263979ae78c4be96689df69527c2089cf95def4c98412",
|
| 374 |
+
"bytes": 180
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-parent_fp32-false.json",
|
| 378 |
+
"sha256": "9dcdfadfca4ac32d1f22daa033875309c9dad2f469440ce11ecf30f94570c028",
|
| 379 |
+
"bytes": 180
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-en-contradictory-parent_fp32-true.json",
|
| 383 |
+
"sha256": "8a850aab41414053a3a15d6292d24943d12cfb090dbe9f22e8119fabdb67a26e",
|
| 384 |
+
"bytes": 180
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_fp32-false.json",
|
| 388 |
+
"sha256": "7e5368690fb4a927e8772e554c73e8dc08f3a1b26ee293758a86533d18b4e564",
|
| 389 |
+
"bytes": 180
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_fp32-true.json",
|
| 393 |
+
"sha256": "3e70ceacfff73c114e5efefff016d020bce6f14bb3e07864f854fc68d3b0f840",
|
| 394 |
+
"bytes": 179
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_ptq-false.json",
|
| 398 |
+
"sha256": "5623aacf8dcda0576bbd255b7e9cf9c6d38781be8d52f82237b3db55d6f60c61",
|
| 399 |
+
"bytes": 180
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_ptq-true.json",
|
| 403 |
+
"sha256": "97ede9c1afea6b8fc9c89fe99d25950a01ae2b139e265c524c61ef297de0eb6b",
|
| 404 |
+
"bytes": 180
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_qat-false.json",
|
| 408 |
+
"sha256": "54f51ab33b99da09bb92bde7d4ccb90f0589dd70d665299c6d72b3ac6ecec09f",
|
| 409 |
+
"bytes": 180
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-feedback_qat-true.json",
|
| 413 |
+
"sha256": "b0c8694ab32f6432a5a1552ef01eb361998ac93cd68e46228c320d389a9f7170",
|
| 414 |
+
"bytes": 180
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-parent_fp32-false.json",
|
| 418 |
+
"sha256": "dfa2a19d604200cf12e346ccab74ddcd1b93163de5ae55288824e532e0a7ed27",
|
| 419 |
+
"bytes": 180
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_assignment-0-ko-contradictory-parent_fp32-true.json",
|
| 423 |
+
"sha256": "15faf80c0fdaef2c734b741982f4cc9e4372e19b82eb3c1cc08993a428226b43",
|
| 424 |
+
"bytes": 180
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_fp32-false.json",
|
| 428 |
+
"sha256": "fb0a3d6ce4da6cc3a81851e4c51a5216c38efe27da799b0b53c29b60e06d5c7e",
|
| 429 |
+
"bytes": 180
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_fp32-true.json",
|
| 433 |
+
"sha256": "5cef51cfa0d9ae62509f6f96ba890a20f2097434caf1ca5f2a6543fcfa5f883a",
|
| 434 |
+
"bytes": 180
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_ptq-false.json",
|
| 438 |
+
"sha256": "3b5fa943a9ef71f0de8717ed0976ae2e40f1bc0aef6f14b1cbccfcb53341c2d7",
|
| 439 |
+
"bytes": 180
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_ptq-true.json",
|
| 443 |
+
"sha256": "7392c2536990a09d6bb75efa9f830798469fcdd7da7bed69ea7dd76392ddbc59",
|
| 444 |
+
"bytes": 180
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_qat-false.json",
|
| 448 |
+
"sha256": "3bc6e148ce29f4bc6eff27d54b7827dede77ba2db0451f80a9224face65b7a9d",
|
| 449 |
+
"bytes": 179
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-feedback_qat-true.json",
|
| 453 |
+
"sha256": "116f3b8d8872442f82873bad16149d164c2e1b02b98edbe4572d51977ac0c45f",
|
| 454 |
+
"bytes": 180
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-parent_fp32-false.json",
|
| 458 |
+
"sha256": "2f8c1fbd9a3e77ef9ac507b9300a5605b2e8ff8a7b21d98d38a6d38a46265c93",
|
| 459 |
+
"bytes": 178
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-en-contradictory-parent_fp32-true.json",
|
| 463 |
+
"sha256": "aca827a0b6a7eadbf81fb69b66eed5e5134b117fa31735de6c5a76ef84c63665",
|
| 464 |
+
"bytes": 180
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_fp32-false.json",
|
| 468 |
+
"sha256": "52413760b87289ec1bd6ad96f1a8ebb411fcf6bde834bf4c3ab75460737763a4",
|
| 469 |
+
"bytes": 180
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_fp32-true.json",
|
| 473 |
+
"sha256": "7a63924256a78efee6414796deaede8f5901956147c6487435351fe4dd2ef286",
|
| 474 |
+
"bytes": 180
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_ptq-false.json",
|
| 478 |
+
"sha256": "de067a00f6dba5a1e511d582f02804ffabe685c6e47e57f4416072396c84a71d",
|
| 479 |
+
"bytes": 180
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_ptq-true.json",
|
| 483 |
+
"sha256": "af4a03c52626ff677957b19b1aaa066d0866fedc7117d6f46157bb081ceb7f25",
|
| 484 |
+
"bytes": 180
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_qat-false.json",
|
| 488 |
+
"sha256": "1bfcc402a7ef9221b6f46db17c83e374639835340015d108609ae3ddd23a7dad",
|
| 489 |
+
"bytes": 180
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-feedback_qat-true.json",
|
| 493 |
+
"sha256": "ebe297625e4aa720efa641a9446e799a3be184412f5319ebe55501760377bda2",
|
| 494 |
+
"bytes": 180
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-parent_fp32-false.json",
|
| 498 |
+
"sha256": "0ae37982c99a8a06e1a463245a7a9784d2e95b8a45eca31258008d7d8a7c97df",
|
| 499 |
+
"bytes": 180
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/metrics/reference_schedule-0-ko-contradictory-parent_fp32-true.json",
|
| 503 |
+
"sha256": "8a63e75934e7e030eecb8b1819f720b43239661b5f313be5c939eaceb7df19bf",
|
| 504 |
+
"bytes": 180
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/preexecution.json",
|
| 508 |
+
"sha256": "b7fd3eedddabac4e37864b05a77d6f65e08dd60b1f626bb83134ab1126e8bdd0",
|
| 509 |
+
"bytes": 911
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/report.json",
|
| 513 |
+
"sha256": "4dba2dab42c17af2c069a442b18053fc804bc50a32f5b4276799ddf3f96d3962",
|
| 514 |
+
"bytes": 52460
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"path": "studies/compound-path-v1/cohort.jsonl",
|
| 518 |
+
"sha256": "aefd16b22076c05b113e29df3e7788b06e60e0c5c14e45cc75547bd1e582a15a",
|
| 519 |
+
"bytes": 181860
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"path": "studies/compound-path-v1/manifest.json",
|
| 523 |
+
"sha256": "16adfcf5af4fbf32c8dd2e82476547d62e3c15a4a40f8f05e44e8207b4081e96",
|
| 524 |
+
"bytes": 1325
|
| 525 |
+
}
|
| 526 |
+
],
|
| 527 |
+
"publication_files": [
|
| 528 |
+
{
|
| 529 |
+
"path": "README.md",
|
| 530 |
+
"sha256": "e941f9f9b843bd5b0fac761bb78079420d17afd5607a5595e9f1cb49f9fb3592",
|
| 531 |
+
"bytes": 1159
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"path": "evidence.tar.gz",
|
| 535 |
+
"sha256": "6c24b18fd52a7735f355833b301c92fb81011405cde7726a1d744bb9868e38df",
|
| 536 |
+
"bytes": 369474
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/audit.json",
|
| 540 |
+
"sha256": "4dba2dab42c17af2c069a442b18053fc804bc50a32f5b4276799ddf3f96d3962",
|
| 541 |
+
"bytes": 52460
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"path": "runs/unfixed-native-feature-pilot-20261001/report.json",
|
| 545 |
+
"sha256": "4dba2dab42c17af2c069a442b18053fc804bc50a32f5b4276799ddf3f96d3962",
|
| 546 |
+
"bytes": 52460
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"path": "studies/compound-path-v1/cohort.jsonl",
|
| 550 |
+
"sha256": "aefd16b22076c05b113e29df3e7788b06e60e0c5c14e45cc75547bd1e582a15a",
|
| 551 |
+
"bytes": 181860
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"path": "studies/compound-path-v1/manifest.json",
|
| 555 |
+
"sha256": "16adfcf5af4fbf32c8dd2e82476547d62e3c15a4a40f8f05e44e8207b4081e96",
|
| 556 |
+
"bytes": 1325
|
| 557 |
+
}
|
| 558 |
+
],
|
| 559 |
+
"scope": "Actual native SDK 0.2.7 pilot using own frozen models, six reused bilingual contradictory views and 24 legacy-first pairs. The explicit --path-feedback-unfixed option ranks varying typed coordinates. Raw native bodies, resource sidecars, derived skip receipts, partial finite outcomes and actual emitted-Go values are retained. Caller PASS is unauthenticated context; source CI/GoProof is separate. Feature/main edition is explicit in the prefix and captured compiler SHA. This does not establish arbitrary natural-language accuracy, causal wall speedup, host CPU growth or all-input ordering equivalence. Core weights/card and prior appendices are preserved. No training, GPU work, upstream Laya calls or model/native/Go calls during packaging or offline verification."
|
| 560 |
+
}
|
research/unfixed-native-feature-pilot-20261001/runs/unfixed-native-feature-pilot-20261001/audit.json
ADDED
|
@@ -0,0 +1,1097 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"actual_function_evaluations": 42,
|
| 3 |
+
"actual_go_processes": 3,
|
| 4 |
+
"actual_model_predictions": 264,
|
| 5 |
+
"changed_candidate_sequences": 0,
|
| 6 |
+
"changed_final_body_or_finite_results": 0,
|
| 7 |
+
"decision": "PASS",
|
| 8 |
+
"execution_inputs": [
|
| 9 |
+
-9223372036854775808,
|
| 10 |
+
-100,
|
| 11 |
+
-7,
|
| 12 |
+
-2,
|
| 13 |
+
-1,
|
| 14 |
+
0,
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
3,
|
| 18 |
+
4,
|
| 19 |
+
5,
|
| 20 |
+
8,
|
| 21 |
+
100,
|
| 22 |
+
9223372036854775807
|
| 23 |
+
],
|
| 24 |
+
"files_sha256": {
|
| 25 |
+
"captures/operand_branch-0-en-contradictory-feedback_fp32-false.json": "003e8ed5cae6ededb76d2f061f98272de4df40fdb683b658309e12fc4932f76b",
|
| 26 |
+
"captures/operand_branch-0-en-contradictory-feedback_fp32-true.json": "005733445ba7fe5584ab93ee1b80d2ccfbd0705e1c8d18b414cd881e034c7d48",
|
| 27 |
+
"captures/operand_branch-0-en-contradictory-feedback_ptq-false.json": "01dfc82c3e81dc1186e246526bc044d4a1092e7edbf37f245bd4435515133590",
|
| 28 |
+
"captures/operand_branch-0-en-contradictory-feedback_ptq-true.json": "db55540635d3d03ed9c9f3859fe63a46667cf255c09237a4d80a31360fd5d1fd",
|
| 29 |
+
"captures/operand_branch-0-en-contradictory-feedback_qat-false.json": "795ac720128705d0087952e7576431c9bc0014d793a5ea5c4aead68fcd88d1a1",
|
| 30 |
+
"captures/operand_branch-0-en-contradictory-feedback_qat-true.json": "bed58b193820a4a56ae28d6fdb76180ed72592633292eb933b453cf94264254f",
|
| 31 |
+
"captures/operand_branch-0-en-contradictory-parent_fp32-false.json": "96f440b6cba0ae66082f3b7dc7d7b4c99825e9b19432f72214907cd577fceaca",
|
| 32 |
+
"captures/operand_branch-0-en-contradictory-parent_fp32-true.json": "d249bcc23bd3adc671e229448709abef2e7c3ecfe0491e8fff00fe3adee68587",
|
| 33 |
+
"captures/operand_branch-0-ko-contradictory-feedback_fp32-false.json": "83b9e8319e84a8c618c86a52262f34c900e11874baa91ea3d16783dc3b0aa3bf",
|
| 34 |
+
"captures/operand_branch-0-ko-contradictory-feedback_fp32-true.json": "3dcfec9ce945c2d79ac318b39b614a1732e4f82e96897226ce405b8069e9d5a2",
|
| 35 |
+
"captures/operand_branch-0-ko-contradictory-feedback_ptq-false.json": "3cbd5fdf27d60d9955011af5d01a31845f5064c4ab6b9e1d10747192868bd76c",
|
| 36 |
+
"captures/operand_branch-0-ko-contradictory-feedback_ptq-true.json": "29767e5fadd38eaf741ad2b52a155b370979ffc57d0223307eaca94cb9a21bb7",
|
| 37 |
+
"captures/operand_branch-0-ko-contradictory-feedback_qat-false.json": "3201402e635fc9dd9e1e5391ac9184216dc38e16dc88b678d86b3ea35f451ae1",
|
| 38 |
+
"captures/operand_branch-0-ko-contradictory-feedback_qat-true.json": "e73f643dc5cfc4ec96d9b43fd7c2664b83daa6a3bea0e36d2f94d0d8f1762c77",
|
| 39 |
+
"captures/operand_branch-0-ko-contradictory-parent_fp32-false.json": "c1d0235ec32a594888e09a241a9f9f143cf9c9fe29cdd0ed4ab85b4b5cf32085",
|
| 40 |
+
"captures/operand_branch-0-ko-contradictory-parent_fp32-true.json": "380d81badb208d7acc69774c7db015a2e8464bb1de0269f4da3954a0dcf6c2c6",
|
| 41 |
+
"captures/reference_assignment-0-en-contradictory-feedback_fp32-false.json": "45edd1410f838650c7a6b4430f4cbf6b0ac133632bbfe6d11aee45a97e24a26c",
|
| 42 |
+
"captures/reference_assignment-0-en-contradictory-feedback_fp32-true.json": "5d315109df8b1bdd81d3b7ad379946d149c6dcdd139a6ff6ecc998206933067a",
|
| 43 |
+
"captures/reference_assignment-0-en-contradictory-feedback_ptq-false.json": "bf74ef6a30536f95f93744c7eb127427d8bb5c7e5f8b63887a277c90a568da37",
|
| 44 |
+
"captures/reference_assignment-0-en-contradictory-feedback_ptq-true.json": "4d5fb4cba03f34ae84bdb2e8ac5fdcdbbc50e88676e39b28c4e799123c5381da",
|
| 45 |
+
"captures/reference_assignment-0-en-contradictory-feedback_qat-false.json": "393aa2300be6ecfd16f791b871dd80d908ed5cb5bc70caea92c5097d829d2090",
|
| 46 |
+
"captures/reference_assignment-0-en-contradictory-feedback_qat-true.json": "18ec11e5226b969fe7c64c253fd1c075eefea42fb1eec63299422ba11c83c8b7",
|
| 47 |
+
"captures/reference_assignment-0-en-contradictory-parent_fp32-false.json": "483e5b80f2f5d7149fb89fe05436e4e7c756a8f0100a4ba6424ddb09e153206d",
|
| 48 |
+
"captures/reference_assignment-0-en-contradictory-parent_fp32-true.json": "2c5739db35d5a28f6fd21fcaa5cc01eb7a2367b43a6fb70fbf8e8dafb0ed47d4",
|
| 49 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_fp32-false.json": "d4bc53f9b7485c8bbc2a8c6fc2a3ff0c562520bf967033119ae119f6a8b8fb0d",
|
| 50 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_fp32-true.json": "90d3f115b51277055c2ba5c7aa7ca195199b86d1b0be75df877789c0e4d06b6c",
|
| 51 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_ptq-false.json": "dd8c07106e6152e862fb00d527120e84c7d680f2196579316de443eb607fd597",
|
| 52 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_ptq-true.json": "e3374ff32a28f68999dc7d1cff2d45fe1cfc26d973d4b07c02951a038f42e3fb",
|
| 53 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_qat-false.json": "983bb76c6765cf8a3127785625563d69da51bb882c2d5f01ea9859b7d6b36836",
|
| 54 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_qat-true.json": "69914d48dfe113f155a0599e9fe6fd4b80bb6f3f641f5936399e2d7e77f0103c",
|
| 55 |
+
"captures/reference_assignment-0-ko-contradictory-parent_fp32-false.json": "365e00f0da6f380972f9d05eb3c158eefd353142f2c8219c25e39c866d826fc2",
|
| 56 |
+
"captures/reference_assignment-0-ko-contradictory-parent_fp32-true.json": "28cdfccd187c18bce6a89198df16406658103710c9b9a15ed9f9cdc2867a0d6f",
|
| 57 |
+
"captures/reference_schedule-0-en-contradictory-feedback_fp32-false.json": "d965ef6240448cabc0b07a4de45251db37e92c9b7b1687b6ca525b635e0df67e",
|
| 58 |
+
"captures/reference_schedule-0-en-contradictory-feedback_fp32-true.json": "95f39c2961a5104797090979ad51505d9d4142ca7c7601579c7f59f0de9a9180",
|
| 59 |
+
"captures/reference_schedule-0-en-contradictory-feedback_ptq-false.json": "a8f921873c0a02bb6d6627791e533048599a2cc9d8af7493703a8908d23c78a3",
|
| 60 |
+
"captures/reference_schedule-0-en-contradictory-feedback_ptq-true.json": "132c3c64509325f74d412d7fdcbe82b26fae63263283da0a2236d085206dd0fd",
|
| 61 |
+
"captures/reference_schedule-0-en-contradictory-feedback_qat-false.json": "0ab759c3016e7e03a31dfbf3af04394577d03b6d30e55c910ff0496ae8a81e59",
|
| 62 |
+
"captures/reference_schedule-0-en-contradictory-feedback_qat-true.json": "ee6a1f02091dec3cd072597e90f21af9d0156473972f5dde102bb8c3111eb790",
|
| 63 |
+
"captures/reference_schedule-0-en-contradictory-parent_fp32-false.json": "cf7e4c8441f90f1f401d39ed42451243c4fd120e15a6890c3595e95edd3ae404",
|
| 64 |
+
"captures/reference_schedule-0-en-contradictory-parent_fp32-true.json": "1be13d26e7ba4b31175e5c414213d94a3b417ea1b0cb78512acbd2e54dc1b423",
|
| 65 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_fp32-false.json": "a33c04afa05bd6403aa50e4eb8a1a02d448bea6a276d84e135e94394bfc6f653",
|
| 66 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_fp32-true.json": "1a8bf50e18662ab8ab44fc788e9382917295d1b6a4e91ce0766f3f31969a244c",
|
| 67 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_ptq-false.json": "17aa26501b2f5df7cac081e9c3f3f3c9f0d741cbf7e48ab476e9e12cacddf7cc",
|
| 68 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_ptq-true.json": "15c8ea4843767eb6bbe3f9599e6c24b14c9dfd2bd3b6c9dd06a31572bc61a72a",
|
| 69 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_qat-false.json": "9d02b37e1cb655634daf2bda8220749fef177492ec12cffa8da3ddddb3540cb3",
|
| 70 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_qat-true.json": "013aeb8e575a069868b577efce263e1226f5baa9789a4a0bf68b89ab5bc55467",
|
| 71 |
+
"captures/reference_schedule-0-ko-contradictory-parent_fp32-false.json": "fed8a744f010717c195b35628f847ba879ae7af385a70181115ad897ac418224",
|
| 72 |
+
"captures/reference_schedule-0-ko-contradictory-parent_fp32-true.json": "437e963896e4c0057c30a25ad9acb7eb6b928826e972e8e577c0bb4090474791",
|
| 73 |
+
"executions/465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81.json": "53b274355168c76e1f78878249d34addc8610aa36bff927558955c2dbaa345fd",
|
| 74 |
+
"executions/62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6.json": "c0409168c097b3050fb89ccb2d202bda3f501af64ac0512ff7ad560693c16049",
|
| 75 |
+
"executions/fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4.json": "5cc1236302b066935711f61756705568c0fb1c995a3245ee8e4d9125fa86af3b",
|
| 76 |
+
"metrics/operand_branch-0-en-contradictory-feedback_fp32-false.json": "6967e95c9c5f70ee7672594c68a39b131cfe05fea552c2c67dc39aabd4dee7af",
|
| 77 |
+
"metrics/operand_branch-0-en-contradictory-feedback_fp32-true.json": "4332926a07e991601f722dd88ce70a898200aabf94e325c09649f8e680b35ef1",
|
| 78 |
+
"metrics/operand_branch-0-en-contradictory-feedback_ptq-false.json": "a19afc29890770a04e979baceabd7e1bc74f263d87a9fcbefa14a7f2659250a1",
|
| 79 |
+
"metrics/operand_branch-0-en-contradictory-feedback_ptq-true.json": "1832ddd08c35d96ff287a9a93ef6a3e70eba4a27eb933299dff5ad65389541eb",
|
| 80 |
+
"metrics/operand_branch-0-en-contradictory-feedback_qat-false.json": "4bc4df4d83bcc7ba95582b447f5df0b1c131e26c609a4f5c0fa0abfd6d2ad49e",
|
| 81 |
+
"metrics/operand_branch-0-en-contradictory-feedback_qat-true.json": "49aae2fc9e349dfa208f306b23fe417f8cd5eed63c69dd7d0f9c692e8ab41d6e",
|
| 82 |
+
"metrics/operand_branch-0-en-contradictory-parent_fp32-false.json": "756ea958e139aefad52c71435baa7f2e5b9f157bb176166c05ce238671781ca0",
|
| 83 |
+
"metrics/operand_branch-0-en-contradictory-parent_fp32-true.json": "c40a259422e0524354f13765cabe130ede819a98eac9d9afd44083e1a3ef018e",
|
| 84 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_fp32-false.json": "fed1c5e6a03f85700047f2f79b45d7cbf276697dd726f247bf030058647b2644",
|
| 85 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_fp32-true.json": "d211ba66c11ba892971adb3383e15c71ca214b2190db6ab4a4b4e24a54d7e575",
|
| 86 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_ptq-false.json": "fb863ef774c7ab51378cdf85b16956a14fe26177447dda4267a71694217b7963",
|
| 87 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_ptq-true.json": "51094d13b83213142f2ba7d269a57ee1c9e1753af824a919386ece6471e83630",
|
| 88 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_qat-false.json": "c80e6e97a05a623313b24b74966695cda4cbd62de5cd181632cf902e1b259010",
|
| 89 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_qat-true.json": "bbf94be41fa1b1e5b04d0e185e26a925e7edf6ac522cf1eb5db02b6bd070598e",
|
| 90 |
+
"metrics/operand_branch-0-ko-contradictory-parent_fp32-false.json": "95b1299531571db46f107a6dbe314fe78739804c72cf08285409b0449ffd4a1d",
|
| 91 |
+
"metrics/operand_branch-0-ko-contradictory-parent_fp32-true.json": "66664bc981b81ca4cb2a6902e89e9fc167417081ec962fdff32593e35a6e220e",
|
| 92 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_fp32-false.json": "4ed218b979871a1e05e4010664cf99f3920e7e84281ca95c9e050d258912bd05",
|
| 93 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_fp32-true.json": "2f13ce76cea8e08290de6aaa026ce080be7c3826a0e3d369da8ff5742bfaead0",
|
| 94 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_ptq-false.json": "aea67403569b4590e37f993099c8d810e1106a4dbf5abb348a654949a78c9b4a",
|
| 95 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_ptq-true.json": "9f3a415e23f5b183c30b2a70b3d1aafc8d4c16a77237aa4e8fb36cdeee096c30",
|
| 96 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_qat-false.json": "f6b4207f12d15aadaefb8224319a9a27fd7cba821ac644c036552cf37dc35459",
|
| 97 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_qat-true.json": "5a794fa3466be9b38cb263979ae78c4be96689df69527c2089cf95def4c98412",
|
| 98 |
+
"metrics/reference_assignment-0-en-contradictory-parent_fp32-false.json": "9dcdfadfca4ac32d1f22daa033875309c9dad2f469440ce11ecf30f94570c028",
|
| 99 |
+
"metrics/reference_assignment-0-en-contradictory-parent_fp32-true.json": "8a850aab41414053a3a15d6292d24943d12cfb090dbe9f22e8119fabdb67a26e",
|
| 100 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_fp32-false.json": "7e5368690fb4a927e8772e554c73e8dc08f3a1b26ee293758a86533d18b4e564",
|
| 101 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_fp32-true.json": "3e70ceacfff73c114e5efefff016d020bce6f14bb3e07864f854fc68d3b0f840",
|
| 102 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_ptq-false.json": "5623aacf8dcda0576bbd255b7e9cf9c6d38781be8d52f82237b3db55d6f60c61",
|
| 103 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_ptq-true.json": "97ede9c1afea6b8fc9c89fe99d25950a01ae2b139e265c524c61ef297de0eb6b",
|
| 104 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_qat-false.json": "54f51ab33b99da09bb92bde7d4ccb90f0589dd70d665299c6d72b3ac6ecec09f",
|
| 105 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_qat-true.json": "b0c8694ab32f6432a5a1552ef01eb361998ac93cd68e46228c320d389a9f7170",
|
| 106 |
+
"metrics/reference_assignment-0-ko-contradictory-parent_fp32-false.json": "dfa2a19d604200cf12e346ccab74ddcd1b93163de5ae55288824e532e0a7ed27",
|
| 107 |
+
"metrics/reference_assignment-0-ko-contradictory-parent_fp32-true.json": "15faf80c0fdaef2c734b741982f4cc9e4372e19b82eb3c1cc08993a428226b43",
|
| 108 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_fp32-false.json": "fb0a3d6ce4da6cc3a81851e4c51a5216c38efe27da799b0b53c29b60e06d5c7e",
|
| 109 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_fp32-true.json": "5cef51cfa0d9ae62509f6f96ba890a20f2097434caf1ca5f2a6543fcfa5f883a",
|
| 110 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_ptq-false.json": "3b5fa943a9ef71f0de8717ed0976ae2e40f1bc0aef6f14b1cbccfcb53341c2d7",
|
| 111 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_ptq-true.json": "7392c2536990a09d6bb75efa9f830798469fcdd7da7bed69ea7dd76392ddbc59",
|
| 112 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_qat-false.json": "3bc6e148ce29f4bc6eff27d54b7827dede77ba2db0451f80a9224face65b7a9d",
|
| 113 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_qat-true.json": "116f3b8d8872442f82873bad16149d164c2e1b02b98edbe4572d51977ac0c45f",
|
| 114 |
+
"metrics/reference_schedule-0-en-contradictory-parent_fp32-false.json": "2f8c1fbd9a3e77ef9ac507b9300a5605b2e8ff8a7b21d98d38a6d38a46265c93",
|
| 115 |
+
"metrics/reference_schedule-0-en-contradictory-parent_fp32-true.json": "aca827a0b6a7eadbf81fb69b66eed5e5134b117fa31735de6c5a76ef84c63665",
|
| 116 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_fp32-false.json": "52413760b87289ec1bd6ad96f1a8ebb411fcf6bde834bf4c3ab75460737763a4",
|
| 117 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_fp32-true.json": "7a63924256a78efee6414796deaede8f5901956147c6487435351fe4dd2ef286",
|
| 118 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_ptq-false.json": "de067a00f6dba5a1e511d582f02804ffabe685c6e47e57f4416072396c84a71d",
|
| 119 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_ptq-true.json": "af4a03c52626ff677957b19b1aaa066d0866fedc7117d6f46157bb081ceb7f25",
|
| 120 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_qat-false.json": "1bfcc402a7ef9221b6f46db17c83e374639835340015d108609ae3ddd23a7dad",
|
| 121 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_qat-true.json": "ebe297625e4aa720efa641a9446e799a3be184412f5319ebe55501760377bda2",
|
| 122 |
+
"metrics/reference_schedule-0-ko-contradictory-parent_fp32-false.json": "0ae37982c99a8a06e1a463245a7a9784d2e95b8a45eca31258008d7d8a7c97df",
|
| 123 |
+
"metrics/reference_schedule-0-ko-contradictory-parent_fp32-true.json": "8a63e75934e7e030eecb8b1819f720b43239661b5f313be5c939eaceb7df19bf"
|
| 124 |
+
},
|
| 125 |
+
"legacy_predictions": 144,
|
| 126 |
+
"native_calls": 48,
|
| 127 |
+
"native_revision": "d869be3219a7798b6cc3b13c31efa8a6d899ae22",
|
| 128 |
+
"observations": [
|
| 129 |
+
{
|
| 130 |
+
"arm": "parent_fp32",
|
| 131 |
+
"candidate_attempts": 4,
|
| 132 |
+
"capture_sha256": "483e5b80f2f5d7149fb89fe05436e4e7c756a8f0100a4ba6424ddb09e153206d",
|
| 133 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 134 |
+
"finite_cases": 8,
|
| 135 |
+
"finite_passed": 7,
|
| 136 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 137 |
+
"id": "reference_assignment-0-en-contradictory-parent_fp32-false",
|
| 138 |
+
"model_predictions": 6,
|
| 139 |
+
"prediction_skips": 0,
|
| 140 |
+
"process_metrics": {
|
| 141 |
+
"wall_ns": 8221417,
|
| 142 |
+
"user_cpu_ns": 4065000,
|
| 143 |
+
"system_cpu_ns": 3249000,
|
| 144 |
+
"child_max_rss_bytes": 17940480,
|
| 145 |
+
"process_cpu_percent_of_one_core_over_wall": 88.96276639416295
|
| 146 |
+
},
|
| 147 |
+
"unfixed": false
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"arm": "parent_fp32",
|
| 151 |
+
"candidate_attempts": 4,
|
| 152 |
+
"capture_sha256": "2c5739db35d5a28f6fd21fcaa5cc01eb7a2367b43a6fb70fbf8e8dafb0ed47d4",
|
| 153 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 154 |
+
"finite_cases": 8,
|
| 155 |
+
"finite_passed": 7,
|
| 156 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 157 |
+
"id": "reference_assignment-0-en-contradictory-parent_fp32-true",
|
| 158 |
+
"model_predictions": 5,
|
| 159 |
+
"prediction_skips": 1,
|
| 160 |
+
"process_metrics": {
|
| 161 |
+
"wall_ns": 6707333,
|
| 162 |
+
"user_cpu_ns": 3860000,
|
| 163 |
+
"system_cpu_ns": 1960000,
|
| 164 |
+
"child_max_rss_bytes": 18071552,
|
| 165 |
+
"process_cpu_percent_of_one_core_over_wall": 86.77070304993057
|
| 166 |
+
},
|
| 167 |
+
"unfixed": true
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"arm": "feedback_fp32",
|
| 171 |
+
"candidate_attempts": 4,
|
| 172 |
+
"capture_sha256": "45edd1410f838650c7a6b4430f4cbf6b0ac133632bbfe6d11aee45a97e24a26c",
|
| 173 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 174 |
+
"finite_cases": 8,
|
| 175 |
+
"finite_passed": 7,
|
| 176 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 177 |
+
"id": "reference_assignment-0-en-contradictory-feedback_fp32-false",
|
| 178 |
+
"model_predictions": 6,
|
| 179 |
+
"prediction_skips": 0,
|
| 180 |
+
"process_metrics": {
|
| 181 |
+
"wall_ns": 5953083,
|
| 182 |
+
"user_cpu_ns": 3501000,
|
| 183 |
+
"system_cpu_ns": 1756000,
|
| 184 |
+
"child_max_rss_bytes": 17940480,
|
| 185 |
+
"process_cpu_percent_of_one_core_over_wall": 88.30718469740805
|
| 186 |
+
},
|
| 187 |
+
"unfixed": false
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"arm": "feedback_fp32",
|
| 191 |
+
"candidate_attempts": 4,
|
| 192 |
+
"capture_sha256": "5d315109df8b1bdd81d3b7ad379946d149c6dcdd139a6ff6ecc998206933067a",
|
| 193 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 194 |
+
"finite_cases": 8,
|
| 195 |
+
"finite_passed": 7,
|
| 196 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 197 |
+
"id": "reference_assignment-0-en-contradictory-feedback_fp32-true",
|
| 198 |
+
"model_predictions": 5,
|
| 199 |
+
"prediction_skips": 1,
|
| 200 |
+
"process_metrics": {
|
| 201 |
+
"wall_ns": 5977375,
|
| 202 |
+
"user_cpu_ns": 3484000,
|
| 203 |
+
"system_cpu_ns": 1788000,
|
| 204 |
+
"child_max_rss_bytes": 17907712,
|
| 205 |
+
"process_cpu_percent_of_one_core_over_wall": 88.19925134360818
|
| 206 |
+
},
|
| 207 |
+
"unfixed": true
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"arm": "feedback_ptq",
|
| 211 |
+
"candidate_attempts": 4,
|
| 212 |
+
"capture_sha256": "bf74ef6a30536f95f93744c7eb127427d8bb5c7e5f8b63887a277c90a568da37",
|
| 213 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 214 |
+
"finite_cases": 8,
|
| 215 |
+
"finite_passed": 7,
|
| 216 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 217 |
+
"id": "reference_assignment-0-en-contradictory-feedback_ptq-false",
|
| 218 |
+
"model_predictions": 6,
|
| 219 |
+
"prediction_skips": 0,
|
| 220 |
+
"process_metrics": {
|
| 221 |
+
"wall_ns": 6003750,
|
| 222 |
+
"user_cpu_ns": 3569000,
|
| 223 |
+
"system_cpu_ns": 1695000,
|
| 224 |
+
"child_max_rss_bytes": 17776640,
|
| 225 |
+
"process_cpu_percent_of_one_core_over_wall": 87.67853424942744
|
| 226 |
+
},
|
| 227 |
+
"unfixed": false
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"arm": "feedback_ptq",
|
| 231 |
+
"candidate_attempts": 4,
|
| 232 |
+
"capture_sha256": "4d5fb4cba03f34ae84bdb2e8ac5fdcdbbc50e88676e39b28c4e799123c5381da",
|
| 233 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 234 |
+
"finite_cases": 8,
|
| 235 |
+
"finite_passed": 7,
|
| 236 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 237 |
+
"id": "reference_assignment-0-en-contradictory-feedback_ptq-true",
|
| 238 |
+
"model_predictions": 5,
|
| 239 |
+
"prediction_skips": 1,
|
| 240 |
+
"process_metrics": {
|
| 241 |
+
"wall_ns": 5880250,
|
| 242 |
+
"user_cpu_ns": 3513000,
|
| 243 |
+
"system_cpu_ns": 1663000,
|
| 244 |
+
"child_max_rss_bytes": 17743872,
|
| 245 |
+
"process_cpu_percent_of_one_core_over_wall": 88.0234683899494
|
| 246 |
+
},
|
| 247 |
+
"unfixed": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"arm": "feedback_qat",
|
| 251 |
+
"candidate_attempts": 4,
|
| 252 |
+
"capture_sha256": "393aa2300be6ecfd16f791b871dd80d908ed5cb5bc70caea92c5097d829d2090",
|
| 253 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 254 |
+
"finite_cases": 8,
|
| 255 |
+
"finite_passed": 7,
|
| 256 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 257 |
+
"id": "reference_assignment-0-en-contradictory-feedback_qat-false",
|
| 258 |
+
"model_predictions": 6,
|
| 259 |
+
"prediction_skips": 0,
|
| 260 |
+
"process_metrics": {
|
| 261 |
+
"wall_ns": 6011250,
|
| 262 |
+
"user_cpu_ns": 3479000,
|
| 263 |
+
"system_cpu_ns": 1731000,
|
| 264 |
+
"child_max_rss_bytes": 17973248,
|
| 265 |
+
"process_cpu_percent_of_one_core_over_wall": 86.67082553545436
|
| 266 |
+
},
|
| 267 |
+
"unfixed": false
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"arm": "feedback_qat",
|
| 271 |
+
"candidate_attempts": 4,
|
| 272 |
+
"capture_sha256": "18ec11e5226b969fe7c64c253fd1c075eefea42fb1eec63299422ba11c83c8b7",
|
| 273 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 274 |
+
"finite_cases": 8,
|
| 275 |
+
"finite_passed": 7,
|
| 276 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 277 |
+
"id": "reference_assignment-0-en-contradictory-feedback_qat-true",
|
| 278 |
+
"model_predictions": 5,
|
| 279 |
+
"prediction_skips": 1,
|
| 280 |
+
"process_metrics": {
|
| 281 |
+
"wall_ns": 6105375,
|
| 282 |
+
"user_cpu_ns": 3522000,
|
| 283 |
+
"system_cpu_ns": 1736000,
|
| 284 |
+
"child_max_rss_bytes": 17874944,
|
| 285 |
+
"process_cpu_percent_of_one_core_over_wall": 86.12083614847573
|
| 286 |
+
},
|
| 287 |
+
"unfixed": true
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"arm": "parent_fp32",
|
| 291 |
+
"candidate_attempts": 4,
|
| 292 |
+
"capture_sha256": "365e00f0da6f380972f9d05eb3c158eefd353142f2c8219c25e39c866d826fc2",
|
| 293 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 294 |
+
"finite_cases": 8,
|
| 295 |
+
"finite_passed": 7,
|
| 296 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 297 |
+
"id": "reference_assignment-0-ko-contradictory-parent_fp32-false",
|
| 298 |
+
"model_predictions": 6,
|
| 299 |
+
"prediction_skips": 0,
|
| 300 |
+
"process_metrics": {
|
| 301 |
+
"wall_ns": 6301666,
|
| 302 |
+
"user_cpu_ns": 3625000,
|
| 303 |
+
"system_cpu_ns": 1806000,
|
| 304 |
+
"child_max_rss_bytes": 18038784,
|
| 305 |
+
"process_cpu_percent_of_one_core_over_wall": 86.18355844311647
|
| 306 |
+
},
|
| 307 |
+
"unfixed": false
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"arm": "parent_fp32",
|
| 311 |
+
"candidate_attempts": 4,
|
| 312 |
+
"capture_sha256": "28cdfccd187c18bce6a89198df16406658103710c9b9a15ed9f9cdc2867a0d6f",
|
| 313 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 314 |
+
"finite_cases": 8,
|
| 315 |
+
"finite_passed": 7,
|
| 316 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 317 |
+
"id": "reference_assignment-0-ko-contradictory-parent_fp32-true",
|
| 318 |
+
"model_predictions": 5,
|
| 319 |
+
"prediction_skips": 1,
|
| 320 |
+
"process_metrics": {
|
| 321 |
+
"wall_ns": 5804958,
|
| 322 |
+
"user_cpu_ns": 3517000,
|
| 323 |
+
"system_cpu_ns": 1644000,
|
| 324 |
+
"child_max_rss_bytes": 17874944,
|
| 325 |
+
"process_cpu_percent_of_one_core_over_wall": 88.90675867077763
|
| 326 |
+
},
|
| 327 |
+
"unfixed": true
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"arm": "feedback_fp32",
|
| 331 |
+
"candidate_attempts": 4,
|
| 332 |
+
"capture_sha256": "d4bc53f9b7485c8bbc2a8c6fc2a3ff0c562520bf967033119ae119f6a8b8fb0d",
|
| 333 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 334 |
+
"finite_cases": 8,
|
| 335 |
+
"finite_passed": 7,
|
| 336 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 337 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_fp32-false",
|
| 338 |
+
"model_predictions": 6,
|
| 339 |
+
"prediction_skips": 0,
|
| 340 |
+
"process_metrics": {
|
| 341 |
+
"wall_ns": 5786750,
|
| 342 |
+
"user_cpu_ns": 3461000,
|
| 343 |
+
"system_cpu_ns": 1602000,
|
| 344 |
+
"child_max_rss_bytes": 17973248,
|
| 345 |
+
"process_cpu_percent_of_one_core_over_wall": 87.49297965179073
|
| 346 |
+
},
|
| 347 |
+
"unfixed": false
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"arm": "feedback_fp32",
|
| 351 |
+
"candidate_attempts": 4,
|
| 352 |
+
"capture_sha256": "90d3f115b51277055c2ba5c7aa7ca195199b86d1b0be75df877789c0e4d06b6c",
|
| 353 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 354 |
+
"finite_cases": 8,
|
| 355 |
+
"finite_passed": 7,
|
| 356 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 357 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_fp32-true",
|
| 358 |
+
"model_predictions": 5,
|
| 359 |
+
"prediction_skips": 1,
|
| 360 |
+
"process_metrics": {
|
| 361 |
+
"wall_ns": 5729917,
|
| 362 |
+
"user_cpu_ns": 3423000,
|
| 363 |
+
"system_cpu_ns": 1549000,
|
| 364 |
+
"child_max_rss_bytes": 17907712,
|
| 365 |
+
"process_cpu_percent_of_one_core_over_wall": 86.7726356245649
|
| 366 |
+
},
|
| 367 |
+
"unfixed": true
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"arm": "feedback_ptq",
|
| 371 |
+
"candidate_attempts": 4,
|
| 372 |
+
"capture_sha256": "dd8c07106e6152e862fb00d527120e84c7d680f2196579316de443eb607fd597",
|
| 373 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 374 |
+
"finite_cases": 8,
|
| 375 |
+
"finite_passed": 7,
|
| 376 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 377 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_ptq-false",
|
| 378 |
+
"model_predictions": 6,
|
| 379 |
+
"prediction_skips": 0,
|
| 380 |
+
"process_metrics": {
|
| 381 |
+
"wall_ns": 6042000,
|
| 382 |
+
"user_cpu_ns": 3556000,
|
| 383 |
+
"system_cpu_ns": 1768000,
|
| 384 |
+
"child_max_rss_bytes": 18038784,
|
| 385 |
+
"process_cpu_percent_of_one_core_over_wall": 88.11651770936776
|
| 386 |
+
},
|
| 387 |
+
"unfixed": false
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"arm": "feedback_ptq",
|
| 391 |
+
"candidate_attempts": 4,
|
| 392 |
+
"capture_sha256": "e3374ff32a28f68999dc7d1cff2d45fe1cfc26d973d4b07c02951a038f42e3fb",
|
| 393 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 394 |
+
"finite_cases": 8,
|
| 395 |
+
"finite_passed": 7,
|
| 396 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 397 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_ptq-true",
|
| 398 |
+
"model_predictions": 5,
|
| 399 |
+
"prediction_skips": 1,
|
| 400 |
+
"process_metrics": {
|
| 401 |
+
"wall_ns": 5867875,
|
| 402 |
+
"user_cpu_ns": 3427000,
|
| 403 |
+
"system_cpu_ns": 1660000,
|
| 404 |
+
"child_max_rss_bytes": 17940480,
|
| 405 |
+
"process_cpu_percent_of_one_core_over_wall": 86.69237159959951
|
| 406 |
+
},
|
| 407 |
+
"unfixed": true
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"arm": "feedback_qat",
|
| 411 |
+
"candidate_attempts": 4,
|
| 412 |
+
"capture_sha256": "983bb76c6765cf8a3127785625563d69da51bb882c2d5f01ea9859b7d6b36836",
|
| 413 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 414 |
+
"finite_cases": 8,
|
| 415 |
+
"finite_passed": 7,
|
| 416 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 417 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_qat-false",
|
| 418 |
+
"model_predictions": 6,
|
| 419 |
+
"prediction_skips": 0,
|
| 420 |
+
"process_metrics": {
|
| 421 |
+
"wall_ns": 5958125,
|
| 422 |
+
"user_cpu_ns": 3475000,
|
| 423 |
+
"system_cpu_ns": 1770000,
|
| 424 |
+
"child_max_rss_bytes": 17989632,
|
| 425 |
+
"process_cpu_percent_of_one_core_over_wall": 88.03105003671457
|
| 426 |
+
},
|
| 427 |
+
"unfixed": false
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"arm": "feedback_qat",
|
| 431 |
+
"candidate_attempts": 4,
|
| 432 |
+
"capture_sha256": "69914d48dfe113f155a0599e9fe6fd4b80bb6f3f641f5936399e2d7e77f0103c",
|
| 433 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 434 |
+
"finite_cases": 8,
|
| 435 |
+
"finite_passed": 7,
|
| 436 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 437 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_qat-true",
|
| 438 |
+
"model_predictions": 5,
|
| 439 |
+
"prediction_skips": 1,
|
| 440 |
+
"process_metrics": {
|
| 441 |
+
"wall_ns": 6001959,
|
| 442 |
+
"user_cpu_ns": 3564000,
|
| 443 |
+
"system_cpu_ns": 1722000,
|
| 444 |
+
"child_max_rss_bytes": 17989632,
|
| 445 |
+
"process_cpu_percent_of_one_core_over_wall": 88.07124473859285
|
| 446 |
+
},
|
| 447 |
+
"unfixed": true
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"arm": "parent_fp32",
|
| 451 |
+
"candidate_attempts": 4,
|
| 452 |
+
"capture_sha256": "96f440b6cba0ae66082f3b7dc7d7b4c99825e9b19432f72214907cd577fceaca",
|
| 453 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 454 |
+
"finite_cases": 8,
|
| 455 |
+
"finite_passed": 7,
|
| 456 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 457 |
+
"id": "operand_branch-0-en-contradictory-parent_fp32-false",
|
| 458 |
+
"model_predictions": 6,
|
| 459 |
+
"prediction_skips": 0,
|
| 460 |
+
"process_metrics": {
|
| 461 |
+
"wall_ns": 6302917,
|
| 462 |
+
"user_cpu_ns": 3754000,
|
| 463 |
+
"system_cpu_ns": 1826000,
|
| 464 |
+
"child_max_rss_bytes": 18186240,
|
| 465 |
+
"process_cpu_percent_of_one_core_over_wall": 88.53043757358697
|
| 466 |
+
},
|
| 467 |
+
"unfixed": false
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"arm": "parent_fp32",
|
| 471 |
+
"candidate_attempts": 4,
|
| 472 |
+
"capture_sha256": "d249bcc23bd3adc671e229448709abef2e7c3ecfe0491e8fff00fe3adee68587",
|
| 473 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 474 |
+
"finite_cases": 8,
|
| 475 |
+
"finite_passed": 7,
|
| 476 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 477 |
+
"id": "operand_branch-0-en-contradictory-parent_fp32-true",
|
| 478 |
+
"model_predictions": 5,
|
| 479 |
+
"prediction_skips": 1,
|
| 480 |
+
"process_metrics": {
|
| 481 |
+
"wall_ns": 5854625,
|
| 482 |
+
"user_cpu_ns": 3555000,
|
| 483 |
+
"system_cpu_ns": 1648000,
|
| 484 |
+
"child_max_rss_bytes": 18137088,
|
| 485 |
+
"process_cpu_percent_of_one_core_over_wall": 88.86991054081174
|
| 486 |
+
},
|
| 487 |
+
"unfixed": true
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"arm": "feedback_fp32",
|
| 491 |
+
"candidate_attempts": 4,
|
| 492 |
+
"capture_sha256": "003e8ed5cae6ededb76d2f061f98272de4df40fdb683b658309e12fc4932f76b",
|
| 493 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 494 |
+
"finite_cases": 8,
|
| 495 |
+
"finite_passed": 7,
|
| 496 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 497 |
+
"id": "operand_branch-0-en-contradictory-feedback_fp32-false",
|
| 498 |
+
"model_predictions": 6,
|
| 499 |
+
"prediction_skips": 0,
|
| 500 |
+
"process_metrics": {
|
| 501 |
+
"wall_ns": 6042542,
|
| 502 |
+
"user_cpu_ns": 3652000,
|
| 503 |
+
"system_cpu_ns": 1668000,
|
| 504 |
+
"child_max_rss_bytes": 17989632,
|
| 505 |
+
"process_cpu_percent_of_one_core_over_wall": 88.04241658560255
|
| 506 |
+
},
|
| 507 |
+
"unfixed": false
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"arm": "feedback_fp32",
|
| 511 |
+
"candidate_attempts": 4,
|
| 512 |
+
"capture_sha256": "005733445ba7fe5584ab93ee1b80d2ccfbd0705e1c8d18b414cd881e034c7d48",
|
| 513 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 514 |
+
"finite_cases": 8,
|
| 515 |
+
"finite_passed": 7,
|
| 516 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 517 |
+
"id": "operand_branch-0-en-contradictory-feedback_fp32-true",
|
| 518 |
+
"model_predictions": 5,
|
| 519 |
+
"prediction_skips": 1,
|
| 520 |
+
"process_metrics": {
|
| 521 |
+
"wall_ns": 5845208,
|
| 522 |
+
"user_cpu_ns": 3528000,
|
| 523 |
+
"system_cpu_ns": 1660000,
|
| 524 |
+
"child_max_rss_bytes": 18104320,
|
| 525 |
+
"process_cpu_percent_of_one_core_over_wall": 88.75646512493653
|
| 526 |
+
},
|
| 527 |
+
"unfixed": true
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"arm": "feedback_ptq",
|
| 531 |
+
"candidate_attempts": 4,
|
| 532 |
+
"capture_sha256": "01dfc82c3e81dc1186e246526bc044d4a1092e7edbf37f245bd4435515133590",
|
| 533 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 534 |
+
"finite_cases": 8,
|
| 535 |
+
"finite_passed": 7,
|
| 536 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 537 |
+
"id": "operand_branch-0-en-contradictory-feedback_ptq-false",
|
| 538 |
+
"model_predictions": 6,
|
| 539 |
+
"prediction_skips": 0,
|
| 540 |
+
"process_metrics": {
|
| 541 |
+
"wall_ns": 6148291,
|
| 542 |
+
"user_cpu_ns": 3584000,
|
| 543 |
+
"system_cpu_ns": 1845000,
|
| 544 |
+
"child_max_rss_bytes": 18055168,
|
| 545 |
+
"process_cpu_percent_of_one_core_over_wall": 88.30096038069766
|
| 546 |
+
},
|
| 547 |
+
"unfixed": false
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"arm": "feedback_ptq",
|
| 551 |
+
"candidate_attempts": 4,
|
| 552 |
+
"capture_sha256": "db55540635d3d03ed9c9f3859fe63a46667cf255c09237a4d80a31360fd5d1fd",
|
| 553 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 554 |
+
"finite_cases": 8,
|
| 555 |
+
"finite_passed": 7,
|
| 556 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 557 |
+
"id": "operand_branch-0-en-contradictory-feedback_ptq-true",
|
| 558 |
+
"model_predictions": 5,
|
| 559 |
+
"prediction_skips": 1,
|
| 560 |
+
"process_metrics": {
|
| 561 |
+
"wall_ns": 6209208,
|
| 562 |
+
"user_cpu_ns": 3653000,
|
| 563 |
+
"system_cpu_ns": 1794000,
|
| 564 |
+
"child_max_rss_bytes": 18055168,
|
| 565 |
+
"process_cpu_percent_of_one_core_over_wall": 87.72455359846215
|
| 566 |
+
},
|
| 567 |
+
"unfixed": true
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"arm": "feedback_qat",
|
| 571 |
+
"candidate_attempts": 4,
|
| 572 |
+
"capture_sha256": "795ac720128705d0087952e7576431c9bc0014d793a5ea5c4aead68fcd88d1a1",
|
| 573 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 574 |
+
"finite_cases": 8,
|
| 575 |
+
"finite_passed": 7,
|
| 576 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 577 |
+
"id": "operand_branch-0-en-contradictory-feedback_qat-false",
|
| 578 |
+
"model_predictions": 6,
|
| 579 |
+
"prediction_skips": 0,
|
| 580 |
+
"process_metrics": {
|
| 581 |
+
"wall_ns": 6328458,
|
| 582 |
+
"user_cpu_ns": 3680000,
|
| 583 |
+
"system_cpu_ns": 1766000,
|
| 584 |
+
"child_max_rss_bytes": 18055168,
|
| 585 |
+
"process_cpu_percent_of_one_core_over_wall": 86.0557184704394
|
| 586 |
+
},
|
| 587 |
+
"unfixed": false
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"arm": "feedback_qat",
|
| 591 |
+
"candidate_attempts": 4,
|
| 592 |
+
"capture_sha256": "bed58b193820a4a56ae28d6fdb76180ed72592633292eb933b453cf94264254f",
|
| 593 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 594 |
+
"finite_cases": 8,
|
| 595 |
+
"finite_passed": 7,
|
| 596 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 597 |
+
"id": "operand_branch-0-en-contradictory-feedback_qat-true",
|
| 598 |
+
"model_predictions": 5,
|
| 599 |
+
"prediction_skips": 1,
|
| 600 |
+
"process_metrics": {
|
| 601 |
+
"wall_ns": 6309333,
|
| 602 |
+
"user_cpu_ns": 3676000,
|
| 603 |
+
"system_cpu_ns": 1826000,
|
| 604 |
+
"child_max_rss_bytes": 17842176,
|
| 605 |
+
"process_cpu_percent_of_one_core_over_wall": 87.20414661898492
|
| 606 |
+
},
|
| 607 |
+
"unfixed": true
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"arm": "parent_fp32",
|
| 611 |
+
"candidate_attempts": 4,
|
| 612 |
+
"capture_sha256": "c1d0235ec32a594888e09a241a9f9f143cf9c9fe29cdd0ed4ab85b4b5cf32085",
|
| 613 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 614 |
+
"finite_cases": 8,
|
| 615 |
+
"finite_passed": 7,
|
| 616 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 617 |
+
"id": "operand_branch-0-ko-contradictory-parent_fp32-false",
|
| 618 |
+
"model_predictions": 6,
|
| 619 |
+
"prediction_skips": 0,
|
| 620 |
+
"process_metrics": {
|
| 621 |
+
"wall_ns": 6099375,
|
| 622 |
+
"user_cpu_ns": 3614000,
|
| 623 |
+
"system_cpu_ns": 1715000,
|
| 624 |
+
"child_max_rss_bytes": 18087936,
|
| 625 |
+
"process_cpu_percent_of_one_core_over_wall": 87.36960754175632
|
| 626 |
+
},
|
| 627 |
+
"unfixed": false
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"arm": "parent_fp32",
|
| 631 |
+
"candidate_attempts": 4,
|
| 632 |
+
"capture_sha256": "380d81badb208d7acc69774c7db015a2e8464bb1de0269f4da3954a0dcf6c2c6",
|
| 633 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 634 |
+
"finite_cases": 8,
|
| 635 |
+
"finite_passed": 7,
|
| 636 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 637 |
+
"id": "operand_branch-0-ko-contradictory-parent_fp32-true",
|
| 638 |
+
"model_predictions": 5,
|
| 639 |
+
"prediction_skips": 1,
|
| 640 |
+
"process_metrics": {
|
| 641 |
+
"wall_ns": 6083458,
|
| 642 |
+
"user_cpu_ns": 3645000,
|
| 643 |
+
"system_cpu_ns": 1711000,
|
| 644 |
+
"child_max_rss_bytes": 18251776,
|
| 645 |
+
"process_cpu_percent_of_one_core_over_wall": 88.04203135782313
|
| 646 |
+
},
|
| 647 |
+
"unfixed": true
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"arm": "feedback_fp32",
|
| 651 |
+
"candidate_attempts": 4,
|
| 652 |
+
"capture_sha256": "83b9e8319e84a8c618c86a52262f34c900e11874baa91ea3d16783dc3b0aa3bf",
|
| 653 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 654 |
+
"finite_cases": 8,
|
| 655 |
+
"finite_passed": 7,
|
| 656 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 657 |
+
"id": "operand_branch-0-ko-contradictory-feedback_fp32-false",
|
| 658 |
+
"model_predictions": 6,
|
| 659 |
+
"prediction_skips": 0,
|
| 660 |
+
"process_metrics": {
|
| 661 |
+
"wall_ns": 5825958,
|
| 662 |
+
"user_cpu_ns": 3481000,
|
| 663 |
+
"system_cpu_ns": 1623000,
|
| 664 |
+
"child_max_rss_bytes": 18219008,
|
| 665 |
+
"process_cpu_percent_of_one_core_over_wall": 87.60790929148476
|
| 666 |
+
},
|
| 667 |
+
"unfixed": false
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"arm": "feedback_fp32",
|
| 671 |
+
"candidate_attempts": 4,
|
| 672 |
+
"capture_sha256": "3dcfec9ce945c2d79ac318b39b614a1732e4f82e96897226ce405b8069e9d5a2",
|
| 673 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 674 |
+
"finite_cases": 8,
|
| 675 |
+
"finite_passed": 7,
|
| 676 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 677 |
+
"id": "operand_branch-0-ko-contradictory-feedback_fp32-true",
|
| 678 |
+
"model_predictions": 5,
|
| 679 |
+
"prediction_skips": 1,
|
| 680 |
+
"process_metrics": {
|
| 681 |
+
"wall_ns": 5724125,
|
| 682 |
+
"user_cpu_ns": 3463000,
|
| 683 |
+
"system_cpu_ns": 1625000,
|
| 684 |
+
"child_max_rss_bytes": 18186240,
|
| 685 |
+
"process_cpu_percent_of_one_core_over_wall": 88.88694778677964
|
| 686 |
+
},
|
| 687 |
+
"unfixed": true
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"arm": "feedback_ptq",
|
| 691 |
+
"candidate_attempts": 4,
|
| 692 |
+
"capture_sha256": "3cbd5fdf27d60d9955011af5d01a31845f5064c4ab6b9e1d10747192868bd76c",
|
| 693 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 694 |
+
"finite_cases": 8,
|
| 695 |
+
"finite_passed": 7,
|
| 696 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 697 |
+
"id": "operand_branch-0-ko-contradictory-feedback_ptq-false",
|
| 698 |
+
"model_predictions": 6,
|
| 699 |
+
"prediction_skips": 0,
|
| 700 |
+
"process_metrics": {
|
| 701 |
+
"wall_ns": 5764125,
|
| 702 |
+
"user_cpu_ns": 3394000,
|
| 703 |
+
"system_cpu_ns": 1662000,
|
| 704 |
+
"child_max_rss_bytes": 17842176,
|
| 705 |
+
"process_cpu_percent_of_one_core_over_wall": 87.71496107388371
|
| 706 |
+
},
|
| 707 |
+
"unfixed": false
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"arm": "feedback_ptq",
|
| 711 |
+
"candidate_attempts": 4,
|
| 712 |
+
"capture_sha256": "29767e5fadd38eaf741ad2b52a155b370979ffc57d0223307eaca94cb9a21bb7",
|
| 713 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 714 |
+
"finite_cases": 8,
|
| 715 |
+
"finite_passed": 7,
|
| 716 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 717 |
+
"id": "operand_branch-0-ko-contradictory-feedback_ptq-true",
|
| 718 |
+
"model_predictions": 5,
|
| 719 |
+
"prediction_skips": 1,
|
| 720 |
+
"process_metrics": {
|
| 721 |
+
"wall_ns": 5918667,
|
| 722 |
+
"user_cpu_ns": 3471000,
|
| 723 |
+
"system_cpu_ns": 1617000,
|
| 724 |
+
"child_max_rss_bytes": 17874944,
|
| 725 |
+
"process_cpu_percent_of_one_core_over_wall": 85.96530266021048
|
| 726 |
+
},
|
| 727 |
+
"unfixed": true
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"arm": "feedback_qat",
|
| 731 |
+
"candidate_attempts": 4,
|
| 732 |
+
"capture_sha256": "3201402e635fc9dd9e1e5391ac9184216dc38e16dc88b678d86b3ea35f451ae1",
|
| 733 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 734 |
+
"finite_cases": 8,
|
| 735 |
+
"finite_passed": 7,
|
| 736 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 737 |
+
"id": "operand_branch-0-ko-contradictory-feedback_qat-false",
|
| 738 |
+
"model_predictions": 6,
|
| 739 |
+
"prediction_skips": 0,
|
| 740 |
+
"process_metrics": {
|
| 741 |
+
"wall_ns": 5747792,
|
| 742 |
+
"user_cpu_ns": 3490000,
|
| 743 |
+
"system_cpu_ns": 1642000,
|
| 744 |
+
"child_max_rss_bytes": 17825792,
|
| 745 |
+
"process_cpu_percent_of_one_core_over_wall": 89.28645991365032
|
| 746 |
+
},
|
| 747 |
+
"unfixed": false
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"arm": "feedback_qat",
|
| 751 |
+
"candidate_attempts": 4,
|
| 752 |
+
"capture_sha256": "e73f643dc5cfc4ec96d9b43fd7c2664b83daa6a3bea0e36d2f94d0d8f1762c77",
|
| 753 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 754 |
+
"finite_cases": 8,
|
| 755 |
+
"finite_passed": 7,
|
| 756 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 757 |
+
"id": "operand_branch-0-ko-contradictory-feedback_qat-true",
|
| 758 |
+
"model_predictions": 5,
|
| 759 |
+
"prediction_skips": 1,
|
| 760 |
+
"process_metrics": {
|
| 761 |
+
"wall_ns": 5979167,
|
| 762 |
+
"user_cpu_ns": 3587000,
|
| 763 |
+
"system_cpu_ns": 1731000,
|
| 764 |
+
"child_max_rss_bytes": 18038784,
|
| 765 |
+
"process_cpu_percent_of_one_core_over_wall": 88.94215532029796
|
| 766 |
+
},
|
| 767 |
+
"unfixed": true
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"arm": "parent_fp32",
|
| 771 |
+
"candidate_attempts": 4,
|
| 772 |
+
"capture_sha256": "cf7e4c8441f90f1f401d39ed42451243c4fd120e15a6890c3595e95edd3ae404",
|
| 773 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 774 |
+
"finite_cases": 8,
|
| 775 |
+
"finite_passed": 7,
|
| 776 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 777 |
+
"id": "reference_schedule-0-en-contradictory-parent_fp32-false",
|
| 778 |
+
"model_predictions": 6,
|
| 779 |
+
"prediction_skips": 0,
|
| 780 |
+
"process_metrics": {
|
| 781 |
+
"wall_ns": 6107708,
|
| 782 |
+
"user_cpu_ns": 3638000,
|
| 783 |
+
"system_cpu_ns": 1745000,
|
| 784 |
+
"child_max_rss_bytes": 17989632,
|
| 785 |
+
"process_cpu_percent_of_one_core_over_wall": 88.134534263917
|
| 786 |
+
},
|
| 787 |
+
"unfixed": false
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"arm": "parent_fp32",
|
| 791 |
+
"candidate_attempts": 4,
|
| 792 |
+
"capture_sha256": "1be13d26e7ba4b31175e5c414213d94a3b417ea1b0cb78512acbd2e54dc1b423",
|
| 793 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 794 |
+
"finite_cases": 8,
|
| 795 |
+
"finite_passed": 7,
|
| 796 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 797 |
+
"id": "reference_schedule-0-en-contradictory-parent_fp32-true",
|
| 798 |
+
"model_predictions": 5,
|
| 799 |
+
"prediction_skips": 1,
|
| 800 |
+
"process_metrics": {
|
| 801 |
+
"wall_ns": 5919083,
|
| 802 |
+
"user_cpu_ns": 3533000,
|
| 803 |
+
"system_cpu_ns": 1744000,
|
| 804 |
+
"child_max_rss_bytes": 18235392,
|
| 805 |
+
"process_cpu_percent_of_one_core_over_wall": 89.15232308788372
|
| 806 |
+
},
|
| 807 |
+
"unfixed": true
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"arm": "feedback_fp32",
|
| 811 |
+
"candidate_attempts": 4,
|
| 812 |
+
"capture_sha256": "d965ef6240448cabc0b07a4de45251db37e92c9b7b1687b6ca525b635e0df67e",
|
| 813 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 814 |
+
"finite_cases": 8,
|
| 815 |
+
"finite_passed": 7,
|
| 816 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 817 |
+
"id": "reference_schedule-0-en-contradictory-feedback_fp32-false",
|
| 818 |
+
"model_predictions": 6,
|
| 819 |
+
"prediction_skips": 0,
|
| 820 |
+
"process_metrics": {
|
| 821 |
+
"wall_ns": 5973917,
|
| 822 |
+
"user_cpu_ns": 3570000,
|
| 823 |
+
"system_cpu_ns": 1685000,
|
| 824 |
+
"child_max_rss_bytes": 17989632,
|
| 825 |
+
"process_cpu_percent_of_one_core_over_wall": 87.96573504452773
|
| 826 |
+
},
|
| 827 |
+
"unfixed": false
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"arm": "feedback_fp32",
|
| 831 |
+
"candidate_attempts": 4,
|
| 832 |
+
"capture_sha256": "95f39c2961a5104797090979ad51505d9d4142ca7c7601579c7f59f0de9a9180",
|
| 833 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 834 |
+
"finite_cases": 8,
|
| 835 |
+
"finite_passed": 7,
|
| 836 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 837 |
+
"id": "reference_schedule-0-en-contradictory-feedback_fp32-true",
|
| 838 |
+
"model_predictions": 5,
|
| 839 |
+
"prediction_skips": 1,
|
| 840 |
+
"process_metrics": {
|
| 841 |
+
"wall_ns": 6099334,
|
| 842 |
+
"user_cpu_ns": 3619000,
|
| 843 |
+
"system_cpu_ns": 1728000,
|
| 844 |
+
"child_max_rss_bytes": 18137088,
|
| 845 |
+
"process_cpu_percent_of_one_core_over_wall": 87.66530903210088
|
| 846 |
+
},
|
| 847 |
+
"unfixed": true
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"arm": "feedback_ptq",
|
| 851 |
+
"candidate_attempts": 4,
|
| 852 |
+
"capture_sha256": "a8f921873c0a02bb6d6627791e533048599a2cc9d8af7493703a8908d23c78a3",
|
| 853 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 854 |
+
"finite_cases": 8,
|
| 855 |
+
"finite_passed": 7,
|
| 856 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 857 |
+
"id": "reference_schedule-0-en-contradictory-feedback_ptq-false",
|
| 858 |
+
"model_predictions": 6,
|
| 859 |
+
"prediction_skips": 0,
|
| 860 |
+
"process_metrics": {
|
| 861 |
+
"wall_ns": 5983500,
|
| 862 |
+
"user_cpu_ns": 3535000,
|
| 863 |
+
"system_cpu_ns": 1727000,
|
| 864 |
+
"child_max_rss_bytes": 17907712,
|
| 865 |
+
"process_cpu_percent_of_one_core_over_wall": 87.94184006016546
|
| 866 |
+
},
|
| 867 |
+
"unfixed": false
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"arm": "feedback_ptq",
|
| 871 |
+
"candidate_attempts": 4,
|
| 872 |
+
"capture_sha256": "132c3c64509325f74d412d7fdcbe82b26fae63263283da0a2236d085206dd0fd",
|
| 873 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 874 |
+
"finite_cases": 8,
|
| 875 |
+
"finite_passed": 7,
|
| 876 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 877 |
+
"id": "reference_schedule-0-en-contradictory-feedback_ptq-true",
|
| 878 |
+
"model_predictions": 5,
|
| 879 |
+
"prediction_skips": 1,
|
| 880 |
+
"process_metrics": {
|
| 881 |
+
"wall_ns": 6132959,
|
| 882 |
+
"user_cpu_ns": 3516000,
|
| 883 |
+
"system_cpu_ns": 2017000,
|
| 884 |
+
"child_max_rss_bytes": 17989632,
|
| 885 |
+
"process_cpu_percent_of_one_core_over_wall": 90.21746272883938
|
| 886 |
+
},
|
| 887 |
+
"unfixed": true
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"arm": "feedback_qat",
|
| 891 |
+
"candidate_attempts": 4,
|
| 892 |
+
"capture_sha256": "0ab759c3016e7e03a31dfbf3af04394577d03b6d30e55c910ff0496ae8a81e59",
|
| 893 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 894 |
+
"finite_cases": 8,
|
| 895 |
+
"finite_passed": 7,
|
| 896 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 897 |
+
"id": "reference_schedule-0-en-contradictory-feedback_qat-false",
|
| 898 |
+
"model_predictions": 6,
|
| 899 |
+
"prediction_skips": 0,
|
| 900 |
+
"process_metrics": {
|
| 901 |
+
"wall_ns": 6239541,
|
| 902 |
+
"user_cpu_ns": 3626000,
|
| 903 |
+
"system_cpu_ns": 1777000,
|
| 904 |
+
"child_max_rss_bytes": 17874944,
|
| 905 |
+
"process_cpu_percent_of_one_core_over_wall": 86.5929080360238
|
| 906 |
+
},
|
| 907 |
+
"unfixed": false
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"arm": "feedback_qat",
|
| 911 |
+
"candidate_attempts": 4,
|
| 912 |
+
"capture_sha256": "ee6a1f02091dec3cd072597e90f21af9d0156473972f5dde102bb8c3111eb790",
|
| 913 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 914 |
+
"finite_cases": 8,
|
| 915 |
+
"finite_passed": 7,
|
| 916 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 917 |
+
"id": "reference_schedule-0-en-contradictory-feedback_qat-true",
|
| 918 |
+
"model_predictions": 5,
|
| 919 |
+
"prediction_skips": 1,
|
| 920 |
+
"process_metrics": {
|
| 921 |
+
"wall_ns": 6005625,
|
| 922 |
+
"user_cpu_ns": 3554000,
|
| 923 |
+
"system_cpu_ns": 1778000,
|
| 924 |
+
"child_max_rss_bytes": 18022400,
|
| 925 |
+
"process_cpu_percent_of_one_core_over_wall": 88.78343219898012
|
| 926 |
+
},
|
| 927 |
+
"unfixed": true
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"arm": "parent_fp32",
|
| 931 |
+
"candidate_attempts": 4,
|
| 932 |
+
"capture_sha256": "fed8a744f010717c195b35628f847ba879ae7af385a70181115ad897ac418224",
|
| 933 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 934 |
+
"finite_cases": 8,
|
| 935 |
+
"finite_passed": 7,
|
| 936 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 937 |
+
"id": "reference_schedule-0-ko-contradictory-parent_fp32-false",
|
| 938 |
+
"model_predictions": 6,
|
| 939 |
+
"prediction_skips": 0,
|
| 940 |
+
"process_metrics": {
|
| 941 |
+
"wall_ns": 6227000,
|
| 942 |
+
"user_cpu_ns": 3653000,
|
| 943 |
+
"system_cpu_ns": 1793000,
|
| 944 |
+
"child_max_rss_bytes": 18071552,
|
| 945 |
+
"process_cpu_percent_of_one_core_over_wall": 87.45784486911836
|
| 946 |
+
},
|
| 947 |
+
"unfixed": false
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"arm": "parent_fp32",
|
| 951 |
+
"candidate_attempts": 4,
|
| 952 |
+
"capture_sha256": "437e963896e4c0057c30a25ad9acb7eb6b928826e972e8e577c0bb4090474791",
|
| 953 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 954 |
+
"finite_cases": 8,
|
| 955 |
+
"finite_passed": 7,
|
| 956 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 957 |
+
"id": "reference_schedule-0-ko-contradictory-parent_fp32-true",
|
| 958 |
+
"model_predictions": 5,
|
| 959 |
+
"prediction_skips": 1,
|
| 960 |
+
"process_metrics": {
|
| 961 |
+
"wall_ns": 6381459,
|
| 962 |
+
"user_cpu_ns": 3808000,
|
| 963 |
+
"system_cpu_ns": 1944000,
|
| 964 |
+
"child_max_rss_bytes": 17924096,
|
| 965 |
+
"process_cpu_percent_of_one_core_over_wall": 90.13612717718628
|
| 966 |
+
},
|
| 967 |
+
"unfixed": true
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"arm": "feedback_fp32",
|
| 971 |
+
"candidate_attempts": 4,
|
| 972 |
+
"capture_sha256": "a33c04afa05bd6403aa50e4eb8a1a02d448bea6a276d84e135e94394bfc6f653",
|
| 973 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 974 |
+
"finite_cases": 8,
|
| 975 |
+
"finite_passed": 7,
|
| 976 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 977 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_fp32-false",
|
| 978 |
+
"model_predictions": 6,
|
| 979 |
+
"prediction_skips": 0,
|
| 980 |
+
"process_metrics": {
|
| 981 |
+
"wall_ns": 6551583,
|
| 982 |
+
"user_cpu_ns": 3919000,
|
| 983 |
+
"system_cpu_ns": 1893000,
|
| 984 |
+
"child_max_rss_bytes": 18169856,
|
| 985 |
+
"process_cpu_percent_of_one_core_over_wall": 88.71138471419808
|
| 986 |
+
},
|
| 987 |
+
"unfixed": false
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"arm": "feedback_fp32",
|
| 991 |
+
"candidate_attempts": 4,
|
| 992 |
+
"capture_sha256": "1a8bf50e18662ab8ab44fc788e9382917295d1b6a4e91ce0766f3f31969a244c",
|
| 993 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 994 |
+
"finite_cases": 8,
|
| 995 |
+
"finite_passed": 7,
|
| 996 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 997 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_fp32-true",
|
| 998 |
+
"model_predictions": 5,
|
| 999 |
+
"prediction_skips": 1,
|
| 1000 |
+
"process_metrics": {
|
| 1001 |
+
"wall_ns": 6157417,
|
| 1002 |
+
"user_cpu_ns": 3697000,
|
| 1003 |
+
"system_cpu_ns": 1719000,
|
| 1004 |
+
"child_max_rss_bytes": 18137088,
|
| 1005 |
+
"process_cpu_percent_of_one_core_over_wall": 87.95896071355895
|
| 1006 |
+
},
|
| 1007 |
+
"unfixed": true
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"arm": "feedback_ptq",
|
| 1011 |
+
"candidate_attempts": 4,
|
| 1012 |
+
"capture_sha256": "17aa26501b2f5df7cac081e9c3f3f3c9f0d741cbf7e48ab476e9e12cacddf7cc",
|
| 1013 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1014 |
+
"finite_cases": 8,
|
| 1015 |
+
"finite_passed": 7,
|
| 1016 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1017 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_ptq-false",
|
| 1018 |
+
"model_predictions": 6,
|
| 1019 |
+
"prediction_skips": 0,
|
| 1020 |
+
"process_metrics": {
|
| 1021 |
+
"wall_ns": 6340375,
|
| 1022 |
+
"user_cpu_ns": 3605000,
|
| 1023 |
+
"system_cpu_ns": 1792000,
|
| 1024 |
+
"child_max_rss_bytes": 17989632,
|
| 1025 |
+
"process_cpu_percent_of_one_core_over_wall": 85.12114819707037
|
| 1026 |
+
},
|
| 1027 |
+
"unfixed": false
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"arm": "feedback_ptq",
|
| 1031 |
+
"candidate_attempts": 4,
|
| 1032 |
+
"capture_sha256": "15c8ea4843767eb6bbe3f9599e6c24b14c9dfd2bd3b6c9dd06a31572bc61a72a",
|
| 1033 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1034 |
+
"finite_cases": 8,
|
| 1035 |
+
"finite_passed": 7,
|
| 1036 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1037 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_ptq-true",
|
| 1038 |
+
"model_predictions": 5,
|
| 1039 |
+
"prediction_skips": 1,
|
| 1040 |
+
"process_metrics": {
|
| 1041 |
+
"wall_ns": 5872542,
|
| 1042 |
+
"user_cpu_ns": 3516000,
|
| 1043 |
+
"system_cpu_ns": 1586000,
|
| 1044 |
+
"child_max_rss_bytes": 17989632,
|
| 1045 |
+
"process_cpu_percent_of_one_core_over_wall": 86.87890184523158
|
| 1046 |
+
},
|
| 1047 |
+
"unfixed": true
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"arm": "feedback_qat",
|
| 1051 |
+
"candidate_attempts": 4,
|
| 1052 |
+
"capture_sha256": "9d02b37e1cb655634daf2bda8220749fef177492ec12cffa8da3ddddb3540cb3",
|
| 1053 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1054 |
+
"finite_cases": 8,
|
| 1055 |
+
"finite_passed": 7,
|
| 1056 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1057 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_qat-false",
|
| 1058 |
+
"model_predictions": 6,
|
| 1059 |
+
"prediction_skips": 0,
|
| 1060 |
+
"process_metrics": {
|
| 1061 |
+
"wall_ns": 6010875,
|
| 1062 |
+
"user_cpu_ns": 3515000,
|
| 1063 |
+
"system_cpu_ns": 1663000,
|
| 1064 |
+
"child_max_rss_bytes": 18022400,
|
| 1065 |
+
"process_cpu_percent_of_one_core_over_wall": 86.14386424605402
|
| 1066 |
+
},
|
| 1067 |
+
"unfixed": false
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"arm": "feedback_qat",
|
| 1071 |
+
"candidate_attempts": 4,
|
| 1072 |
+
"capture_sha256": "013aeb8e575a069868b577efce263e1226f5baa9789a4a0bf68b89ab5bc55467",
|
| 1073 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1074 |
+
"finite_cases": 8,
|
| 1075 |
+
"finite_passed": 7,
|
| 1076 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1077 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_qat-true",
|
| 1078 |
+
"model_predictions": 5,
|
| 1079 |
+
"prediction_skips": 1,
|
| 1080 |
+
"process_metrics": {
|
| 1081 |
+
"wall_ns": 5954584,
|
| 1082 |
+
"user_cpu_ns": 3540000,
|
| 1083 |
+
"system_cpu_ns": 1732000,
|
| 1084 |
+
"child_max_rss_bytes": 18087936,
|
| 1085 |
+
"process_cpu_percent_of_one_core_over_wall": 88.53683145623607
|
| 1086 |
+
},
|
| 1087 |
+
"unfixed": true
|
| 1088 |
+
}
|
| 1089 |
+
],
|
| 1090 |
+
"observed_prediction_skips": 24,
|
| 1091 |
+
"opt_in_predictions": 120,
|
| 1092 |
+
"paired_views": 24,
|
| 1093 |
+
"preexecution_sha256": "b7fd3eedddabac4e37864b05a77d6f65e08dd60b1f626bb83134ab1126e8bdd0",
|
| 1094 |
+
"runner_revision": "3749fdc6c1f218c36d944a7899bb1125061c6906",
|
| 1095 |
+
"schema": "gooo/native-unfixed-pilot/v1",
|
| 1096 |
+
"scope": "Actual clean native SDK 2.7 codegen and own models; six reused bilingual/contradictory views and 24 legacy-first pairs, not independent new tasks. Native bodies are source-bound, type/replay checked and matched to selected typed function AST and independent integer-state oracle. Fixed arm order, whole compiler child resources, no causal speedup or host CPU utilization claim. Go execution deduplicates identical emitted source. Resource sidecars are retained observations. No training, GPU work, upstream Laya calls or source writes; offline audit performs zero inference or subprocess calls."
|
| 1097 |
+
}
|
research/unfixed-native-feature-pilot-20261001/runs/unfixed-native-feature-pilot-20261001/report.json
ADDED
|
@@ -0,0 +1,1097 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"actual_function_evaluations": 42,
|
| 3 |
+
"actual_go_processes": 3,
|
| 4 |
+
"actual_model_predictions": 264,
|
| 5 |
+
"changed_candidate_sequences": 0,
|
| 6 |
+
"changed_final_body_or_finite_results": 0,
|
| 7 |
+
"decision": "PASS",
|
| 8 |
+
"execution_inputs": [
|
| 9 |
+
-9223372036854775808,
|
| 10 |
+
-100,
|
| 11 |
+
-7,
|
| 12 |
+
-2,
|
| 13 |
+
-1,
|
| 14 |
+
0,
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
3,
|
| 18 |
+
4,
|
| 19 |
+
5,
|
| 20 |
+
8,
|
| 21 |
+
100,
|
| 22 |
+
9223372036854775807
|
| 23 |
+
],
|
| 24 |
+
"files_sha256": {
|
| 25 |
+
"captures/operand_branch-0-en-contradictory-feedback_fp32-false.json": "003e8ed5cae6ededb76d2f061f98272de4df40fdb683b658309e12fc4932f76b",
|
| 26 |
+
"captures/operand_branch-0-en-contradictory-feedback_fp32-true.json": "005733445ba7fe5584ab93ee1b80d2ccfbd0705e1c8d18b414cd881e034c7d48",
|
| 27 |
+
"captures/operand_branch-0-en-contradictory-feedback_ptq-false.json": "01dfc82c3e81dc1186e246526bc044d4a1092e7edbf37f245bd4435515133590",
|
| 28 |
+
"captures/operand_branch-0-en-contradictory-feedback_ptq-true.json": "db55540635d3d03ed9c9f3859fe63a46667cf255c09237a4d80a31360fd5d1fd",
|
| 29 |
+
"captures/operand_branch-0-en-contradictory-feedback_qat-false.json": "795ac720128705d0087952e7576431c9bc0014d793a5ea5c4aead68fcd88d1a1",
|
| 30 |
+
"captures/operand_branch-0-en-contradictory-feedback_qat-true.json": "bed58b193820a4a56ae28d6fdb76180ed72592633292eb933b453cf94264254f",
|
| 31 |
+
"captures/operand_branch-0-en-contradictory-parent_fp32-false.json": "96f440b6cba0ae66082f3b7dc7d7b4c99825e9b19432f72214907cd577fceaca",
|
| 32 |
+
"captures/operand_branch-0-en-contradictory-parent_fp32-true.json": "d249bcc23bd3adc671e229448709abef2e7c3ecfe0491e8fff00fe3adee68587",
|
| 33 |
+
"captures/operand_branch-0-ko-contradictory-feedback_fp32-false.json": "83b9e8319e84a8c618c86a52262f34c900e11874baa91ea3d16783dc3b0aa3bf",
|
| 34 |
+
"captures/operand_branch-0-ko-contradictory-feedback_fp32-true.json": "3dcfec9ce945c2d79ac318b39b614a1732e4f82e96897226ce405b8069e9d5a2",
|
| 35 |
+
"captures/operand_branch-0-ko-contradictory-feedback_ptq-false.json": "3cbd5fdf27d60d9955011af5d01a31845f5064c4ab6b9e1d10747192868bd76c",
|
| 36 |
+
"captures/operand_branch-0-ko-contradictory-feedback_ptq-true.json": "29767e5fadd38eaf741ad2b52a155b370979ffc57d0223307eaca94cb9a21bb7",
|
| 37 |
+
"captures/operand_branch-0-ko-contradictory-feedback_qat-false.json": "3201402e635fc9dd9e1e5391ac9184216dc38e16dc88b678d86b3ea35f451ae1",
|
| 38 |
+
"captures/operand_branch-0-ko-contradictory-feedback_qat-true.json": "e73f643dc5cfc4ec96d9b43fd7c2664b83daa6a3bea0e36d2f94d0d8f1762c77",
|
| 39 |
+
"captures/operand_branch-0-ko-contradictory-parent_fp32-false.json": "c1d0235ec32a594888e09a241a9f9f143cf9c9fe29cdd0ed4ab85b4b5cf32085",
|
| 40 |
+
"captures/operand_branch-0-ko-contradictory-parent_fp32-true.json": "380d81badb208d7acc69774c7db015a2e8464bb1de0269f4da3954a0dcf6c2c6",
|
| 41 |
+
"captures/reference_assignment-0-en-contradictory-feedback_fp32-false.json": "45edd1410f838650c7a6b4430f4cbf6b0ac133632bbfe6d11aee45a97e24a26c",
|
| 42 |
+
"captures/reference_assignment-0-en-contradictory-feedback_fp32-true.json": "5d315109df8b1bdd81d3b7ad379946d149c6dcdd139a6ff6ecc998206933067a",
|
| 43 |
+
"captures/reference_assignment-0-en-contradictory-feedback_ptq-false.json": "bf74ef6a30536f95f93744c7eb127427d8bb5c7e5f8b63887a277c90a568da37",
|
| 44 |
+
"captures/reference_assignment-0-en-contradictory-feedback_ptq-true.json": "4d5fb4cba03f34ae84bdb2e8ac5fdcdbbc50e88676e39b28c4e799123c5381da",
|
| 45 |
+
"captures/reference_assignment-0-en-contradictory-feedback_qat-false.json": "393aa2300be6ecfd16f791b871dd80d908ed5cb5bc70caea92c5097d829d2090",
|
| 46 |
+
"captures/reference_assignment-0-en-contradictory-feedback_qat-true.json": "18ec11e5226b969fe7c64c253fd1c075eefea42fb1eec63299422ba11c83c8b7",
|
| 47 |
+
"captures/reference_assignment-0-en-contradictory-parent_fp32-false.json": "483e5b80f2f5d7149fb89fe05436e4e7c756a8f0100a4ba6424ddb09e153206d",
|
| 48 |
+
"captures/reference_assignment-0-en-contradictory-parent_fp32-true.json": "2c5739db35d5a28f6fd21fcaa5cc01eb7a2367b43a6fb70fbf8e8dafb0ed47d4",
|
| 49 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_fp32-false.json": "d4bc53f9b7485c8bbc2a8c6fc2a3ff0c562520bf967033119ae119f6a8b8fb0d",
|
| 50 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_fp32-true.json": "90d3f115b51277055c2ba5c7aa7ca195199b86d1b0be75df877789c0e4d06b6c",
|
| 51 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_ptq-false.json": "dd8c07106e6152e862fb00d527120e84c7d680f2196579316de443eb607fd597",
|
| 52 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_ptq-true.json": "e3374ff32a28f68999dc7d1cff2d45fe1cfc26d973d4b07c02951a038f42e3fb",
|
| 53 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_qat-false.json": "983bb76c6765cf8a3127785625563d69da51bb882c2d5f01ea9859b7d6b36836",
|
| 54 |
+
"captures/reference_assignment-0-ko-contradictory-feedback_qat-true.json": "69914d48dfe113f155a0599e9fe6fd4b80bb6f3f641f5936399e2d7e77f0103c",
|
| 55 |
+
"captures/reference_assignment-0-ko-contradictory-parent_fp32-false.json": "365e00f0da6f380972f9d05eb3c158eefd353142f2c8219c25e39c866d826fc2",
|
| 56 |
+
"captures/reference_assignment-0-ko-contradictory-parent_fp32-true.json": "28cdfccd187c18bce6a89198df16406658103710c9b9a15ed9f9cdc2867a0d6f",
|
| 57 |
+
"captures/reference_schedule-0-en-contradictory-feedback_fp32-false.json": "d965ef6240448cabc0b07a4de45251db37e92c9b7b1687b6ca525b635e0df67e",
|
| 58 |
+
"captures/reference_schedule-0-en-contradictory-feedback_fp32-true.json": "95f39c2961a5104797090979ad51505d9d4142ca7c7601579c7f59f0de9a9180",
|
| 59 |
+
"captures/reference_schedule-0-en-contradictory-feedback_ptq-false.json": "a8f921873c0a02bb6d6627791e533048599a2cc9d8af7493703a8908d23c78a3",
|
| 60 |
+
"captures/reference_schedule-0-en-contradictory-feedback_ptq-true.json": "132c3c64509325f74d412d7fdcbe82b26fae63263283da0a2236d085206dd0fd",
|
| 61 |
+
"captures/reference_schedule-0-en-contradictory-feedback_qat-false.json": "0ab759c3016e7e03a31dfbf3af04394577d03b6d30e55c910ff0496ae8a81e59",
|
| 62 |
+
"captures/reference_schedule-0-en-contradictory-feedback_qat-true.json": "ee6a1f02091dec3cd072597e90f21af9d0156473972f5dde102bb8c3111eb790",
|
| 63 |
+
"captures/reference_schedule-0-en-contradictory-parent_fp32-false.json": "cf7e4c8441f90f1f401d39ed42451243c4fd120e15a6890c3595e95edd3ae404",
|
| 64 |
+
"captures/reference_schedule-0-en-contradictory-parent_fp32-true.json": "1be13d26e7ba4b31175e5c414213d94a3b417ea1b0cb78512acbd2e54dc1b423",
|
| 65 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_fp32-false.json": "a33c04afa05bd6403aa50e4eb8a1a02d448bea6a276d84e135e94394bfc6f653",
|
| 66 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_fp32-true.json": "1a8bf50e18662ab8ab44fc788e9382917295d1b6a4e91ce0766f3f31969a244c",
|
| 67 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_ptq-false.json": "17aa26501b2f5df7cac081e9c3f3f3c9f0d741cbf7e48ab476e9e12cacddf7cc",
|
| 68 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_ptq-true.json": "15c8ea4843767eb6bbe3f9599e6c24b14c9dfd2bd3b6c9dd06a31572bc61a72a",
|
| 69 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_qat-false.json": "9d02b37e1cb655634daf2bda8220749fef177492ec12cffa8da3ddddb3540cb3",
|
| 70 |
+
"captures/reference_schedule-0-ko-contradictory-feedback_qat-true.json": "013aeb8e575a069868b577efce263e1226f5baa9789a4a0bf68b89ab5bc55467",
|
| 71 |
+
"captures/reference_schedule-0-ko-contradictory-parent_fp32-false.json": "fed8a744f010717c195b35628f847ba879ae7af385a70181115ad897ac418224",
|
| 72 |
+
"captures/reference_schedule-0-ko-contradictory-parent_fp32-true.json": "437e963896e4c0057c30a25ad9acb7eb6b928826e972e8e577c0bb4090474791",
|
| 73 |
+
"executions/465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81.json": "53b274355168c76e1f78878249d34addc8610aa36bff927558955c2dbaa345fd",
|
| 74 |
+
"executions/62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6.json": "c0409168c097b3050fb89ccb2d202bda3f501af64ac0512ff7ad560693c16049",
|
| 75 |
+
"executions/fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4.json": "5cc1236302b066935711f61756705568c0fb1c995a3245ee8e4d9125fa86af3b",
|
| 76 |
+
"metrics/operand_branch-0-en-contradictory-feedback_fp32-false.json": "6967e95c9c5f70ee7672594c68a39b131cfe05fea552c2c67dc39aabd4dee7af",
|
| 77 |
+
"metrics/operand_branch-0-en-contradictory-feedback_fp32-true.json": "4332926a07e991601f722dd88ce70a898200aabf94e325c09649f8e680b35ef1",
|
| 78 |
+
"metrics/operand_branch-0-en-contradictory-feedback_ptq-false.json": "a19afc29890770a04e979baceabd7e1bc74f263d87a9fcbefa14a7f2659250a1",
|
| 79 |
+
"metrics/operand_branch-0-en-contradictory-feedback_ptq-true.json": "1832ddd08c35d96ff287a9a93ef6a3e70eba4a27eb933299dff5ad65389541eb",
|
| 80 |
+
"metrics/operand_branch-0-en-contradictory-feedback_qat-false.json": "4bc4df4d83bcc7ba95582b447f5df0b1c131e26c609a4f5c0fa0abfd6d2ad49e",
|
| 81 |
+
"metrics/operand_branch-0-en-contradictory-feedback_qat-true.json": "49aae2fc9e349dfa208f306b23fe417f8cd5eed63c69dd7d0f9c692e8ab41d6e",
|
| 82 |
+
"metrics/operand_branch-0-en-contradictory-parent_fp32-false.json": "756ea958e139aefad52c71435baa7f2e5b9f157bb176166c05ce238671781ca0",
|
| 83 |
+
"metrics/operand_branch-0-en-contradictory-parent_fp32-true.json": "c40a259422e0524354f13765cabe130ede819a98eac9d9afd44083e1a3ef018e",
|
| 84 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_fp32-false.json": "fed1c5e6a03f85700047f2f79b45d7cbf276697dd726f247bf030058647b2644",
|
| 85 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_fp32-true.json": "d211ba66c11ba892971adb3383e15c71ca214b2190db6ab4a4b4e24a54d7e575",
|
| 86 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_ptq-false.json": "fb863ef774c7ab51378cdf85b16956a14fe26177447dda4267a71694217b7963",
|
| 87 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_ptq-true.json": "51094d13b83213142f2ba7d269a57ee1c9e1753af824a919386ece6471e83630",
|
| 88 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_qat-false.json": "c80e6e97a05a623313b24b74966695cda4cbd62de5cd181632cf902e1b259010",
|
| 89 |
+
"metrics/operand_branch-0-ko-contradictory-feedback_qat-true.json": "bbf94be41fa1b1e5b04d0e185e26a925e7edf6ac522cf1eb5db02b6bd070598e",
|
| 90 |
+
"metrics/operand_branch-0-ko-contradictory-parent_fp32-false.json": "95b1299531571db46f107a6dbe314fe78739804c72cf08285409b0449ffd4a1d",
|
| 91 |
+
"metrics/operand_branch-0-ko-contradictory-parent_fp32-true.json": "66664bc981b81ca4cb2a6902e89e9fc167417081ec962fdff32593e35a6e220e",
|
| 92 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_fp32-false.json": "4ed218b979871a1e05e4010664cf99f3920e7e84281ca95c9e050d258912bd05",
|
| 93 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_fp32-true.json": "2f13ce76cea8e08290de6aaa026ce080be7c3826a0e3d369da8ff5742bfaead0",
|
| 94 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_ptq-false.json": "aea67403569b4590e37f993099c8d810e1106a4dbf5abb348a654949a78c9b4a",
|
| 95 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_ptq-true.json": "9f3a415e23f5b183c30b2a70b3d1aafc8d4c16a77237aa4e8fb36cdeee096c30",
|
| 96 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_qat-false.json": "f6b4207f12d15aadaefb8224319a9a27fd7cba821ac644c036552cf37dc35459",
|
| 97 |
+
"metrics/reference_assignment-0-en-contradictory-feedback_qat-true.json": "5a794fa3466be9b38cb263979ae78c4be96689df69527c2089cf95def4c98412",
|
| 98 |
+
"metrics/reference_assignment-0-en-contradictory-parent_fp32-false.json": "9dcdfadfca4ac32d1f22daa033875309c9dad2f469440ce11ecf30f94570c028",
|
| 99 |
+
"metrics/reference_assignment-0-en-contradictory-parent_fp32-true.json": "8a850aab41414053a3a15d6292d24943d12cfb090dbe9f22e8119fabdb67a26e",
|
| 100 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_fp32-false.json": "7e5368690fb4a927e8772e554c73e8dc08f3a1b26ee293758a86533d18b4e564",
|
| 101 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_fp32-true.json": "3e70ceacfff73c114e5efefff016d020bce6f14bb3e07864f854fc68d3b0f840",
|
| 102 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_ptq-false.json": "5623aacf8dcda0576bbd255b7e9cf9c6d38781be8d52f82237b3db55d6f60c61",
|
| 103 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_ptq-true.json": "97ede9c1afea6b8fc9c89fe99d25950a01ae2b139e265c524c61ef297de0eb6b",
|
| 104 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_qat-false.json": "54f51ab33b99da09bb92bde7d4ccb90f0589dd70d665299c6d72b3ac6ecec09f",
|
| 105 |
+
"metrics/reference_assignment-0-ko-contradictory-feedback_qat-true.json": "b0c8694ab32f6432a5a1552ef01eb361998ac93cd68e46228c320d389a9f7170",
|
| 106 |
+
"metrics/reference_assignment-0-ko-contradictory-parent_fp32-false.json": "dfa2a19d604200cf12e346ccab74ddcd1b93163de5ae55288824e532e0a7ed27",
|
| 107 |
+
"metrics/reference_assignment-0-ko-contradictory-parent_fp32-true.json": "15faf80c0fdaef2c734b741982f4cc9e4372e19b82eb3c1cc08993a428226b43",
|
| 108 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_fp32-false.json": "fb0a3d6ce4da6cc3a81851e4c51a5216c38efe27da799b0b53c29b60e06d5c7e",
|
| 109 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_fp32-true.json": "5cef51cfa0d9ae62509f6f96ba890a20f2097434caf1ca5f2a6543fcfa5f883a",
|
| 110 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_ptq-false.json": "3b5fa943a9ef71f0de8717ed0976ae2e40f1bc0aef6f14b1cbccfcb53341c2d7",
|
| 111 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_ptq-true.json": "7392c2536990a09d6bb75efa9f830798469fcdd7da7bed69ea7dd76392ddbc59",
|
| 112 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_qat-false.json": "3bc6e148ce29f4bc6eff27d54b7827dede77ba2db0451f80a9224face65b7a9d",
|
| 113 |
+
"metrics/reference_schedule-0-en-contradictory-feedback_qat-true.json": "116f3b8d8872442f82873bad16149d164c2e1b02b98edbe4572d51977ac0c45f",
|
| 114 |
+
"metrics/reference_schedule-0-en-contradictory-parent_fp32-false.json": "2f8c1fbd9a3e77ef9ac507b9300a5605b2e8ff8a7b21d98d38a6d38a46265c93",
|
| 115 |
+
"metrics/reference_schedule-0-en-contradictory-parent_fp32-true.json": "aca827a0b6a7eadbf81fb69b66eed5e5134b117fa31735de6c5a76ef84c63665",
|
| 116 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_fp32-false.json": "52413760b87289ec1bd6ad96f1a8ebb411fcf6bde834bf4c3ab75460737763a4",
|
| 117 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_fp32-true.json": "7a63924256a78efee6414796deaede8f5901956147c6487435351fe4dd2ef286",
|
| 118 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_ptq-false.json": "de067a00f6dba5a1e511d582f02804ffabe685c6e47e57f4416072396c84a71d",
|
| 119 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_ptq-true.json": "af4a03c52626ff677957b19b1aaa066d0866fedc7117d6f46157bb081ceb7f25",
|
| 120 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_qat-false.json": "1bfcc402a7ef9221b6f46db17c83e374639835340015d108609ae3ddd23a7dad",
|
| 121 |
+
"metrics/reference_schedule-0-ko-contradictory-feedback_qat-true.json": "ebe297625e4aa720efa641a9446e799a3be184412f5319ebe55501760377bda2",
|
| 122 |
+
"metrics/reference_schedule-0-ko-contradictory-parent_fp32-false.json": "0ae37982c99a8a06e1a463245a7a9784d2e95b8a45eca31258008d7d8a7c97df",
|
| 123 |
+
"metrics/reference_schedule-0-ko-contradictory-parent_fp32-true.json": "8a63e75934e7e030eecb8b1819f720b43239661b5f313be5c939eaceb7df19bf"
|
| 124 |
+
},
|
| 125 |
+
"legacy_predictions": 144,
|
| 126 |
+
"native_calls": 48,
|
| 127 |
+
"native_revision": "d869be3219a7798b6cc3b13c31efa8a6d899ae22",
|
| 128 |
+
"observations": [
|
| 129 |
+
{
|
| 130 |
+
"arm": "parent_fp32",
|
| 131 |
+
"candidate_attempts": 4,
|
| 132 |
+
"capture_sha256": "483e5b80f2f5d7149fb89fe05436e4e7c756a8f0100a4ba6424ddb09e153206d",
|
| 133 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 134 |
+
"finite_cases": 8,
|
| 135 |
+
"finite_passed": 7,
|
| 136 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 137 |
+
"id": "reference_assignment-0-en-contradictory-parent_fp32-false",
|
| 138 |
+
"model_predictions": 6,
|
| 139 |
+
"prediction_skips": 0,
|
| 140 |
+
"process_metrics": {
|
| 141 |
+
"wall_ns": 8221417,
|
| 142 |
+
"user_cpu_ns": 4065000,
|
| 143 |
+
"system_cpu_ns": 3249000,
|
| 144 |
+
"child_max_rss_bytes": 17940480,
|
| 145 |
+
"process_cpu_percent_of_one_core_over_wall": 88.96276639416295
|
| 146 |
+
},
|
| 147 |
+
"unfixed": false
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"arm": "parent_fp32",
|
| 151 |
+
"candidate_attempts": 4,
|
| 152 |
+
"capture_sha256": "2c5739db35d5a28f6fd21fcaa5cc01eb7a2367b43a6fb70fbf8e8dafb0ed47d4",
|
| 153 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 154 |
+
"finite_cases": 8,
|
| 155 |
+
"finite_passed": 7,
|
| 156 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 157 |
+
"id": "reference_assignment-0-en-contradictory-parent_fp32-true",
|
| 158 |
+
"model_predictions": 5,
|
| 159 |
+
"prediction_skips": 1,
|
| 160 |
+
"process_metrics": {
|
| 161 |
+
"wall_ns": 6707333,
|
| 162 |
+
"user_cpu_ns": 3860000,
|
| 163 |
+
"system_cpu_ns": 1960000,
|
| 164 |
+
"child_max_rss_bytes": 18071552,
|
| 165 |
+
"process_cpu_percent_of_one_core_over_wall": 86.77070304993057
|
| 166 |
+
},
|
| 167 |
+
"unfixed": true
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"arm": "feedback_fp32",
|
| 171 |
+
"candidate_attempts": 4,
|
| 172 |
+
"capture_sha256": "45edd1410f838650c7a6b4430f4cbf6b0ac133632bbfe6d11aee45a97e24a26c",
|
| 173 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 174 |
+
"finite_cases": 8,
|
| 175 |
+
"finite_passed": 7,
|
| 176 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 177 |
+
"id": "reference_assignment-0-en-contradictory-feedback_fp32-false",
|
| 178 |
+
"model_predictions": 6,
|
| 179 |
+
"prediction_skips": 0,
|
| 180 |
+
"process_metrics": {
|
| 181 |
+
"wall_ns": 5953083,
|
| 182 |
+
"user_cpu_ns": 3501000,
|
| 183 |
+
"system_cpu_ns": 1756000,
|
| 184 |
+
"child_max_rss_bytes": 17940480,
|
| 185 |
+
"process_cpu_percent_of_one_core_over_wall": 88.30718469740805
|
| 186 |
+
},
|
| 187 |
+
"unfixed": false
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"arm": "feedback_fp32",
|
| 191 |
+
"candidate_attempts": 4,
|
| 192 |
+
"capture_sha256": "5d315109df8b1bdd81d3b7ad379946d149c6dcdd139a6ff6ecc998206933067a",
|
| 193 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 194 |
+
"finite_cases": 8,
|
| 195 |
+
"finite_passed": 7,
|
| 196 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 197 |
+
"id": "reference_assignment-0-en-contradictory-feedback_fp32-true",
|
| 198 |
+
"model_predictions": 5,
|
| 199 |
+
"prediction_skips": 1,
|
| 200 |
+
"process_metrics": {
|
| 201 |
+
"wall_ns": 5977375,
|
| 202 |
+
"user_cpu_ns": 3484000,
|
| 203 |
+
"system_cpu_ns": 1788000,
|
| 204 |
+
"child_max_rss_bytes": 17907712,
|
| 205 |
+
"process_cpu_percent_of_one_core_over_wall": 88.19925134360818
|
| 206 |
+
},
|
| 207 |
+
"unfixed": true
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"arm": "feedback_ptq",
|
| 211 |
+
"candidate_attempts": 4,
|
| 212 |
+
"capture_sha256": "bf74ef6a30536f95f93744c7eb127427d8bb5c7e5f8b63887a277c90a568da37",
|
| 213 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 214 |
+
"finite_cases": 8,
|
| 215 |
+
"finite_passed": 7,
|
| 216 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 217 |
+
"id": "reference_assignment-0-en-contradictory-feedback_ptq-false",
|
| 218 |
+
"model_predictions": 6,
|
| 219 |
+
"prediction_skips": 0,
|
| 220 |
+
"process_metrics": {
|
| 221 |
+
"wall_ns": 6003750,
|
| 222 |
+
"user_cpu_ns": 3569000,
|
| 223 |
+
"system_cpu_ns": 1695000,
|
| 224 |
+
"child_max_rss_bytes": 17776640,
|
| 225 |
+
"process_cpu_percent_of_one_core_over_wall": 87.67853424942744
|
| 226 |
+
},
|
| 227 |
+
"unfixed": false
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"arm": "feedback_ptq",
|
| 231 |
+
"candidate_attempts": 4,
|
| 232 |
+
"capture_sha256": "4d5fb4cba03f34ae84bdb2e8ac5fdcdbbc50e88676e39b28c4e799123c5381da",
|
| 233 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 234 |
+
"finite_cases": 8,
|
| 235 |
+
"finite_passed": 7,
|
| 236 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 237 |
+
"id": "reference_assignment-0-en-contradictory-feedback_ptq-true",
|
| 238 |
+
"model_predictions": 5,
|
| 239 |
+
"prediction_skips": 1,
|
| 240 |
+
"process_metrics": {
|
| 241 |
+
"wall_ns": 5880250,
|
| 242 |
+
"user_cpu_ns": 3513000,
|
| 243 |
+
"system_cpu_ns": 1663000,
|
| 244 |
+
"child_max_rss_bytes": 17743872,
|
| 245 |
+
"process_cpu_percent_of_one_core_over_wall": 88.0234683899494
|
| 246 |
+
},
|
| 247 |
+
"unfixed": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"arm": "feedback_qat",
|
| 251 |
+
"candidate_attempts": 4,
|
| 252 |
+
"capture_sha256": "393aa2300be6ecfd16f791b871dd80d908ed5cb5bc70caea92c5097d829d2090",
|
| 253 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 254 |
+
"finite_cases": 8,
|
| 255 |
+
"finite_passed": 7,
|
| 256 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 257 |
+
"id": "reference_assignment-0-en-contradictory-feedback_qat-false",
|
| 258 |
+
"model_predictions": 6,
|
| 259 |
+
"prediction_skips": 0,
|
| 260 |
+
"process_metrics": {
|
| 261 |
+
"wall_ns": 6011250,
|
| 262 |
+
"user_cpu_ns": 3479000,
|
| 263 |
+
"system_cpu_ns": 1731000,
|
| 264 |
+
"child_max_rss_bytes": 17973248,
|
| 265 |
+
"process_cpu_percent_of_one_core_over_wall": 86.67082553545436
|
| 266 |
+
},
|
| 267 |
+
"unfixed": false
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"arm": "feedback_qat",
|
| 271 |
+
"candidate_attempts": 4,
|
| 272 |
+
"capture_sha256": "18ec11e5226b969fe7c64c253fd1c075eefea42fb1eec63299422ba11c83c8b7",
|
| 273 |
+
"case_id": "reference_assignment-0-en-contradictory",
|
| 274 |
+
"finite_cases": 8,
|
| 275 |
+
"finite_passed": 7,
|
| 276 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 277 |
+
"id": "reference_assignment-0-en-contradictory-feedback_qat-true",
|
| 278 |
+
"model_predictions": 5,
|
| 279 |
+
"prediction_skips": 1,
|
| 280 |
+
"process_metrics": {
|
| 281 |
+
"wall_ns": 6105375,
|
| 282 |
+
"user_cpu_ns": 3522000,
|
| 283 |
+
"system_cpu_ns": 1736000,
|
| 284 |
+
"child_max_rss_bytes": 17874944,
|
| 285 |
+
"process_cpu_percent_of_one_core_over_wall": 86.12083614847573
|
| 286 |
+
},
|
| 287 |
+
"unfixed": true
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"arm": "parent_fp32",
|
| 291 |
+
"candidate_attempts": 4,
|
| 292 |
+
"capture_sha256": "365e00f0da6f380972f9d05eb3c158eefd353142f2c8219c25e39c866d826fc2",
|
| 293 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 294 |
+
"finite_cases": 8,
|
| 295 |
+
"finite_passed": 7,
|
| 296 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 297 |
+
"id": "reference_assignment-0-ko-contradictory-parent_fp32-false",
|
| 298 |
+
"model_predictions": 6,
|
| 299 |
+
"prediction_skips": 0,
|
| 300 |
+
"process_metrics": {
|
| 301 |
+
"wall_ns": 6301666,
|
| 302 |
+
"user_cpu_ns": 3625000,
|
| 303 |
+
"system_cpu_ns": 1806000,
|
| 304 |
+
"child_max_rss_bytes": 18038784,
|
| 305 |
+
"process_cpu_percent_of_one_core_over_wall": 86.18355844311647
|
| 306 |
+
},
|
| 307 |
+
"unfixed": false
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"arm": "parent_fp32",
|
| 311 |
+
"candidate_attempts": 4,
|
| 312 |
+
"capture_sha256": "28cdfccd187c18bce6a89198df16406658103710c9b9a15ed9f9cdc2867a0d6f",
|
| 313 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 314 |
+
"finite_cases": 8,
|
| 315 |
+
"finite_passed": 7,
|
| 316 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 317 |
+
"id": "reference_assignment-0-ko-contradictory-parent_fp32-true",
|
| 318 |
+
"model_predictions": 5,
|
| 319 |
+
"prediction_skips": 1,
|
| 320 |
+
"process_metrics": {
|
| 321 |
+
"wall_ns": 5804958,
|
| 322 |
+
"user_cpu_ns": 3517000,
|
| 323 |
+
"system_cpu_ns": 1644000,
|
| 324 |
+
"child_max_rss_bytes": 17874944,
|
| 325 |
+
"process_cpu_percent_of_one_core_over_wall": 88.90675867077763
|
| 326 |
+
},
|
| 327 |
+
"unfixed": true
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"arm": "feedback_fp32",
|
| 331 |
+
"candidate_attempts": 4,
|
| 332 |
+
"capture_sha256": "d4bc53f9b7485c8bbc2a8c6fc2a3ff0c562520bf967033119ae119f6a8b8fb0d",
|
| 333 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 334 |
+
"finite_cases": 8,
|
| 335 |
+
"finite_passed": 7,
|
| 336 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 337 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_fp32-false",
|
| 338 |
+
"model_predictions": 6,
|
| 339 |
+
"prediction_skips": 0,
|
| 340 |
+
"process_metrics": {
|
| 341 |
+
"wall_ns": 5786750,
|
| 342 |
+
"user_cpu_ns": 3461000,
|
| 343 |
+
"system_cpu_ns": 1602000,
|
| 344 |
+
"child_max_rss_bytes": 17973248,
|
| 345 |
+
"process_cpu_percent_of_one_core_over_wall": 87.49297965179073
|
| 346 |
+
},
|
| 347 |
+
"unfixed": false
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"arm": "feedback_fp32",
|
| 351 |
+
"candidate_attempts": 4,
|
| 352 |
+
"capture_sha256": "90d3f115b51277055c2ba5c7aa7ca195199b86d1b0be75df877789c0e4d06b6c",
|
| 353 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 354 |
+
"finite_cases": 8,
|
| 355 |
+
"finite_passed": 7,
|
| 356 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 357 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_fp32-true",
|
| 358 |
+
"model_predictions": 5,
|
| 359 |
+
"prediction_skips": 1,
|
| 360 |
+
"process_metrics": {
|
| 361 |
+
"wall_ns": 5729917,
|
| 362 |
+
"user_cpu_ns": 3423000,
|
| 363 |
+
"system_cpu_ns": 1549000,
|
| 364 |
+
"child_max_rss_bytes": 17907712,
|
| 365 |
+
"process_cpu_percent_of_one_core_over_wall": 86.7726356245649
|
| 366 |
+
},
|
| 367 |
+
"unfixed": true
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"arm": "feedback_ptq",
|
| 371 |
+
"candidate_attempts": 4,
|
| 372 |
+
"capture_sha256": "dd8c07106e6152e862fb00d527120e84c7d680f2196579316de443eb607fd597",
|
| 373 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 374 |
+
"finite_cases": 8,
|
| 375 |
+
"finite_passed": 7,
|
| 376 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 377 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_ptq-false",
|
| 378 |
+
"model_predictions": 6,
|
| 379 |
+
"prediction_skips": 0,
|
| 380 |
+
"process_metrics": {
|
| 381 |
+
"wall_ns": 6042000,
|
| 382 |
+
"user_cpu_ns": 3556000,
|
| 383 |
+
"system_cpu_ns": 1768000,
|
| 384 |
+
"child_max_rss_bytes": 18038784,
|
| 385 |
+
"process_cpu_percent_of_one_core_over_wall": 88.11651770936776
|
| 386 |
+
},
|
| 387 |
+
"unfixed": false
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"arm": "feedback_ptq",
|
| 391 |
+
"candidate_attempts": 4,
|
| 392 |
+
"capture_sha256": "e3374ff32a28f68999dc7d1cff2d45fe1cfc26d973d4b07c02951a038f42e3fb",
|
| 393 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 394 |
+
"finite_cases": 8,
|
| 395 |
+
"finite_passed": 7,
|
| 396 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 397 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_ptq-true",
|
| 398 |
+
"model_predictions": 5,
|
| 399 |
+
"prediction_skips": 1,
|
| 400 |
+
"process_metrics": {
|
| 401 |
+
"wall_ns": 5867875,
|
| 402 |
+
"user_cpu_ns": 3427000,
|
| 403 |
+
"system_cpu_ns": 1660000,
|
| 404 |
+
"child_max_rss_bytes": 17940480,
|
| 405 |
+
"process_cpu_percent_of_one_core_over_wall": 86.69237159959951
|
| 406 |
+
},
|
| 407 |
+
"unfixed": true
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"arm": "feedback_qat",
|
| 411 |
+
"candidate_attempts": 4,
|
| 412 |
+
"capture_sha256": "983bb76c6765cf8a3127785625563d69da51bb882c2d5f01ea9859b7d6b36836",
|
| 413 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 414 |
+
"finite_cases": 8,
|
| 415 |
+
"finite_passed": 7,
|
| 416 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 417 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_qat-false",
|
| 418 |
+
"model_predictions": 6,
|
| 419 |
+
"prediction_skips": 0,
|
| 420 |
+
"process_metrics": {
|
| 421 |
+
"wall_ns": 5958125,
|
| 422 |
+
"user_cpu_ns": 3475000,
|
| 423 |
+
"system_cpu_ns": 1770000,
|
| 424 |
+
"child_max_rss_bytes": 17989632,
|
| 425 |
+
"process_cpu_percent_of_one_core_over_wall": 88.03105003671457
|
| 426 |
+
},
|
| 427 |
+
"unfixed": false
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"arm": "feedback_qat",
|
| 431 |
+
"candidate_attempts": 4,
|
| 432 |
+
"capture_sha256": "69914d48dfe113f155a0599e9fe6fd4b80bb6f3f641f5936399e2d7e77f0103c",
|
| 433 |
+
"case_id": "reference_assignment-0-ko-contradictory",
|
| 434 |
+
"finite_cases": 8,
|
| 435 |
+
"finite_passed": 7,
|
| 436 |
+
"generated_go_sha256": "465c435f9d0f204af984b4c08ce0a2bb0cd5a19ec71aa21066dd3b0a2cb19d81",
|
| 437 |
+
"id": "reference_assignment-0-ko-contradictory-feedback_qat-true",
|
| 438 |
+
"model_predictions": 5,
|
| 439 |
+
"prediction_skips": 1,
|
| 440 |
+
"process_metrics": {
|
| 441 |
+
"wall_ns": 6001959,
|
| 442 |
+
"user_cpu_ns": 3564000,
|
| 443 |
+
"system_cpu_ns": 1722000,
|
| 444 |
+
"child_max_rss_bytes": 17989632,
|
| 445 |
+
"process_cpu_percent_of_one_core_over_wall": 88.07124473859285
|
| 446 |
+
},
|
| 447 |
+
"unfixed": true
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"arm": "parent_fp32",
|
| 451 |
+
"candidate_attempts": 4,
|
| 452 |
+
"capture_sha256": "96f440b6cba0ae66082f3b7dc7d7b4c99825e9b19432f72214907cd577fceaca",
|
| 453 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 454 |
+
"finite_cases": 8,
|
| 455 |
+
"finite_passed": 7,
|
| 456 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 457 |
+
"id": "operand_branch-0-en-contradictory-parent_fp32-false",
|
| 458 |
+
"model_predictions": 6,
|
| 459 |
+
"prediction_skips": 0,
|
| 460 |
+
"process_metrics": {
|
| 461 |
+
"wall_ns": 6302917,
|
| 462 |
+
"user_cpu_ns": 3754000,
|
| 463 |
+
"system_cpu_ns": 1826000,
|
| 464 |
+
"child_max_rss_bytes": 18186240,
|
| 465 |
+
"process_cpu_percent_of_one_core_over_wall": 88.53043757358697
|
| 466 |
+
},
|
| 467 |
+
"unfixed": false
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"arm": "parent_fp32",
|
| 471 |
+
"candidate_attempts": 4,
|
| 472 |
+
"capture_sha256": "d249bcc23bd3adc671e229448709abef2e7c3ecfe0491e8fff00fe3adee68587",
|
| 473 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 474 |
+
"finite_cases": 8,
|
| 475 |
+
"finite_passed": 7,
|
| 476 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 477 |
+
"id": "operand_branch-0-en-contradictory-parent_fp32-true",
|
| 478 |
+
"model_predictions": 5,
|
| 479 |
+
"prediction_skips": 1,
|
| 480 |
+
"process_metrics": {
|
| 481 |
+
"wall_ns": 5854625,
|
| 482 |
+
"user_cpu_ns": 3555000,
|
| 483 |
+
"system_cpu_ns": 1648000,
|
| 484 |
+
"child_max_rss_bytes": 18137088,
|
| 485 |
+
"process_cpu_percent_of_one_core_over_wall": 88.86991054081174
|
| 486 |
+
},
|
| 487 |
+
"unfixed": true
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"arm": "feedback_fp32",
|
| 491 |
+
"candidate_attempts": 4,
|
| 492 |
+
"capture_sha256": "003e8ed5cae6ededb76d2f061f98272de4df40fdb683b658309e12fc4932f76b",
|
| 493 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 494 |
+
"finite_cases": 8,
|
| 495 |
+
"finite_passed": 7,
|
| 496 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 497 |
+
"id": "operand_branch-0-en-contradictory-feedback_fp32-false",
|
| 498 |
+
"model_predictions": 6,
|
| 499 |
+
"prediction_skips": 0,
|
| 500 |
+
"process_metrics": {
|
| 501 |
+
"wall_ns": 6042542,
|
| 502 |
+
"user_cpu_ns": 3652000,
|
| 503 |
+
"system_cpu_ns": 1668000,
|
| 504 |
+
"child_max_rss_bytes": 17989632,
|
| 505 |
+
"process_cpu_percent_of_one_core_over_wall": 88.04241658560255
|
| 506 |
+
},
|
| 507 |
+
"unfixed": false
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"arm": "feedback_fp32",
|
| 511 |
+
"candidate_attempts": 4,
|
| 512 |
+
"capture_sha256": "005733445ba7fe5584ab93ee1b80d2ccfbd0705e1c8d18b414cd881e034c7d48",
|
| 513 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 514 |
+
"finite_cases": 8,
|
| 515 |
+
"finite_passed": 7,
|
| 516 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 517 |
+
"id": "operand_branch-0-en-contradictory-feedback_fp32-true",
|
| 518 |
+
"model_predictions": 5,
|
| 519 |
+
"prediction_skips": 1,
|
| 520 |
+
"process_metrics": {
|
| 521 |
+
"wall_ns": 5845208,
|
| 522 |
+
"user_cpu_ns": 3528000,
|
| 523 |
+
"system_cpu_ns": 1660000,
|
| 524 |
+
"child_max_rss_bytes": 18104320,
|
| 525 |
+
"process_cpu_percent_of_one_core_over_wall": 88.75646512493653
|
| 526 |
+
},
|
| 527 |
+
"unfixed": true
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"arm": "feedback_ptq",
|
| 531 |
+
"candidate_attempts": 4,
|
| 532 |
+
"capture_sha256": "01dfc82c3e81dc1186e246526bc044d4a1092e7edbf37f245bd4435515133590",
|
| 533 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 534 |
+
"finite_cases": 8,
|
| 535 |
+
"finite_passed": 7,
|
| 536 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 537 |
+
"id": "operand_branch-0-en-contradictory-feedback_ptq-false",
|
| 538 |
+
"model_predictions": 6,
|
| 539 |
+
"prediction_skips": 0,
|
| 540 |
+
"process_metrics": {
|
| 541 |
+
"wall_ns": 6148291,
|
| 542 |
+
"user_cpu_ns": 3584000,
|
| 543 |
+
"system_cpu_ns": 1845000,
|
| 544 |
+
"child_max_rss_bytes": 18055168,
|
| 545 |
+
"process_cpu_percent_of_one_core_over_wall": 88.30096038069766
|
| 546 |
+
},
|
| 547 |
+
"unfixed": false
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"arm": "feedback_ptq",
|
| 551 |
+
"candidate_attempts": 4,
|
| 552 |
+
"capture_sha256": "db55540635d3d03ed9c9f3859fe63a46667cf255c09237a4d80a31360fd5d1fd",
|
| 553 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 554 |
+
"finite_cases": 8,
|
| 555 |
+
"finite_passed": 7,
|
| 556 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 557 |
+
"id": "operand_branch-0-en-contradictory-feedback_ptq-true",
|
| 558 |
+
"model_predictions": 5,
|
| 559 |
+
"prediction_skips": 1,
|
| 560 |
+
"process_metrics": {
|
| 561 |
+
"wall_ns": 6209208,
|
| 562 |
+
"user_cpu_ns": 3653000,
|
| 563 |
+
"system_cpu_ns": 1794000,
|
| 564 |
+
"child_max_rss_bytes": 18055168,
|
| 565 |
+
"process_cpu_percent_of_one_core_over_wall": 87.72455359846215
|
| 566 |
+
},
|
| 567 |
+
"unfixed": true
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"arm": "feedback_qat",
|
| 571 |
+
"candidate_attempts": 4,
|
| 572 |
+
"capture_sha256": "795ac720128705d0087952e7576431c9bc0014d793a5ea5c4aead68fcd88d1a1",
|
| 573 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 574 |
+
"finite_cases": 8,
|
| 575 |
+
"finite_passed": 7,
|
| 576 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 577 |
+
"id": "operand_branch-0-en-contradictory-feedback_qat-false",
|
| 578 |
+
"model_predictions": 6,
|
| 579 |
+
"prediction_skips": 0,
|
| 580 |
+
"process_metrics": {
|
| 581 |
+
"wall_ns": 6328458,
|
| 582 |
+
"user_cpu_ns": 3680000,
|
| 583 |
+
"system_cpu_ns": 1766000,
|
| 584 |
+
"child_max_rss_bytes": 18055168,
|
| 585 |
+
"process_cpu_percent_of_one_core_over_wall": 86.0557184704394
|
| 586 |
+
},
|
| 587 |
+
"unfixed": false
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"arm": "feedback_qat",
|
| 591 |
+
"candidate_attempts": 4,
|
| 592 |
+
"capture_sha256": "bed58b193820a4a56ae28d6fdb76180ed72592633292eb933b453cf94264254f",
|
| 593 |
+
"case_id": "operand_branch-0-en-contradictory",
|
| 594 |
+
"finite_cases": 8,
|
| 595 |
+
"finite_passed": 7,
|
| 596 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 597 |
+
"id": "operand_branch-0-en-contradictory-feedback_qat-true",
|
| 598 |
+
"model_predictions": 5,
|
| 599 |
+
"prediction_skips": 1,
|
| 600 |
+
"process_metrics": {
|
| 601 |
+
"wall_ns": 6309333,
|
| 602 |
+
"user_cpu_ns": 3676000,
|
| 603 |
+
"system_cpu_ns": 1826000,
|
| 604 |
+
"child_max_rss_bytes": 17842176,
|
| 605 |
+
"process_cpu_percent_of_one_core_over_wall": 87.20414661898492
|
| 606 |
+
},
|
| 607 |
+
"unfixed": true
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"arm": "parent_fp32",
|
| 611 |
+
"candidate_attempts": 4,
|
| 612 |
+
"capture_sha256": "c1d0235ec32a594888e09a241a9f9f143cf9c9fe29cdd0ed4ab85b4b5cf32085",
|
| 613 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 614 |
+
"finite_cases": 8,
|
| 615 |
+
"finite_passed": 7,
|
| 616 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 617 |
+
"id": "operand_branch-0-ko-contradictory-parent_fp32-false",
|
| 618 |
+
"model_predictions": 6,
|
| 619 |
+
"prediction_skips": 0,
|
| 620 |
+
"process_metrics": {
|
| 621 |
+
"wall_ns": 6099375,
|
| 622 |
+
"user_cpu_ns": 3614000,
|
| 623 |
+
"system_cpu_ns": 1715000,
|
| 624 |
+
"child_max_rss_bytes": 18087936,
|
| 625 |
+
"process_cpu_percent_of_one_core_over_wall": 87.36960754175632
|
| 626 |
+
},
|
| 627 |
+
"unfixed": false
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"arm": "parent_fp32",
|
| 631 |
+
"candidate_attempts": 4,
|
| 632 |
+
"capture_sha256": "380d81badb208d7acc69774c7db015a2e8464bb1de0269f4da3954a0dcf6c2c6",
|
| 633 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 634 |
+
"finite_cases": 8,
|
| 635 |
+
"finite_passed": 7,
|
| 636 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 637 |
+
"id": "operand_branch-0-ko-contradictory-parent_fp32-true",
|
| 638 |
+
"model_predictions": 5,
|
| 639 |
+
"prediction_skips": 1,
|
| 640 |
+
"process_metrics": {
|
| 641 |
+
"wall_ns": 6083458,
|
| 642 |
+
"user_cpu_ns": 3645000,
|
| 643 |
+
"system_cpu_ns": 1711000,
|
| 644 |
+
"child_max_rss_bytes": 18251776,
|
| 645 |
+
"process_cpu_percent_of_one_core_over_wall": 88.04203135782313
|
| 646 |
+
},
|
| 647 |
+
"unfixed": true
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"arm": "feedback_fp32",
|
| 651 |
+
"candidate_attempts": 4,
|
| 652 |
+
"capture_sha256": "83b9e8319e84a8c618c86a52262f34c900e11874baa91ea3d16783dc3b0aa3bf",
|
| 653 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 654 |
+
"finite_cases": 8,
|
| 655 |
+
"finite_passed": 7,
|
| 656 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 657 |
+
"id": "operand_branch-0-ko-contradictory-feedback_fp32-false",
|
| 658 |
+
"model_predictions": 6,
|
| 659 |
+
"prediction_skips": 0,
|
| 660 |
+
"process_metrics": {
|
| 661 |
+
"wall_ns": 5825958,
|
| 662 |
+
"user_cpu_ns": 3481000,
|
| 663 |
+
"system_cpu_ns": 1623000,
|
| 664 |
+
"child_max_rss_bytes": 18219008,
|
| 665 |
+
"process_cpu_percent_of_one_core_over_wall": 87.60790929148476
|
| 666 |
+
},
|
| 667 |
+
"unfixed": false
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"arm": "feedback_fp32",
|
| 671 |
+
"candidate_attempts": 4,
|
| 672 |
+
"capture_sha256": "3dcfec9ce945c2d79ac318b39b614a1732e4f82e96897226ce405b8069e9d5a2",
|
| 673 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 674 |
+
"finite_cases": 8,
|
| 675 |
+
"finite_passed": 7,
|
| 676 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 677 |
+
"id": "operand_branch-0-ko-contradictory-feedback_fp32-true",
|
| 678 |
+
"model_predictions": 5,
|
| 679 |
+
"prediction_skips": 1,
|
| 680 |
+
"process_metrics": {
|
| 681 |
+
"wall_ns": 5724125,
|
| 682 |
+
"user_cpu_ns": 3463000,
|
| 683 |
+
"system_cpu_ns": 1625000,
|
| 684 |
+
"child_max_rss_bytes": 18186240,
|
| 685 |
+
"process_cpu_percent_of_one_core_over_wall": 88.88694778677964
|
| 686 |
+
},
|
| 687 |
+
"unfixed": true
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"arm": "feedback_ptq",
|
| 691 |
+
"candidate_attempts": 4,
|
| 692 |
+
"capture_sha256": "3cbd5fdf27d60d9955011af5d01a31845f5064c4ab6b9e1d10747192868bd76c",
|
| 693 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 694 |
+
"finite_cases": 8,
|
| 695 |
+
"finite_passed": 7,
|
| 696 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 697 |
+
"id": "operand_branch-0-ko-contradictory-feedback_ptq-false",
|
| 698 |
+
"model_predictions": 6,
|
| 699 |
+
"prediction_skips": 0,
|
| 700 |
+
"process_metrics": {
|
| 701 |
+
"wall_ns": 5764125,
|
| 702 |
+
"user_cpu_ns": 3394000,
|
| 703 |
+
"system_cpu_ns": 1662000,
|
| 704 |
+
"child_max_rss_bytes": 17842176,
|
| 705 |
+
"process_cpu_percent_of_one_core_over_wall": 87.71496107388371
|
| 706 |
+
},
|
| 707 |
+
"unfixed": false
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"arm": "feedback_ptq",
|
| 711 |
+
"candidate_attempts": 4,
|
| 712 |
+
"capture_sha256": "29767e5fadd38eaf741ad2b52a155b370979ffc57d0223307eaca94cb9a21bb7",
|
| 713 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 714 |
+
"finite_cases": 8,
|
| 715 |
+
"finite_passed": 7,
|
| 716 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 717 |
+
"id": "operand_branch-0-ko-contradictory-feedback_ptq-true",
|
| 718 |
+
"model_predictions": 5,
|
| 719 |
+
"prediction_skips": 1,
|
| 720 |
+
"process_metrics": {
|
| 721 |
+
"wall_ns": 5918667,
|
| 722 |
+
"user_cpu_ns": 3471000,
|
| 723 |
+
"system_cpu_ns": 1617000,
|
| 724 |
+
"child_max_rss_bytes": 17874944,
|
| 725 |
+
"process_cpu_percent_of_one_core_over_wall": 85.96530266021048
|
| 726 |
+
},
|
| 727 |
+
"unfixed": true
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"arm": "feedback_qat",
|
| 731 |
+
"candidate_attempts": 4,
|
| 732 |
+
"capture_sha256": "3201402e635fc9dd9e1e5391ac9184216dc38e16dc88b678d86b3ea35f451ae1",
|
| 733 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 734 |
+
"finite_cases": 8,
|
| 735 |
+
"finite_passed": 7,
|
| 736 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 737 |
+
"id": "operand_branch-0-ko-contradictory-feedback_qat-false",
|
| 738 |
+
"model_predictions": 6,
|
| 739 |
+
"prediction_skips": 0,
|
| 740 |
+
"process_metrics": {
|
| 741 |
+
"wall_ns": 5747792,
|
| 742 |
+
"user_cpu_ns": 3490000,
|
| 743 |
+
"system_cpu_ns": 1642000,
|
| 744 |
+
"child_max_rss_bytes": 17825792,
|
| 745 |
+
"process_cpu_percent_of_one_core_over_wall": 89.28645991365032
|
| 746 |
+
},
|
| 747 |
+
"unfixed": false
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"arm": "feedback_qat",
|
| 751 |
+
"candidate_attempts": 4,
|
| 752 |
+
"capture_sha256": "e73f643dc5cfc4ec96d9b43fd7c2664b83daa6a3bea0e36d2f94d0d8f1762c77",
|
| 753 |
+
"case_id": "operand_branch-0-ko-contradictory",
|
| 754 |
+
"finite_cases": 8,
|
| 755 |
+
"finite_passed": 7,
|
| 756 |
+
"generated_go_sha256": "62e8aa4d51696162279431476eaaeb935aa85393af3483d94bff923cec8999e6",
|
| 757 |
+
"id": "operand_branch-0-ko-contradictory-feedback_qat-true",
|
| 758 |
+
"model_predictions": 5,
|
| 759 |
+
"prediction_skips": 1,
|
| 760 |
+
"process_metrics": {
|
| 761 |
+
"wall_ns": 5979167,
|
| 762 |
+
"user_cpu_ns": 3587000,
|
| 763 |
+
"system_cpu_ns": 1731000,
|
| 764 |
+
"child_max_rss_bytes": 18038784,
|
| 765 |
+
"process_cpu_percent_of_one_core_over_wall": 88.94215532029796
|
| 766 |
+
},
|
| 767 |
+
"unfixed": true
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"arm": "parent_fp32",
|
| 771 |
+
"candidate_attempts": 4,
|
| 772 |
+
"capture_sha256": "cf7e4c8441f90f1f401d39ed42451243c4fd120e15a6890c3595e95edd3ae404",
|
| 773 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 774 |
+
"finite_cases": 8,
|
| 775 |
+
"finite_passed": 7,
|
| 776 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 777 |
+
"id": "reference_schedule-0-en-contradictory-parent_fp32-false",
|
| 778 |
+
"model_predictions": 6,
|
| 779 |
+
"prediction_skips": 0,
|
| 780 |
+
"process_metrics": {
|
| 781 |
+
"wall_ns": 6107708,
|
| 782 |
+
"user_cpu_ns": 3638000,
|
| 783 |
+
"system_cpu_ns": 1745000,
|
| 784 |
+
"child_max_rss_bytes": 17989632,
|
| 785 |
+
"process_cpu_percent_of_one_core_over_wall": 88.134534263917
|
| 786 |
+
},
|
| 787 |
+
"unfixed": false
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"arm": "parent_fp32",
|
| 791 |
+
"candidate_attempts": 4,
|
| 792 |
+
"capture_sha256": "1be13d26e7ba4b31175e5c414213d94a3b417ea1b0cb78512acbd2e54dc1b423",
|
| 793 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 794 |
+
"finite_cases": 8,
|
| 795 |
+
"finite_passed": 7,
|
| 796 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 797 |
+
"id": "reference_schedule-0-en-contradictory-parent_fp32-true",
|
| 798 |
+
"model_predictions": 5,
|
| 799 |
+
"prediction_skips": 1,
|
| 800 |
+
"process_metrics": {
|
| 801 |
+
"wall_ns": 5919083,
|
| 802 |
+
"user_cpu_ns": 3533000,
|
| 803 |
+
"system_cpu_ns": 1744000,
|
| 804 |
+
"child_max_rss_bytes": 18235392,
|
| 805 |
+
"process_cpu_percent_of_one_core_over_wall": 89.15232308788372
|
| 806 |
+
},
|
| 807 |
+
"unfixed": true
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"arm": "feedback_fp32",
|
| 811 |
+
"candidate_attempts": 4,
|
| 812 |
+
"capture_sha256": "d965ef6240448cabc0b07a4de45251db37e92c9b7b1687b6ca525b635e0df67e",
|
| 813 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 814 |
+
"finite_cases": 8,
|
| 815 |
+
"finite_passed": 7,
|
| 816 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 817 |
+
"id": "reference_schedule-0-en-contradictory-feedback_fp32-false",
|
| 818 |
+
"model_predictions": 6,
|
| 819 |
+
"prediction_skips": 0,
|
| 820 |
+
"process_metrics": {
|
| 821 |
+
"wall_ns": 5973917,
|
| 822 |
+
"user_cpu_ns": 3570000,
|
| 823 |
+
"system_cpu_ns": 1685000,
|
| 824 |
+
"child_max_rss_bytes": 17989632,
|
| 825 |
+
"process_cpu_percent_of_one_core_over_wall": 87.96573504452773
|
| 826 |
+
},
|
| 827 |
+
"unfixed": false
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"arm": "feedback_fp32",
|
| 831 |
+
"candidate_attempts": 4,
|
| 832 |
+
"capture_sha256": "95f39c2961a5104797090979ad51505d9d4142ca7c7601579c7f59f0de9a9180",
|
| 833 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 834 |
+
"finite_cases": 8,
|
| 835 |
+
"finite_passed": 7,
|
| 836 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 837 |
+
"id": "reference_schedule-0-en-contradictory-feedback_fp32-true",
|
| 838 |
+
"model_predictions": 5,
|
| 839 |
+
"prediction_skips": 1,
|
| 840 |
+
"process_metrics": {
|
| 841 |
+
"wall_ns": 6099334,
|
| 842 |
+
"user_cpu_ns": 3619000,
|
| 843 |
+
"system_cpu_ns": 1728000,
|
| 844 |
+
"child_max_rss_bytes": 18137088,
|
| 845 |
+
"process_cpu_percent_of_one_core_over_wall": 87.66530903210088
|
| 846 |
+
},
|
| 847 |
+
"unfixed": true
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"arm": "feedback_ptq",
|
| 851 |
+
"candidate_attempts": 4,
|
| 852 |
+
"capture_sha256": "a8f921873c0a02bb6d6627791e533048599a2cc9d8af7493703a8908d23c78a3",
|
| 853 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 854 |
+
"finite_cases": 8,
|
| 855 |
+
"finite_passed": 7,
|
| 856 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 857 |
+
"id": "reference_schedule-0-en-contradictory-feedback_ptq-false",
|
| 858 |
+
"model_predictions": 6,
|
| 859 |
+
"prediction_skips": 0,
|
| 860 |
+
"process_metrics": {
|
| 861 |
+
"wall_ns": 5983500,
|
| 862 |
+
"user_cpu_ns": 3535000,
|
| 863 |
+
"system_cpu_ns": 1727000,
|
| 864 |
+
"child_max_rss_bytes": 17907712,
|
| 865 |
+
"process_cpu_percent_of_one_core_over_wall": 87.94184006016546
|
| 866 |
+
},
|
| 867 |
+
"unfixed": false
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"arm": "feedback_ptq",
|
| 871 |
+
"candidate_attempts": 4,
|
| 872 |
+
"capture_sha256": "132c3c64509325f74d412d7fdcbe82b26fae63263283da0a2236d085206dd0fd",
|
| 873 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 874 |
+
"finite_cases": 8,
|
| 875 |
+
"finite_passed": 7,
|
| 876 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 877 |
+
"id": "reference_schedule-0-en-contradictory-feedback_ptq-true",
|
| 878 |
+
"model_predictions": 5,
|
| 879 |
+
"prediction_skips": 1,
|
| 880 |
+
"process_metrics": {
|
| 881 |
+
"wall_ns": 6132959,
|
| 882 |
+
"user_cpu_ns": 3516000,
|
| 883 |
+
"system_cpu_ns": 2017000,
|
| 884 |
+
"child_max_rss_bytes": 17989632,
|
| 885 |
+
"process_cpu_percent_of_one_core_over_wall": 90.21746272883938
|
| 886 |
+
},
|
| 887 |
+
"unfixed": true
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"arm": "feedback_qat",
|
| 891 |
+
"candidate_attempts": 4,
|
| 892 |
+
"capture_sha256": "0ab759c3016e7e03a31dfbf3af04394577d03b6d30e55c910ff0496ae8a81e59",
|
| 893 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 894 |
+
"finite_cases": 8,
|
| 895 |
+
"finite_passed": 7,
|
| 896 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 897 |
+
"id": "reference_schedule-0-en-contradictory-feedback_qat-false",
|
| 898 |
+
"model_predictions": 6,
|
| 899 |
+
"prediction_skips": 0,
|
| 900 |
+
"process_metrics": {
|
| 901 |
+
"wall_ns": 6239541,
|
| 902 |
+
"user_cpu_ns": 3626000,
|
| 903 |
+
"system_cpu_ns": 1777000,
|
| 904 |
+
"child_max_rss_bytes": 17874944,
|
| 905 |
+
"process_cpu_percent_of_one_core_over_wall": 86.5929080360238
|
| 906 |
+
},
|
| 907 |
+
"unfixed": false
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"arm": "feedback_qat",
|
| 911 |
+
"candidate_attempts": 4,
|
| 912 |
+
"capture_sha256": "ee6a1f02091dec3cd072597e90f21af9d0156473972f5dde102bb8c3111eb790",
|
| 913 |
+
"case_id": "reference_schedule-0-en-contradictory",
|
| 914 |
+
"finite_cases": 8,
|
| 915 |
+
"finite_passed": 7,
|
| 916 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 917 |
+
"id": "reference_schedule-0-en-contradictory-feedback_qat-true",
|
| 918 |
+
"model_predictions": 5,
|
| 919 |
+
"prediction_skips": 1,
|
| 920 |
+
"process_metrics": {
|
| 921 |
+
"wall_ns": 6005625,
|
| 922 |
+
"user_cpu_ns": 3554000,
|
| 923 |
+
"system_cpu_ns": 1778000,
|
| 924 |
+
"child_max_rss_bytes": 18022400,
|
| 925 |
+
"process_cpu_percent_of_one_core_over_wall": 88.78343219898012
|
| 926 |
+
},
|
| 927 |
+
"unfixed": true
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"arm": "parent_fp32",
|
| 931 |
+
"candidate_attempts": 4,
|
| 932 |
+
"capture_sha256": "fed8a744f010717c195b35628f847ba879ae7af385a70181115ad897ac418224",
|
| 933 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 934 |
+
"finite_cases": 8,
|
| 935 |
+
"finite_passed": 7,
|
| 936 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 937 |
+
"id": "reference_schedule-0-ko-contradictory-parent_fp32-false",
|
| 938 |
+
"model_predictions": 6,
|
| 939 |
+
"prediction_skips": 0,
|
| 940 |
+
"process_metrics": {
|
| 941 |
+
"wall_ns": 6227000,
|
| 942 |
+
"user_cpu_ns": 3653000,
|
| 943 |
+
"system_cpu_ns": 1793000,
|
| 944 |
+
"child_max_rss_bytes": 18071552,
|
| 945 |
+
"process_cpu_percent_of_one_core_over_wall": 87.45784486911836
|
| 946 |
+
},
|
| 947 |
+
"unfixed": false
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"arm": "parent_fp32",
|
| 951 |
+
"candidate_attempts": 4,
|
| 952 |
+
"capture_sha256": "437e963896e4c0057c30a25ad9acb7eb6b928826e972e8e577c0bb4090474791",
|
| 953 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 954 |
+
"finite_cases": 8,
|
| 955 |
+
"finite_passed": 7,
|
| 956 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 957 |
+
"id": "reference_schedule-0-ko-contradictory-parent_fp32-true",
|
| 958 |
+
"model_predictions": 5,
|
| 959 |
+
"prediction_skips": 1,
|
| 960 |
+
"process_metrics": {
|
| 961 |
+
"wall_ns": 6381459,
|
| 962 |
+
"user_cpu_ns": 3808000,
|
| 963 |
+
"system_cpu_ns": 1944000,
|
| 964 |
+
"child_max_rss_bytes": 17924096,
|
| 965 |
+
"process_cpu_percent_of_one_core_over_wall": 90.13612717718628
|
| 966 |
+
},
|
| 967 |
+
"unfixed": true
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"arm": "feedback_fp32",
|
| 971 |
+
"candidate_attempts": 4,
|
| 972 |
+
"capture_sha256": "a33c04afa05bd6403aa50e4eb8a1a02d448bea6a276d84e135e94394bfc6f653",
|
| 973 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 974 |
+
"finite_cases": 8,
|
| 975 |
+
"finite_passed": 7,
|
| 976 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 977 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_fp32-false",
|
| 978 |
+
"model_predictions": 6,
|
| 979 |
+
"prediction_skips": 0,
|
| 980 |
+
"process_metrics": {
|
| 981 |
+
"wall_ns": 6551583,
|
| 982 |
+
"user_cpu_ns": 3919000,
|
| 983 |
+
"system_cpu_ns": 1893000,
|
| 984 |
+
"child_max_rss_bytes": 18169856,
|
| 985 |
+
"process_cpu_percent_of_one_core_over_wall": 88.71138471419808
|
| 986 |
+
},
|
| 987 |
+
"unfixed": false
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"arm": "feedback_fp32",
|
| 991 |
+
"candidate_attempts": 4,
|
| 992 |
+
"capture_sha256": "1a8bf50e18662ab8ab44fc788e9382917295d1b6a4e91ce0766f3f31969a244c",
|
| 993 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 994 |
+
"finite_cases": 8,
|
| 995 |
+
"finite_passed": 7,
|
| 996 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 997 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_fp32-true",
|
| 998 |
+
"model_predictions": 5,
|
| 999 |
+
"prediction_skips": 1,
|
| 1000 |
+
"process_metrics": {
|
| 1001 |
+
"wall_ns": 6157417,
|
| 1002 |
+
"user_cpu_ns": 3697000,
|
| 1003 |
+
"system_cpu_ns": 1719000,
|
| 1004 |
+
"child_max_rss_bytes": 18137088,
|
| 1005 |
+
"process_cpu_percent_of_one_core_over_wall": 87.95896071355895
|
| 1006 |
+
},
|
| 1007 |
+
"unfixed": true
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"arm": "feedback_ptq",
|
| 1011 |
+
"candidate_attempts": 4,
|
| 1012 |
+
"capture_sha256": "17aa26501b2f5df7cac081e9c3f3f3c9f0d741cbf7e48ab476e9e12cacddf7cc",
|
| 1013 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1014 |
+
"finite_cases": 8,
|
| 1015 |
+
"finite_passed": 7,
|
| 1016 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1017 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_ptq-false",
|
| 1018 |
+
"model_predictions": 6,
|
| 1019 |
+
"prediction_skips": 0,
|
| 1020 |
+
"process_metrics": {
|
| 1021 |
+
"wall_ns": 6340375,
|
| 1022 |
+
"user_cpu_ns": 3605000,
|
| 1023 |
+
"system_cpu_ns": 1792000,
|
| 1024 |
+
"child_max_rss_bytes": 17989632,
|
| 1025 |
+
"process_cpu_percent_of_one_core_over_wall": 85.12114819707037
|
| 1026 |
+
},
|
| 1027 |
+
"unfixed": false
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"arm": "feedback_ptq",
|
| 1031 |
+
"candidate_attempts": 4,
|
| 1032 |
+
"capture_sha256": "15c8ea4843767eb6bbe3f9599e6c24b14c9dfd2bd3b6c9dd06a31572bc61a72a",
|
| 1033 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1034 |
+
"finite_cases": 8,
|
| 1035 |
+
"finite_passed": 7,
|
| 1036 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1037 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_ptq-true",
|
| 1038 |
+
"model_predictions": 5,
|
| 1039 |
+
"prediction_skips": 1,
|
| 1040 |
+
"process_metrics": {
|
| 1041 |
+
"wall_ns": 5872542,
|
| 1042 |
+
"user_cpu_ns": 3516000,
|
| 1043 |
+
"system_cpu_ns": 1586000,
|
| 1044 |
+
"child_max_rss_bytes": 17989632,
|
| 1045 |
+
"process_cpu_percent_of_one_core_over_wall": 86.87890184523158
|
| 1046 |
+
},
|
| 1047 |
+
"unfixed": true
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"arm": "feedback_qat",
|
| 1051 |
+
"candidate_attempts": 4,
|
| 1052 |
+
"capture_sha256": "9d02b37e1cb655634daf2bda8220749fef177492ec12cffa8da3ddddb3540cb3",
|
| 1053 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1054 |
+
"finite_cases": 8,
|
| 1055 |
+
"finite_passed": 7,
|
| 1056 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1057 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_qat-false",
|
| 1058 |
+
"model_predictions": 6,
|
| 1059 |
+
"prediction_skips": 0,
|
| 1060 |
+
"process_metrics": {
|
| 1061 |
+
"wall_ns": 6010875,
|
| 1062 |
+
"user_cpu_ns": 3515000,
|
| 1063 |
+
"system_cpu_ns": 1663000,
|
| 1064 |
+
"child_max_rss_bytes": 18022400,
|
| 1065 |
+
"process_cpu_percent_of_one_core_over_wall": 86.14386424605402
|
| 1066 |
+
},
|
| 1067 |
+
"unfixed": false
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"arm": "feedback_qat",
|
| 1071 |
+
"candidate_attempts": 4,
|
| 1072 |
+
"capture_sha256": "013aeb8e575a069868b577efce263e1226f5baa9789a4a0bf68b89ab5bc55467",
|
| 1073 |
+
"case_id": "reference_schedule-0-ko-contradictory",
|
| 1074 |
+
"finite_cases": 8,
|
| 1075 |
+
"finite_passed": 7,
|
| 1076 |
+
"generated_go_sha256": "fe156f821ad78046fd0827e696147467a0ad0b1348c21b1ea1a2bcb0cf1b1ed4",
|
| 1077 |
+
"id": "reference_schedule-0-ko-contradictory-feedback_qat-true",
|
| 1078 |
+
"model_predictions": 5,
|
| 1079 |
+
"prediction_skips": 1,
|
| 1080 |
+
"process_metrics": {
|
| 1081 |
+
"wall_ns": 5954584,
|
| 1082 |
+
"user_cpu_ns": 3540000,
|
| 1083 |
+
"system_cpu_ns": 1732000,
|
| 1084 |
+
"child_max_rss_bytes": 18087936,
|
| 1085 |
+
"process_cpu_percent_of_one_core_over_wall": 88.53683145623607
|
| 1086 |
+
},
|
| 1087 |
+
"unfixed": true
|
| 1088 |
+
}
|
| 1089 |
+
],
|
| 1090 |
+
"observed_prediction_skips": 24,
|
| 1091 |
+
"opt_in_predictions": 120,
|
| 1092 |
+
"paired_views": 24,
|
| 1093 |
+
"preexecution_sha256": "b7fd3eedddabac4e37864b05a77d6f65e08dd60b1f626bb83134ab1126e8bdd0",
|
| 1094 |
+
"runner_revision": "3749fdc6c1f218c36d944a7899bb1125061c6906",
|
| 1095 |
+
"schema": "gooo/native-unfixed-pilot/v1",
|
| 1096 |
+
"scope": "Actual clean native SDK 2.7 codegen and own models; six reused bilingual/contradictory views and 24 legacy-first pairs, not independent new tasks. Native bodies are source-bound, type/replay checked and matched to selected typed function AST and independent integer-state oracle. Fixed arm order, whole compiler child resources, no causal speedup or host CPU utilization claim. Go execution deduplicates identical emitted source. Resource sidecars are retained observations. No training, GPU work, upstream Laya calls or source writes; offline audit performs zero inference or subprocess calls."
|
| 1097 |
+
}
|
research/unfixed-native-feature-pilot-20261001/studies/compound-path-v1/cohort.jsonl
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
research/unfixed-native-feature-pilot-20261001/studies/compound-path-v1/manifest.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"ambiguous_finite_views": 32,
|
| 3 |
+
"bilingual_program_instructions": 24,
|
| 4 |
+
"cohort_sha256": "aefd16b22076c05b113e29df3e7788b06e60e0c5c14e45cc75547bd1e582a15a",
|
| 5 |
+
"configuration": 101,
|
| 6 |
+
"contracts": [
|
| 7 |
+
"complete",
|
| 8 |
+
"sparse",
|
| 9 |
+
"contradictory"
|
| 10 |
+
],
|
| 11 |
+
"declared_masks_per_body": 4,
|
| 12 |
+
"languages": [
|
| 13 |
+
"en",
|
| 14 |
+
"ko"
|
| 15 |
+
],
|
| 16 |
+
"planned_native_matrix_calls": 648,
|
| 17 |
+
"planned_pilot_calls": 3,
|
| 18 |
+
"schema": "gooo/compound-path-cohort/v1",
|
| 19 |
+
"scope": "Three newly authored interacting body templates using five existing binary decision kinds. Two decisions yield four whole-body paths; each decision still has two options. One synthetic numeric configuration. Views/languages/contracts/arms are repeated policy observations, not 72 independent experiments or an untouched language benchmark. reference_schedule masks 1 and 3 commute and are functionally equivalent even when structural intention differs.",
|
| 20 |
+
"source_bodies": 3,
|
| 21 |
+
"source_sha256": {
|
| 22 |
+
"internal/compoundstudy/cohort.go": "bee1dd607e945521eb4903c8715a7e66f95db9984aa27d12eb9ef965f9ab330e",
|
| 23 |
+
"internal/compoundstudy/cohort_test.go": "aacd7d74bf96a59401337459a8e8abec4be0af7675e98f7dc156d4d7c60e7bd1"
|
| 24 |
+
},
|
| 25 |
+
"structural_intention_groups": 12,
|
| 26 |
+
"templates": [
|
| 27 |
+
"reference_assignment",
|
| 28 |
+
"operand_branch",
|
| 29 |
+
"reference_schedule"
|
| 30 |
+
],
|
| 31 |
+
"views": 72
|
| 32 |
+
}
|