Spaces:
Running
Running
Publish verified EvalArc 3da6d996086f
Browse files- index.html +1 -1
- manifest.json +4 -4
- research/manifest.json +1 -1
index.html
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
<main>
|
| 25 |
<section class="hero">
|
| 26 |
<div>
|
| 27 |
-
<p class="eyebrow"><span class="dot"></span> OPEN SOURCE / RESEARCH PREVIEW 0.17.
|
| 28 |
<h1>Look past<br>the <em>score.</em></h1>
|
| 29 |
<p class="intro">More passing plans.<br>Still a failed upgrade.</p>
|
| 30 |
<p class="muted">See what improved, what broke, and the original answer behind each check. Start with 48 real model generations.</p>
|
|
|
|
| 24 |
<main>
|
| 25 |
<section class="hero">
|
| 26 |
<div>
|
| 27 |
+
<p class="eyebrow"><span class="dot"></span> OPEN SOURCE / RESEARCH PREVIEW 0.17.7</p>
|
| 28 |
<h1>Look past<br>the <em>score.</em></h1>
|
| 29 |
<p class="intro">More passing plans.<br>Still a failed upgrade.</p>
|
| 30 |
<p class="muted">See what improved, what broke, and the original answer behind each check. Start with 48 real model generations.</p>
|
manifest.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"schema": "evalarc.site.v1",
|
| 3 |
"source_repository": "https://github.com/noteflowai/evalarc",
|
| 4 |
-
"source_commit": "
|
| 5 |
"source_dirty": false,
|
| 6 |
"evidence": "Scripted grader controls and separately labeled recorded GPU model pilots; no live inference.",
|
| 7 |
"files": {
|
|
@@ -1546,7 +1546,7 @@
|
|
| 1546 |
"independent-swe/traces/33.json": "d197c2fb032d7880421776ca181734f72b8d41dc90ce1c5c6ae81861e143e72d",
|
| 1547 |
"independent-swe/traces/34.json": "6560c0f302f744d1698d126b4e2f491ab2cac5814a90440171d0070ff28eefcc",
|
| 1548 |
"independent-swe/traces/35.json": "db6f526955e5214a453a56dd482a9b6faf3f0d7d52676b80aebe8fef64eefda5",
|
| 1549 |
-
"index.html": "
|
| 1550 |
"judge-stability/index.html": "2ab0d839c2ca0b4f42490c2392a77e6df024de142d49cb4d2a54e934223c766a",
|
| 1551 |
"judge-stability/inputs/0001.json": "d3807680a44436922ed827cd7a6a120984f8e0d7478d3d93fee6da1e7ff13a70",
|
| 1552 |
"judge-stability/inputs/0002.json": "230e9ddd3d6deac2785272e476d661f65597eef99e5059d9146fdc0628c7db9a",
|
|
@@ -1728,7 +1728,7 @@
|
|
| 1728 |
"research/harbor-native/robot-oracle-fixed/harbor-task__pYo9jgP/result.json": "850450b131e1c2930e53a95497208f6a95a1362b7c5a161c4ab7b6d558461d05",
|
| 1729 |
"research/harbor-native/robot-oracle-fixed/result.json": "2bbc3bb73ff4f1f71993e0f7761384f8aec3f02e610b8a569067c722531feb6a",
|
| 1730 |
"research/index.html": "b2132e5fd89a4321fa805d41e5c1bf93b479fe16f222fc7d0fed56168f6095dc",
|
| 1731 |
-
"research/manifest.json": "
|
| 1732 |
"research/research-records.zip": "d7d9084f4b8b69ed7b5faf82b4cb387e5f4c91e68816799f400701fa5aa50fd7",
|
| 1733 |
"research/robot-audit-javascript/audit.json": "86ff8a9b2991d3ee6a0a87cbe64e8fb9aa2bad533110d3f8ec9e7c72fb7ecf1f",
|
| 1734 |
"research/robot-audit-python/audit.json": "43f13a031ad5af63c632e61bcfb93f76dd9678aa29904904fa1ade3a6454d9ec",
|
|
@@ -2279,7 +2279,7 @@
|
|
| 2279 |
"skill-impact/app.js": "4f72654da43cdbf44b048c82bc16d8ead7d8c3050286e466743d23056d60fd4e",
|
| 2280 |
"skill-impact/index.html": "a86a39215daa5959b3b093ca6a15a498254501cd03239aae38d0810f6a907d44",
|
| 2281 |
"skill-impact/lab.json": "2b1c8dc7cda172b901be79c93f49f3c79743c031c296532575989cfed0997d80",
|
| 2282 |
-
"skill-impact/manifest.json": "
|
| 2283 |
"skill-impact/profiles/skill-impact-catalog-fallback/atif-validation.json": "4a3b89219116ccb1ed4942d1d86b53c4cb68b46bbb12c651eb8b66704d5c2a5a",
|
| 2284 |
"skill-impact/profiles/skill-impact-catalog-fallback/experiment.json": "0525de8fb77deed6617984d614906dc28a2c61f66f0970739c81809a8b9af16f",
|
| 2285 |
"skill-impact/profiles/skill-impact-contract-inline/atif-validation.json": "a43d99f77e6e1671729e4cc5c050391b0a3798ff8a2fc50723964a29848902f5",
|
|
|
|
| 1 |
{
|
| 2 |
"schema": "evalarc.site.v1",
|
| 3 |
"source_repository": "https://github.com/noteflowai/evalarc",
|
| 4 |
+
"source_commit": "3da6d996086f351f7d5fe2dae1107283e5f74cc4",
|
| 5 |
"source_dirty": false,
|
| 6 |
"evidence": "Scripted grader controls and separately labeled recorded GPU model pilots; no live inference.",
|
| 7 |
"files": {
|
|
|
|
| 1546 |
"independent-swe/traces/33.json": "d197c2fb032d7880421776ca181734f72b8d41dc90ce1c5c6ae81861e143e72d",
|
| 1547 |
"independent-swe/traces/34.json": "6560c0f302f744d1698d126b4e2f491ab2cac5814a90440171d0070ff28eefcc",
|
| 1548 |
"independent-swe/traces/35.json": "db6f526955e5214a453a56dd482a9b6faf3f0d7d52676b80aebe8fef64eefda5",
|
| 1549 |
+
"index.html": "c8eb5ea330d0475579c974d0d2ca113735397c3db57fce574f2cc060be080754",
|
| 1550 |
"judge-stability/index.html": "2ab0d839c2ca0b4f42490c2392a77e6df024de142d49cb4d2a54e934223c766a",
|
| 1551 |
"judge-stability/inputs/0001.json": "d3807680a44436922ed827cd7a6a120984f8e0d7478d3d93fee6da1e7ff13a70",
|
| 1552 |
"judge-stability/inputs/0002.json": "230e9ddd3d6deac2785272e476d661f65597eef99e5059d9146fdc0628c7db9a",
|
|
|
|
| 1728 |
"research/harbor-native/robot-oracle-fixed/harbor-task__pYo9jgP/result.json": "850450b131e1c2930e53a95497208f6a95a1362b7c5a161c4ab7b6d558461d05",
|
| 1729 |
"research/harbor-native/robot-oracle-fixed/result.json": "2bbc3bb73ff4f1f71993e0f7761384f8aec3f02e610b8a569067c722531feb6a",
|
| 1730 |
"research/index.html": "b2132e5fd89a4321fa805d41e5c1bf93b479fe16f222fc7d0fed56168f6095dc",
|
| 1731 |
+
"research/manifest.json": "cc0a416cadae56350231c11baef71593981af035e8d0af84a175e35cb0a96295",
|
| 1732 |
"research/research-records.zip": "d7d9084f4b8b69ed7b5faf82b4cb387e5f4c91e68816799f400701fa5aa50fd7",
|
| 1733 |
"research/robot-audit-javascript/audit.json": "86ff8a9b2991d3ee6a0a87cbe64e8fb9aa2bad533110d3f8ec9e7c72fb7ecf1f",
|
| 1734 |
"research/robot-audit-python/audit.json": "43f13a031ad5af63c632e61bcfb93f76dd9678aa29904904fa1ade3a6454d9ec",
|
|
|
|
| 2279 |
"skill-impact/app.js": "4f72654da43cdbf44b048c82bc16d8ead7d8c3050286e466743d23056d60fd4e",
|
| 2280 |
"skill-impact/index.html": "a86a39215daa5959b3b093ca6a15a498254501cd03239aae38d0810f6a907d44",
|
| 2281 |
"skill-impact/lab.json": "2b1c8dc7cda172b901be79c93f49f3c79743c031c296532575989cfed0997d80",
|
| 2282 |
+
"skill-impact/manifest.json": "0857729c70edffff1b702fb7da69772946368214e9ee058e9c4f225580f242b4",
|
| 2283 |
"skill-impact/profiles/skill-impact-catalog-fallback/atif-validation.json": "4a3b89219116ccb1ed4942d1d86b53c4cb68b46bbb12c651eb8b66704d5c2a5a",
|
| 2284 |
"skill-impact/profiles/skill-impact-catalog-fallback/experiment.json": "0525de8fb77deed6617984d614906dc28a2c61f66f0970739c81809a8b9af16f",
|
| 2285 |
"skill-impact/profiles/skill-impact-contract-inline/atif-validation.json": "a43d99f77e6e1671729e4cc5c050391b0a3798ff8a2fc50723964a29848902f5",
|
research/manifest.json
CHANGED
|
@@ -1523,7 +1523,7 @@
|
|
| 1523 |
}
|
| 1524 |
},
|
| 1525 |
"presentation": {
|
| 1526 |
-
"source_commit": "
|
| 1527 |
"original_index_sha256": "82b4cf542730fe3b8eb7c32acb9fbbda4abeabfa22a0a68f8008276ebe27a7bf",
|
| 1528 |
"change": "Explicit HTML navigation and attachment downloads for static hosting"
|
| 1529 |
}
|
|
|
|
| 1523 |
}
|
| 1524 |
},
|
| 1525 |
"presentation": {
|
| 1526 |
+
"source_commit": "3da6d996086f351f7d5fe2dae1107283e5f74cc4",
|
| 1527 |
"original_index_sha256": "82b4cf542730fe3b8eb7c32acb9fbbda4abeabfa22a0a68f8008276ebe27a7bf",
|
| 1528 |
"change": "Explicit HTML navigation and attachment downloads for static hosting"
|
| 1529 |
}
|