AGILab-KU/NeuDFT-project / accepted-data.json
AGILab-KU's picture
download
raw
13.5 kB
{
"schema": 1,
"status": "ACCEPTED",
"accepted_final": true,
"approval": {
"accepted_by": "main director after verification"
},
"dataset": "fock1.1M",
"release_scope": "fock1.1M",
"export_kind": "fock1.1M-delivered-rows-only",
"root": ".",
"membership_seal_sha256": "8da57c1718f7c358af5ccb31839fa2e3cfaed2c16416275bdfc47837aac2715b",
"sources": [
"campaign_batch_01",
"campaign_batch_02",
"campaign_batch_03",
"tier0_ge100",
"campaign_batch_04",
"campaign_batch_06",
"campaign_batch_08",
"campaign_batch_10",
"campaign_batch_05",
"campaign_batch_07",
"campaign_batch_09",
"campaign_batch_11",
"campaign_batch_12",
"campaign_batch_14",
"campaign_batch_16",
"campaign_batch_11_ge100_nhn_p21",
"campaign_batch_11_ge100_stat48",
"campaign_batch_13",
"campaign_batch_15",
"tier0_2ch_remaining14"
],
"source_aliases": {
"tier0_ge100": "physical source label differs; mapping recorded in the membership seal"
},
"rows": {
"train": 1073668,
"val": 19981,
"test": 45965,
"total": 1139614
},
"per_split": {
"train": {
"rows": 1073668,
"shards": 73738,
"zip_bytes": 7013562964028
},
"val": {
"rows": 19981,
"shards": 2906,
"zip_bytes": 265502634776
},
"test": {
"rows": 45965,
"shards": 5260,
"zip_bytes": 419797822480
}
},
"zip_bytes_total": 7698863421284,
"artifacts": {
"split": {
"path": "metadata/split.npz",
"sha256": "452c3c18af8898bca56df60431944d3b5cc91ddacbd8b6f0990fa9288783aa63"
},
"repair": {
"path": "metadata/repair.npz",
"sha256": "c9ff018d2096276f726aee3a02b5d976dc708d537562ec390a2b28e34f93c473"
},
"composition": {
"path": "metadata/train_composition.npz",
"sha256": "730da0bbfc922777bf55ea194b186c83433584b6c18424c206c331946ef7d1d4"
},
"index": {
"path": "train_mds/index.json",
"sha256": "f79dfdd8711afb403c8876232ec7692dc615f96c998385bcc3c490ef1894f6bf"
},
"index_val": {
"path": "val_mds/index.json",
"sha256": "1d821477b54a64309c3812961bd8dcfc5c5422f856b22887455f35421851df33"
},
"index_test": {
"path": "test_mds/index.json",
"sha256": "8f4ee2ad6a5c3925bf3ef3f1c14801544d125f896a79171d9078103f246a5121"
},
"manifest_train": {
"path": "train_mds/build_manifest.json",
"sha256": "49df2f157e45be89319f8a195c8b29f4b335e5af814fa38b732abd9874fecf91"
},
"manifest_val": {
"path": "val_mds/build_manifest.json",
"sha256": "d7f4d40b83350df0bb7a4c8d28f55e779af06321629e78dd529f4037065eb9f9"
},
"manifest_test": {
"path": "test_mds/build_manifest.json",
"sha256": "930c24e71b285bc404723a5a61929e39b256792490e432ddb2f98c903df11066"
},
"ledger": {
"path": "metadata/ledger.tsv",
"sha256": "e623e3a50c20021c45367c8435e8ad9fd358fa0cc22f6299dac93c30f5238969"
},
"helm_evaluable": {
"path": "metadata/helm_evaluable_ids.npy",
"sha256": "6a62b89052f70612b4a50251bbe0320f0b2c33acf0b4b9c6a85648514883aa8e"
},
"spin_channel_census": {
"path": "metadata/spin_channel_census.json",
"sha256": "3fd42c1a3e18f6b37cb1996dc083f6dcf93fa6a710346eabc2762c8c3f52c5be"
},
"n_atoms": {
"path": "n_atoms.npy",
"sha256": "586e2ce6de437d77973525b79f27b8f737c02d742303300f66aee90bcce44ec1"
},
"n_edges": {
"path": "n_edges.npy",
"sha256": "79a5de7a45bca82463c1bbf2264ee02708090f3a6df74cd947cdf8d702c38e6e"
},
"spin_multiplicity": {
"path": "spin_multiplicity.npy",
"sha256": "d5afb82fadd72281c034aad3fd149a5f561207b137cd58e346f9fd41af8cd0cf"
},
"gid_tag_map": {
"path": "gid_tag_map.json",
"sha256": "e0e9d206b799c73ea1e6877f60447919ddf957b0ab92998abae293ebb7794763"
},
"shell_order": {
"path": "shell_order.json",
"sha256": "f642efbd2157f5b89f7f0ec3378507a172c74bea98dd7b077daa469ea8eeda25"
},
"n_edges_rcut12": {
"path": "n_edges_rcut12.npy",
"sha256": "4c5d8db29e09648d6fed4bb5f1f95e25a929af00ac2f10644efe73bbb336c1e2"
},
"n_edges_rcut12_provenance": {
"path": "n_edges_rcut12.provenance.json",
"sha256": "2a0b2e992b220204b2ac71189c82191cb0e17bd83281e55a60575ad135a0c48a"
}
},
"training_edge_envelope": {
"population": "train",
"cutoff_angstrom": 12,
"pair_radius_angstrom": 24,
"max_stored_edges": {
"global_idx": 712630,
"stored_edges": 122148,
"cutoff_edges": 83464,
"n_atoms": 350
},
"max_cutoff_edges": {
"global_idx": 24069,
"cutoff_edges": 89250,
"stored_edges": 116622,
"n_atoms": 342
}
},
"census": {
"mode": "export_manifest",
"ids": "delivered global_idx of every split, one file per source group",
"sources": {
"campaign_batch_00": {
"path": "metadata/census/campaign_batch_00.npy",
"sha256": "231b4355ac47a13347ad7cd33d2def3f4c7686d26b5e9c55ba80b8d171134d63",
"rows": 49228,
"train_rows": 46937
},
"campaign_batch_01": {
"path": "metadata/census/campaign_batch_01.npy",
"sha256": "62dde8abe67665880f798dfc125d1b5d5a8311296b169c062ac4c37b7f666bfa",
"rows": 49249,
"train_rows": 46902
},
"campaign_batch_02": {
"path": "metadata/census/campaign_batch_02.npy",
"sha256": "4d7cc31e447ccaf84812b5a252e6240a9fa5c09306daa364ec628826388881b9",
"rows": 49236,
"train_rows": 46860
},
"campaign_batch_03": {
"path": "metadata/census/campaign_batch_03.npy",
"sha256": "f9f377d5b97f89a011fe13600289ed5098ae4f0c7fde88ee858fe9cd2c29aa82",
"rows": 49271,
"train_rows": 46843
},
"campaign_batch_04": {
"path": "metadata/census/campaign_batch_04.npy",
"sha256": "92def2b4d9cace6ea397f08271b7d33c613a43eebd9fa0534e3698295746d81b",
"rows": 49281,
"train_rows": 46903
},
"campaign_batch_05": {
"path": "metadata/census/campaign_batch_05.npy",
"sha256": "75b52fbc8cdafa25f453007d516eefe2f86eebe3147df6182b4ac076a34c93af",
"rows": 49272,
"train_rows": 46904
},
"campaign_batch_06": {
"path": "metadata/census/campaign_batch_06.npy",
"sha256": "1170333fddf061dcd0c1a1f77a533ffbd34162c35f4d84a6bc9aec9fe9b82874",
"rows": 49270,
"train_rows": 46877
},
"campaign_batch_07": {
"path": "metadata/census/campaign_batch_07.npy",
"sha256": "0adc522bacf5f05cc9d94737648788342ee9507fff9402bffe9aa3f002835a16",
"rows": 49232,
"train_rows": 46940
},
"campaign_batch_08": {
"path": "metadata/census/campaign_batch_08.npy",
"sha256": "a55f295d19bd2b3ef481041442e87ed6cb5a25faf64d28e99d93f5f2efdb3697",
"rows": 49209,
"train_rows": 46882
},
"campaign_batch_09": {
"path": "metadata/census/campaign_batch_09.npy",
"sha256": "c19e7d1915271a783c4ea01dc56a24b97414e6072cf86bd3be0785c687847821",
"rows": 49197,
"train_rows": 46846
},
"campaign_batch_10": {
"path": "metadata/census/campaign_batch_10.npy",
"sha256": "ef2ffd6640477ce81b5c3026a0aa72695ed4d5f393ae5609f3ab6f17ae3db1b1",
"rows": 49283,
"train_rows": 46866
},
"campaign_batch_11": {
"path": "metadata/census/campaign_batch_11.npy",
"sha256": "fdbd5563c367b78c263576f97c0d36fd1352f8e25315f675cd90787f8284b3df",
"rows": 49264,
"train_rows": 46927
},
"campaign_batch_11_ge100_nhn_p21": {
"path": "metadata/census/campaign_batch_11_ge100_nhn_p21.npy",
"sha256": "b0ff76fde41808689b24ab6372ad311bffe23290da5f29403bc7f7892111d29c",
"rows": 25,
"train_rows": 24
},
"campaign_batch_11_ge100_stat48": {
"path": "metadata/census/campaign_batch_11_ge100_stat48.npy",
"sha256": "e4cf691be3353912286b58a315b2970a2de3f8e55d625081f2a90fc5abfc9d03",
"rows": 661,
"train_rows": 632
},
"campaign_batch_12": {
"path": "metadata/census/campaign_batch_12.npy",
"sha256": "5d018ee0c1366f85e9342a356f276b08bf80064cb0cf58f2325b48165e8a2b28",
"rows": 49275,
"train_rows": 46893
},
"campaign_batch_13": {
"path": "metadata/census/campaign_batch_13.npy",
"sha256": "704d06a332a650ba98697743af20061438a58dd317b460f9b58f084e7f49d6df",
"rows": 49298,
"train_rows": 46908
},
"campaign_batch_14": {
"path": "metadata/census/campaign_batch_14.npy",
"sha256": "0255c5a8576888d71d3fea3708eac62df7860a1c4c2e61cf59ec1f189c9d6d07",
"rows": 49288,
"train_rows": 46852
},
"campaign_batch_15": {
"path": "metadata/census/campaign_batch_15.npy",
"sha256": "bf6d0f71a32354a2dcaa0e150b9a0d9ddf4ef37b8dae838a58815ef56173dcd9",
"rows": 49270,
"train_rows": 46904
},
"campaign_batch_16": {
"path": "metadata/census/campaign_batch_16.npy",
"sha256": "63e873cdafdf7fb39cfb2231603b54a660ccfd6b89b9af31e0f40254061fc6d2",
"rows": 49279,
"train_rows": 46898
},
"omol4m_v5": {
"path": "metadata/census/omol4m_v5.npy",
"sha256": "42eac8999348ad3091f39f0c3cd168a7625de60aa0292a1c32ae2ee98971e5d4",
"rows": 105157,
"train_rows": 99734
},
"omol4m_v6-added": {
"path": "metadata/census/omol4m_v6-added.npy",
"sha256": "e82f3d90de606d9e9bc56c511688310008bff37b61ecb496dc0f651e209e665b",
"rows": 48328,
"train_rows": 45139
},
"omol_csh1k": {
"path": "metadata/census/omol_csh1k.npy",
"sha256": "19ed6d3df69ef2440ea8af998f9d01998e312897ad87e88e00d274a1fa130238",
"rows": 1008,
"train_rows": 0
},
"omol_csh58k": {
"path": "metadata/census/omol_csh58k.npy",
"sha256": "3b1920ef4da64e8f823f04e332b50509783255aadb96651c7a4ec94533e914a3",
"rows": 56275,
"train_rows": 53231
},
"omol_csh5k": {
"path": "metadata/census/omol_csh5k.npy",
"sha256": "631eb5c4a2e7c4b9fba7c53e2c920031b4217878cd5cb2bcf38b752710882677",
"rows": 4813,
"train_rows": 0
},
"tier0_2ch_a": {
"path": "metadata/census/tier0_2ch_a.npy",
"sha256": "08c049d57ed7739bb1ae946f5d72afb96decc13014e9c4412bb545ddff7c83ae",
"rows": 63917,
"train_rows": 56750
},
"tier0_2ch_remaining14": {
"path": "metadata/census/tier0_2ch_remaining14.npy",
"sha256": "5909219b0d3e883db0d76f1be1e7dd8a2c76da6858fed7ccaf2c29fd61010dd9",
"rows": 6621,
"train_rows": 6496
},
"tier0_ge100": {
"path": "metadata/census/tier0_ge100.npy",
"sha256": "4e0125da51c799a0a63919193382d1268f4e1827935a5c454de231628e955600",
"rows": 4379,
"train_rows": 3993
},
"tier1_2ch_orca3d": {
"path": "metadata/census/tier1_2ch_orca3d.npy",
"sha256": "ab6f7b4aa0fe0481e653870a471a69ea6f70a699cdf86f72adf2d6337e2ca862",
"rows": 8759,
"train_rows": 8338
},
"tier1_2ch_orca3d_ge100": {
"path": "metadata/census/tier1_2ch_orca3d_ge100.npy",
"sha256": "aafb6c5184245865028b783cc902edb19aa53d54e39e22f115dc87dbecfb1935",
"rows": 2269,
"train_rows": 2189
}
}
},
"retained_train_ids": {
"path": "metadata/retained_train_ids.npy",
"sha256": "74f8acbd06ab950c3cd188d79056b310bdd17e52ceb809a3513c1e0abb75b772",
"rows": 1073668
},
"exclude": null,
"repair_provenance": {
"full_sha256": "53d1b56770356c5417082756690b609e736059aa1b52e43efcf541558db30ece",
"full_rows": 44149,
"subset_rows": 18763,
"subset_sha256": "c9ff018d2096276f726aee3a02b5d976dc708d537562ec390a2b28e34f93c473",
"every_subset_row_equals_full": true,
"subset_rows_all_delivered": true,
"full_rows_delivered_missing_from_subset": 0
},
"composition_provenance": {
"rows": 1073668,
"rule": "payload atomic numbers from the 12 A validation scan",
"formula_equals_payload": true,
"cross_checked_rows_against_census_atomic_numbers": 876220,
"mismatches": 0,
"note": "the 12 A scan over the export root re-derives composition from payload atomic numbers"
},
"heldout_evaluations": {
"helm": {
"schema": 1,
"source_report_sha256": "821be652a45ea7fca145e1bd803852ec159a420b13bac60af45f217b15b3fbdb",
"helm_id_list_sha256": "2aeb22036317745ff0393982515c6cce7042eab055cce7d56c7bdae7c9315485",
"split_sha256": "452c3c18af8898bca56df60431944d3b5cc91ddacbd8b6f0990fa9288783aa63",
"population": 5992,
"excluded": 171,
"evaluable": 5821,
"train_val_membership": 0,
"train_val_formula_leakage": 0,
"note": "the 5,992-ID list and the 171 non-delivered IDs live in the membership seal; this bundle carries only the 5,821 evaluable IDs; HELM metrics select them, never the whole test key"
}
},
"spin_channel_census": {
"path": "metadata/spin_channel_census.json",
"sha256": "3fd42c1a3e18f6b37cb1996dc083f6dcf93fa6a710346eabc2762c8c3f52c5be",
"violation_total": 0,
"population": {
"train": 1073668,
"val": 19981,
"test": 45965
}
},
"helm_evaluable": {
"path": "metadata/helm_evaluable_ids.npy",
"sha256": "6a62b89052f70612b4a50251bbe0320f0b2c33acf0b4b9c6a85648514883aa8e",
"count": 5821
},
"helm_ids": {
"in_bundle": false,
"sha256": "2aeb22036317745ff0393982515c6cce7042eab055cce7d56c7bdae7c9315485",
"population": 5992,
"excluded": 171,
"provenance": "membership_seal"
},
"physical": {
"pure_shards_byte_identical_to_source": true,
"rebuilt_mixed_shards": "train/val/test_mds/part_r1_<source part>/*: delivered rows only, one export part per source part with that part's shell-order record, sample bytes verified identical",
"seal_overlay_part": "val_mds,test_mds/part_seal_r1"
},
"open_gates": [
"preflight/stats-guard export-receipt mode and 20th source (owner change)"
],
"created_utc": "2026-10-26T07:58:30Z",
"content_digest": {
"sha256": "c409da08be58f50a3907689c614ae154f01838b4f6a9b9c82070d4a7b5e9544d",
"rule": "sha256 of json.dumps(receipt minus status,accepted_final,approval,content_digest,created_utc, sort_keys=True, separators=(',',':'))"
}
}

Xet Storage Details

Size:
13.5 kB
·
Xet hash:
a84e214fa959288c8b36c053b5c525f36a714ef717bcf6b4df862aa0f0b2fd48

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.