{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V5T6XRKFLW2PFRBXCIY3WR5NF5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"10a03160c833d67bf5f4228c7b258fa657d0d2a8ab9dd7aedd77ecb59a7cfd34","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T02:23:53Z","title_canon_sha256":"529eac416395574b8fb4db2126248736047bee9daa3285d18356efe9056c31ad"},"schema_version":"1.0","source":{"id":"2607.20465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20465","created_at":"2026-07-24T00:23:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20465v1","created_at":"2026-07-24T00:23:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20465","created_at":"2026-07-24T00:23:17Z"},{"alias_kind":"pith_short_12","alias_value":"V5T6XRKFLW2P","created_at":"2026-07-24T00:23:17Z"},{"alias_kind":"pith_short_16","alias_value":"V5T6XRKFLW2PFRBX","created_at":"2026-07-24T00:23:17Z"},{"alias_kind":"pith_short_8","alias_value":"V5T6XRKF","created_at":"2026-07-24T00:23:17Z"}],"graph_snapshots":[{"event_id":"sha256:17a349c91e075eed3f5b9e7aa922d351eacbae07c5d00ca2af0daecfb954c847","target":"graph","created_at":"2026-07-24T00:23:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.20465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end. We view LLM-driven data preparation as comprising two complementary capabilities: data construction, which transforms raw sources into supervised training data, and data quality evaluation, which predicts the training value of candidate datasets before downstream training; throughout, \"quality\" refers to downstream training utility rather than surface-level ","authors_text":"Bohan Zeng, Conghui He, Hao Liang, Jianzhuo Du, Linzhuang Sun, Meiyi Qiang, Qifeng Cai, Qifeng Xia, Ruichuan An, Sizhe Qiu, Wentao Zhang, Xiaochen Ma, Yibo Lin, Zhaoyang Han","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T02:23:53Z","title":"DataPrep-Bench: Benchmarking LLMs as Training Data Preparators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20465","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:96a4aa54c4a514fb6a0a05ec7485c331541ec5391775044e6af0133fbd1792b4","target":"record","created_at":"2026-07-24T00:23:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"10a03160c833d67bf5f4228c7b258fa657d0d2a8ab9dd7aedd77ecb59a7cfd34","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T02:23:53Z","title_canon_sha256":"529eac416395574b8fb4db2126248736047bee9daa3285d18356efe9056c31ad"},"schema_version":"1.0","source":{"id":"2607.20465","kind":"arxiv","version":1}},"canonical_sha256":"af67ebc5455db4f2c4371231bb47ad2f4f8dda92351f370a8b012c65954bdf40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af67ebc5455db4f2c4371231bb47ad2f4f8dda92351f370a8b012c65954bdf40","first_computed_at":"2026-07-24T00:23:17.061257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:17.061257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7G+f48931PWSKTHlYKYPI2rfIRqR+3oZ1/cFNXikrfjE1bTw0+2CcZy+W82uNsA2dkUQ3TDHgqgZ9KTVk3E0Aw==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:17.062151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96a4aa54c4a514fb6a0a05ec7485c331541ec5391775044e6af0133fbd1792b4","sha256:17a349c91e075eed3f5b9e7aa922d351eacbae07c5d00ca2af0daecfb954c847"],"state_sha256":"ad316f01e1993223b9d100896017a629aa6cf4c6eb4964019908ef4e34b4a8ca"}