{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QLSOI33YSZ7O2BIPYL7LGN5V4V","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":"b94ed096176dbecc567ac7d471c6bb57d3513a4e9e6e9bf114b64d8718097479","cross_cats_sorted":["cs.CL","cs.CV","cs.ET","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T22:26:53Z","title_canon_sha256":"64decccfe3ac2148fb4d0cad8aec3cdd896c52a68faac689b8e87072f3202732"},"schema_version":"1.0","source":{"id":"2606.04261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04261","created_at":"2026-06-04T01:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04261v1","created_at":"2026-06-04T01:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04261","created_at":"2026-06-04T01:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"QLSOI33YSZ7O","created_at":"2026-06-04T01:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"QLSOI33YSZ7O2BIP","created_at":"2026-06-04T01:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"QLSOI33Y","created_at":"2026-06-04T01:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:6096b0de67508cda9b1e7c229267e6131cc5114f78686b69f036e0fe677ae0fa","target":"graph","created_at":"2026-06-04T01:09:00Z","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/2606.04261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback. We ask whether generalist coding agents can automate this data-curation loop. We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite while giving agents command-line access to inspect data, implement policies, submit them to a fixed training/evaluation pipeline, and revise. In a vision-language instruction-tuning ","authors_text":"Adam Nguyen, Dawn Song, Feiyang Kang, Frederic Sala, Hanze Li, Jiaqi W. Ma, Mahavir Dabas, Ruoxi Jia","cross_cats":["cs.CL","cs.CV","cs.ET","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T22:26:53Z","title":"Can Generalist Agents Automate Data Curation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04261","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:d26f8f765fb249608482f87668edfe852a6d9b83d8e96b731b887dd1696c42bf","target":"record","created_at":"2026-06-04T01:09:00Z","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":"b94ed096176dbecc567ac7d471c6bb57d3513a4e9e6e9bf114b64d8718097479","cross_cats_sorted":["cs.CL","cs.CV","cs.ET","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T22:26:53Z","title_canon_sha256":"64decccfe3ac2148fb4d0cad8aec3cdd896c52a68faac689b8e87072f3202732"},"schema_version":"1.0","source":{"id":"2606.04261","kind":"arxiv","version":1}},"canonical_sha256":"82e4e46f78967eed050fc2feb337b5e562c80c002e3b50ea293dd2774759ff9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82e4e46f78967eed050fc2feb337b5e562c80c002e3b50ea293dd2774759ff9d","first_computed_at":"2026-06-04T01:09:00.791690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:00.791690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e2Id7oWy4tAmV+YRm3Ozaa8VD56udPUNzfJwfKMQ/rrB2RDHO4xi18jIIls5CIgv4TpVD7dlujRb6T9Hbjk4Bw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:00.792186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d26f8f765fb249608482f87668edfe852a6d9b83d8e96b731b887dd1696c42bf","sha256:6096b0de67508cda9b1e7c229267e6131cc5114f78686b69f036e0fe677ae0fa"],"state_sha256":"5ba711902c6eec3d6a80a787f2273793a961d97f751fe7d9b0188993434c849e"}