{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QLSOI33YSZ7O2BIPYL7LGN5V4V","short_pith_number":"pith:QLSOI33Y","schema_version":"1.0","canonical_sha256":"82e4e46f78967eed050fc2feb337b5e562c80c002e3b50ea293dd2774759ff9d","source":{"kind":"arxiv","id":"2606.04261","version":1},"attestation_state":"computed","paper":{"title":"Can Generalist Agents Automate Data Curation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.ET","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Nguyen, Dawn Song, Feiyang Kang, Frederic Sala, Hanze Li, Jiaqi W. Ma, Mahavir Dabas, Ruoxi Jia","submitted_at":"2026-06-02T22:26:53Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.04261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T22:26:53Z","cross_cats_sorted":["cs.CL","cs.CV","cs.ET","cs.LG"],"title_canon_sha256":"64decccfe3ac2148fb4d0cad8aec3cdd896c52a68faac689b8e87072f3202732","abstract_canon_sha256":"b94ed096176dbecc567ac7d471c6bb57d3513a4e9e6e9bf114b64d8718097479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:00.792186Z","signature_b64":"e2Id7oWy4tAmV+YRm3Ozaa8VD56udPUNzfJwfKMQ/rrB2RDHO4xi18jIIls5CIgv4TpVD7dlujRb6T9Hbjk4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e4e46f78967eed050fc2feb337b5e562c80c002e3b50ea293dd2774759ff9d","last_reissued_at":"2026-06-04T01:09:00.791690Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:00.791690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Generalist Agents Automate Data Curation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.ET","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Nguyen, Dawn Song, Feiyang Kang, Frederic Sala, Hanze Li, Jiaqi W. Ma, Mahavir Dabas, Ruoxi Jia","submitted_at":"2026-06-02T22:26:53Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04261","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04261/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.04261","created_at":"2026-06-04T01:09:00.791757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04261v1","created_at":"2026-06-04T01:09:00.791757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04261","created_at":"2026-06-04T01:09:00.791757+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLSOI33YSZ7O","created_at":"2026-06-04T01:09:00.791757+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLSOI33YSZ7O2BIP","created_at":"2026-06-04T01:09:00.791757+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLSOI33Y","created_at":"2026-06-04T01:09:00.791757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V","json":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V.json","graph_json":"https://pith.science/api/pith-number/QLSOI33YSZ7O2BIPYL7LGN5V4V/graph.json","events_json":"https://pith.science/api/pith-number/QLSOI33YSZ7O2BIPYL7LGN5V4V/events.json","paper":"https://pith.science/paper/QLSOI33Y"},"agent_actions":{"view_html":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V","download_json":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V.json","view_paper":"https://pith.science/paper/QLSOI33Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04261&json=true","fetch_graph":"https://pith.science/api/pith-number/QLSOI33YSZ7O2BIPYL7LGN5V4V/graph.json","fetch_events":"https://pith.science/api/pith-number/QLSOI33YSZ7O2BIPYL7LGN5V4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V/action/storage_attestation","attest_author":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V/action/author_attestation","sign_citation":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V/action/citation_signature","submit_replication":"https://pith.science/pith/QLSOI33YSZ7O2BIPYL7LGN5V4V/action/replication_record"}},"created_at":"2026-06-04T01:09:00.791757+00:00","updated_at":"2026-06-04T01:09:00.791757+00:00"}