{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CHCYCGYTOIB4C4ZIQ6Y5MFRADE","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":"dde504c24fea4a1920857080d35be4868089022512671dd1f730cf2d103a371a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T01:02:21Z","title_canon_sha256":"44f9dcaca0dbdbe3de0d4e33aac9b52563c62a1845fe5c922e2ff031084e5e81"},"schema_version":"1.0","source":{"id":"2505.16100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16100","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16100v1","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16100","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_12","alias_value":"CHCYCGYTOIB4","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_16","alias_value":"CHCYCGYTOIB4C4ZI","created_at":"2026-07-05T11:07:29Z"},{"alias_kind":"pith_short_8","alias_value":"CHCYCGYT","created_at":"2026-07-05T11:07:29Z"}],"graph_snapshots":[{"event_id":"sha256:363bb955b238a164b04291b51f19f2fd1075ab380317e4b575ed2af0dac87e1d","target":"graph","created_at":"2026-07-05T11:07:29Z","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/2505.16100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Validating scientific hypotheses is a central challenge in biomedical research, and remains difficult for artificial intelligence (AI) agents due to the complexity of real-world data analysis and evidence interpretation. In this work, we present BioDSA-1K, a benchmark designed to evaluate AI agents on realistic, data-driven biomedical hypothesis validation tasks. BioDSA-1K consists of 1,029 hypothesis-centric tasks paired with 1,177 analysis plans, curated from over 300 published biomedical studies to reflect the structure and reasoning found in authentic research workflows. Each task includes","authors_text":"Benjamin Danek, Jimeng Sun, Zifeng Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T01:02:21Z","title":"BioDSA-1K: Benchmarking Data Science Agents for Biomedical Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16100","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":"sha256:27889833a86b90d822584a29c638e35777cc325c61a2ee2639db0b7ae83ab163","target":"record","created_at":"2026-07-05T11:07:29Z","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":"dde504c24fea4a1920857080d35be4868089022512671dd1f730cf2d103a371a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-22T01:02:21Z","title_canon_sha256":"44f9dcaca0dbdbe3de0d4e33aac9b52563c62a1845fe5c922e2ff031084e5e81"},"schema_version":"1.0","source":{"id":"2505.16100","kind":"arxiv","version":1}},"canonical_sha256":"11c5811b137203c1732887b1d6162019170cd37b97b06fe060a1a4e55a7326ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11c5811b137203c1732887b1d6162019170cd37b97b06fe060a1a4e55a7326ab","first_computed_at":"2026-07-05T11:07:29.935386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:29.935386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+JjynbTrQXbrBeuTrurJvdcshmntMaRJVHlr1NLjIG/L4GkwsWTX85VrPcInWeIfhKw8qH4b7fKmL0leng2NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:29.935880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27889833a86b90d822584a29c638e35777cc325c61a2ee2639db0b7ae83ab163","sha256:363bb955b238a164b04291b51f19f2fd1075ab380317e4b575ed2af0dac87e1d"],"state_sha256":"48290540eb05a36c9a4ba115b22c484ba4a81591e44bec4d77c9f2909b4afc00"}