{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L7XGLXUWLIBDHFWDNGZZGENKBR","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":"83e73e6b3e9edf8760583d888fefa5b59c7b916bea8c3ed40ff74da4148a5bed","cross_cats_sorted":["cs.AI","cs.IR","physics.soc-ph"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T16:37:58Z","title_canon_sha256":"e62a4a295bd2ed9269234d7e5cdabd21b174751348d584cb5bc1268b538987c7"},"schema_version":"1.0","source":{"id":"2409.13740","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13740","created_at":"2026-07-05T09:12:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13740v2","created_at":"2026-07-05T09:12:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13740","created_at":"2026-07-05T09:12:09Z"},{"alias_kind":"pith_short_12","alias_value":"L7XGLXUWLIBD","created_at":"2026-07-05T09:12:09Z"},{"alias_kind":"pith_short_16","alias_value":"L7XGLXUWLIBDHFWD","created_at":"2026-07-05T09:12:09Z"},{"alias_kind":"pith_short_8","alias_value":"L7XGLXUW","created_at":"2026-07-05T09:12:09Z"}],"graph_snapshots":[{"event_id":"sha256:9f35ae70b8827c844dda5ae624ef131f70d15953649b594f296eef2424d2a206","target":"graph","created_at":"2026-07-05T09:12:09Z","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/2409.13740/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are known to hallucinate incorrect information, and it is unclear if they are sufficiently accurate and reliable for use in scientific research. We developed a rigorous human-AI comparison methodology to evaluate language model agents on real-world literature search tasks covering information retrieval, summarization, and contradiction detection tasks. We show that PaperQA2, a frontier language model agent optimized for improved factuality, matches or exceeds subject matter expert performance on three realistic literature research tasks without any restrictions on humans (i.e.,","authors_text":"Andrew D. White, James D. Braza, Jon M. Laurent, Manvitha Ponnapati, Michaela Hinks, Michael D. Skarlinski, Michael J. Hammerling, Sam Cox, Samuel G. Rodriques","cross_cats":["cs.AI","cs.IR","physics.soc-ph"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T16:37:58Z","title":"Language agents achieve superhuman synthesis of scientific knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13740","kind":"arxiv","version":2},"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:f6211d4761704e4fcfd396ae46c93a48a7566ddca89bab44b50a1a82b99a657f","target":"record","created_at":"2026-07-05T09:12:09Z","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":"83e73e6b3e9edf8760583d888fefa5b59c7b916bea8c3ed40ff74da4148a5bed","cross_cats_sorted":["cs.AI","cs.IR","physics.soc-ph"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T16:37:58Z","title_canon_sha256":"e62a4a295bd2ed9269234d7e5cdabd21b174751348d584cb5bc1268b538987c7"},"schema_version":"1.0","source":{"id":"2409.13740","kind":"arxiv","version":2}},"canonical_sha256":"5fee65de965a023396c369b39311aa0c46a9d789eecf451fa0afe21e75f4c981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fee65de965a023396c369b39311aa0c46a9d789eecf451fa0afe21e75f4c981","first_computed_at":"2026-07-05T09:12:09.842943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:09.842943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aAuPF+5O92EiSSk9jxOGxLyk+KR6ZavheMOM0Low308vh4wel/qIZ6fa54qmQYrr0VCIQ+rUbMvkpQ5Mqo/zCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:09.843443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13740","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6211d4761704e4fcfd396ae46c93a48a7566ddca89bab44b50a1a82b99a657f","sha256:9f35ae70b8827c844dda5ae624ef131f70d15953649b594f296eef2424d2a206"],"state_sha256":"a42a52770ffbd5f1346894b6fa9b27d7b32d198422ddf2cd3597ed6ef5f49f74"}