{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5VKMMTNGJ5PD2WMSELN4TA2DIS","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":"80e4e9fee16fccb1dc7b570d7dba221405ee6689e9e9df3fbdef80d7653b8b7e","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:07:42Z","title_canon_sha256":"7f78669d33e4ab53a3b64652f2a9680c0d4e0a0f6312c35d29057aba5bd40665"},"schema_version":"1.0","source":{"id":"2411.14199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14199","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14199v1","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14199","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"5VKMMTNGJ5PD","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"5VKMMTNGJ5PD2WMS","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"5VKMMTNG","created_at":"2026-07-05T09:38:43Z"}],"graph_snapshots":[{"event_id":"sha256:093123edc57be0b17baf82594765f8ac190d9a30bdae510474161e1ab138c2d4","target":"graph","created_at":"2026-07-05T09:38:43Z","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/2411.14199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 million open-access papers and synthesizing citation-backed responses. To evaluate OpenScholar, we develop ScholarQABench, the first large-scale multi-domain benchmark for literature search, comprising 2,967 expert-written queries and 208 long-form answers across computer science, physics, neuroscienc","authors_text":"Akari Asai, Amanpreet Singh, Bohao Wu, Dan Weld, David Wadden, Doug Downey, Graham Neubig, Hannaneh Hajishirzi, Hao Tong, Jacqueline He, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Luke Zettlemoyer, Matt Latzke, Mike D'Arcy, Minyang Tian, Pang Wei Koh, Pan Ji, Rulin Shao, Sergey Feldman, Shengyan Liu, Weijia Shi, Wen-tau Yih, Yanyu Xiong","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:07:42Z","title":"OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14199","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":"sha256:62d9f921de40e79389b162409d4335a1ab8d444be7545750c231cad34f478084","target":"record","created_at":"2026-07-05T09:38:43Z","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":"80e4e9fee16fccb1dc7b570d7dba221405ee6689e9e9df3fbdef80d7653b8b7e","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T15:07:42Z","title_canon_sha256":"7f78669d33e4ab53a3b64652f2a9680c0d4e0a0f6312c35d29057aba5bd40665"},"schema_version":"1.0","source":{"id":"2411.14199","kind":"arxiv","version":1}},"canonical_sha256":"ed54c64da64f5e3d599222dbc9834344857f58b5a1013a2d9b291386963f97f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed54c64da64f5e3d599222dbc9834344857f58b5a1013a2d9b291386963f97f9","first_computed_at":"2026-07-05T09:38:43.190207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:43.190207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kHqflfo7SIVl4g5K8/EBVudFzQjakeqA2owMwPXp9TQW/Ii/N7YG5Eq+6Lo17w+uf5359MgbQ6xZcUYOIFWDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:43.190650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62d9f921de40e79389b162409d4335a1ab8d444be7545750c231cad34f478084","sha256:093123edc57be0b17baf82594765f8ac190d9a30bdae510474161e1ab138c2d4"],"state_sha256":"f24bfaba840832bd04681ae477e49d98fa7690987b866abc433cc0033bd26fed"}