{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HP3XB6O5YXSOJRSB4UO3EERAVS","short_pith_number":"pith:HP3XB6O5","schema_version":"1.0","canonical_sha256":"3bf770f9ddc5e4e4c641e51db21220acb3649a82a43503e517750d7e1eb49720","source":{"kind":"arxiv","id":"2410.22360","version":1},"attestation_state":"computed","paper":{"title":"ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakanksha Naik, Benjamin Newman, Daniel S. Weld, Joseph Chee Chang, Juho Kim, Kyle Lo, Pao Siangliulue, Raymond Fok, Yoonjoo Lee","submitted_at":"2024-10-25T18:31:50Z","abstract_excerpt":"When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate these tables using language models (LMs)? In this work, we introduce a framework that leverages LMs to perform this task by decomposing it into separate schema and value generation steps. To enable experimentation, we address two main challenges: First, we overcome a lack of high-quality datasets to benchmark table generation by curating and releasi"},"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":"2410.22360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T18:31:50Z","cross_cats_sorted":[],"title_canon_sha256":"a89e390c6794429695c860585cfdbd6f754376355cdaa4e95f0296e48def6bb0","abstract_canon_sha256":"689dab274439febba5354306e8bad19acdb2a13fca5b618390af633c4875d3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:15.351204Z","signature_b64":"GfpaqOICSGUl0/pGO99Zq9QlDT+veX8oEQL/aALF5g/qCv8Xvoye6CiNl8fdC1hYgnTE6YCoRKfjTpBzh7W8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf770f9ddc5e4e4c641e51db21220acb3649a82a43503e517750d7e1eb49720","last_reissued_at":"2026-07-05T09:28:15.350765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:15.350765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aakanksha Naik, Benjamin Newman, Daniel S. Weld, Joseph Chee Chang, Juho Kim, Kyle Lo, Pao Siangliulue, Raymond Fok, Yoonjoo Lee","submitted_at":"2024-10-25T18:31:50Z","abstract_excerpt":"When conducting literature reviews, scientists often create literature review tables - tables whose rows are publications and whose columns constitute a schema, a set of aspects used to compare and contrast the papers. Can we automatically generate these tables using language models (LMs)? In this work, we introduce a framework that leverages LMs to perform this task by decomposing it into separate schema and value generation steps. To enable experimentation, we address two main challenges: First, we overcome a lack of high-quality datasets to benchmark table generation by curating and releasi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22360","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/2410.22360/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":"2410.22360","created_at":"2026-07-05T09:28:15.350823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22360v1","created_at":"2026-07-05T09:28:15.350823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22360","created_at":"2026-07-05T09:28:15.350823+00:00"},{"alias_kind":"pith_short_12","alias_value":"HP3XB6O5YXSO","created_at":"2026-07-05T09:28:15.350823+00:00"},{"alias_kind":"pith_short_16","alias_value":"HP3XB6O5YXSOJRSB","created_at":"2026-07-05T09:28:15.350823+00:00"},{"alias_kind":"pith_short_8","alias_value":"HP3XB6O5","created_at":"2026-07-05T09:28:15.350823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.00361","citing_title":"Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS","json":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS.json","graph_json":"https://pith.science/api/pith-number/HP3XB6O5YXSOJRSB4UO3EERAVS/graph.json","events_json":"https://pith.science/api/pith-number/HP3XB6O5YXSOJRSB4UO3EERAVS/events.json","paper":"https://pith.science/paper/HP3XB6O5"},"agent_actions":{"view_html":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS","download_json":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS.json","view_paper":"https://pith.science/paper/HP3XB6O5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22360&json=true","fetch_graph":"https://pith.science/api/pith-number/HP3XB6O5YXSOJRSB4UO3EERAVS/graph.json","fetch_events":"https://pith.science/api/pith-number/HP3XB6O5YXSOJRSB4UO3EERAVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS/action/storage_attestation","attest_author":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS/action/author_attestation","sign_citation":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS/action/citation_signature","submit_replication":"https://pith.science/pith/HP3XB6O5YXSOJRSB4UO3EERAVS/action/replication_record"}},"created_at":"2026-07-05T09:28:15.350823+00:00","updated_at":"2026-07-05T09:28:15.350823+00:00"}