{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AXK7XZCP7VK7IJD25VPV3RR262","short_pith_number":"pith:AXK7XZCP","schema_version":"1.0","canonical_sha256":"05d5fbe44ffd55f4247aed5f5dc63af695fbbd03ae89c273c88f6f23ebe5636c","source":{"kind":"arxiv","id":"2305.14336","version":5},"attestation_state":"computed","paper":{"title":"Schema-Driven Information Extraction from Heterogeneous Tables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Dayne Freitag, Fan Bai, Gabriel Stanovsky, Junmo Kang, Mark Dredze","submitted_at":"2023-05-23T17:58:10Z","abstract_excerpt":"In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM's capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature, material science journals, and webpages. We use this collection of annotated tables to evaluate the ability of open-source and API-based language m"},"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":"2305.14336","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:58:10Z","cross_cats_sorted":[],"title_canon_sha256":"1338bc06f136ce93a8281d257143c70de8d71df236f88d4a6b9dc580192dff67","abstract_canon_sha256":"37ed67f8be1b8328b73ee68cc36667dd149ace3d784a990cbffb9fc8e260ed45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:20.653497Z","signature_b64":"KCzdqWBmy/dE7g8tMLYgpA5/h0QdFvPaOCAdLmc5DJ6/eVon+UssDuoM8h/oQFIQ/Jlg0wuJQMWDa9wy7P0lCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05d5fbe44ffd55f4247aed5f5dc63af695fbbd03ae89c273c88f6f23ebe5636c","last_reissued_at":"2026-07-05T09:38:20.653031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:20.653031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Schema-Driven Information Extraction from Heterogeneous Tables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Ritter, Dayne Freitag, Fan Bai, Gabriel Stanovsky, Junmo Kang, Mark Dredze","submitted_at":"2023-05-23T17:58:10Z","abstract_excerpt":"In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM's capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature, material science journals, and webpages. We use this collection of annotated tables to evaluate the ability of open-source and API-based language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14336","kind":"arxiv","version":5},"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/2305.14336/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":"2305.14336","created_at":"2026-07-05T09:38:20.653098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14336v5","created_at":"2026-07-05T09:38:20.653098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14336","created_at":"2026-07-05T09:38:20.653098+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXK7XZCP7VK7","created_at":"2026-07-05T09:38:20.653098+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXK7XZCP7VK7IJD2","created_at":"2026-07-05T09:38:20.653098+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXK7XZCP","created_at":"2026-07-05T09:38:20.653098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04573","citing_title":"Give me Some Hard Questions: Synthetic Data Generation for Clinical QA","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262","json":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262.json","graph_json":"https://pith.science/api/pith-number/AXK7XZCP7VK7IJD25VPV3RR262/graph.json","events_json":"https://pith.science/api/pith-number/AXK7XZCP7VK7IJD25VPV3RR262/events.json","paper":"https://pith.science/paper/AXK7XZCP"},"agent_actions":{"view_html":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262","download_json":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262.json","view_paper":"https://pith.science/paper/AXK7XZCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14336&json=true","fetch_graph":"https://pith.science/api/pith-number/AXK7XZCP7VK7IJD25VPV3RR262/graph.json","fetch_events":"https://pith.science/api/pith-number/AXK7XZCP7VK7IJD25VPV3RR262/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262/action/storage_attestation","attest_author":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262/action/author_attestation","sign_citation":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262/action/citation_signature","submit_replication":"https://pith.science/pith/AXK7XZCP7VK7IJD25VPV3RR262/action/replication_record"}},"created_at":"2026-07-05T09:38:20.653098+00:00","updated_at":"2026-07-05T09:38:20.653098+00:00"}