{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AXK7XZCP7VK7IJD25VPV3RR262","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":"37ed67f8be1b8328b73ee68cc36667dd149ace3d784a990cbffb9fc8e260ed45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:58:10Z","title_canon_sha256":"1338bc06f136ce93a8281d257143c70de8d71df236f88d4a6b9dc580192dff67"},"schema_version":"1.0","source":{"id":"2305.14336","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14336","created_at":"2026-07-05T09:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14336v5","created_at":"2026-07-05T09:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14336","created_at":"2026-07-05T09:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"AXK7XZCP7VK7","created_at":"2026-07-05T09:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"AXK7XZCP7VK7IJD2","created_at":"2026-07-05T09:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"AXK7XZCP","created_at":"2026-07-05T09:38:20Z"}],"graph_snapshots":[{"event_id":"sha256:eeb447a3c96b4bbc963ec32aeee3f6f2fa3f82754855d97fec664c7bbbb26a71","target":"graph","created_at":"2026-07-05T09:38:20Z","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/2305.14336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alan Ritter, Dayne Freitag, Fan Bai, Gabriel Stanovsky, Junmo Kang, Mark Dredze","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:58:10Z","title":"Schema-Driven Information Extraction from Heterogeneous Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14336","kind":"arxiv","version":5},"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":"sha256:7c6d8a847a2ba2524f2b7d00dfe09dfc37c1e0f91e7313ed0b047886b6ad7ecf","target":"record","created_at":"2026-07-05T09:38:20Z","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":"37ed67f8be1b8328b73ee68cc36667dd149ace3d784a990cbffb9fc8e260ed45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:58:10Z","title_canon_sha256":"1338bc06f136ce93a8281d257143c70de8d71df236f88d4a6b9dc580192dff67"},"schema_version":"1.0","source":{"id":"2305.14336","kind":"arxiv","version":5}},"canonical_sha256":"05d5fbe44ffd55f4247aed5f5dc63af695fbbd03ae89c273c88f6f23ebe5636c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05d5fbe44ffd55f4247aed5f5dc63af695fbbd03ae89c273c88f6f23ebe5636c","first_computed_at":"2026-07-05T09:38:20.653031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:20.653031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KCzdqWBmy/dE7g8tMLYgpA5/h0QdFvPaOCAdLmc5DJ6/eVon+UssDuoM8h/oQFIQ/Jlg0wuJQMWDa9wy7P0lCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:20.653497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14336","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c6d8a847a2ba2524f2b7d00dfe09dfc37c1e0f91e7313ed0b047886b6ad7ecf","sha256:eeb447a3c96b4bbc963ec32aeee3f6f2fa3f82754855d97fec664c7bbbb26a71"],"state_sha256":"a3e77c876c42b1924d13f4cb6470e34e5db8395b6185acf653353810265db0c1"}