{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X32OJUTKSK7G746YDDDK22ZAMT","short_pith_number":"pith:X32OJUTK","schema_version":"1.0","canonical_sha256":"bef4e4d26a92be6ff3d818c6ad6b2064fe7cf3929617a45b93e7800ca2392e10","source":{"kind":"arxiv","id":"2305.13186","version":3},"attestation_state":"computed","paper":{"title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Liangming Pan, Min-Yen Kan, Preslav Nakov, Qian Liu, Xinyuan Lu","submitted_at":"2023-05-22T16:13:50Z","abstract_excerpt":"Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence. We present SCITAB, a challenging evaluation dataset consisting of 1.2K expert-verified scientific claims that 1) originate from authentic scientific publications and 2) require compositional reasoning for verification. The claims are paired with evidence-containing scientific tables annotated with labels. Through extensive evaluations, we demonstrate that SCITAB poses a significant challenge to state-of-the-art models, including"},"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":"2305.13186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:13:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8e57e32e5d9743b7bfb879b619a175bbfb1cd9dc59232f9a7b75e38f7c539341","abstract_canon_sha256":"486c63e50034e451dd11c22c1f4bc685f0e1b8a5a02d23ab287371364be48865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:25.097199Z","signature_b64":"Ie7wbjCK5AbVNByWaCVbJEkqkSglZeN25GFsIpats3swbUtvXOrF5IkC+8z/UQ9YpZn+NESkS2EK4RV0FtHpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef4e4d26a92be6ff3d818c6ad6b2064fe7cf3929617a45b93e7800ca2392e10","last_reissued_at":"2026-07-05T07:03:25.096733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:25.096733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Liangming Pan, Min-Yen Kan, Preslav Nakov, Qian Liu, Xinyuan Lu","submitted_at":"2023-05-22T16:13:50Z","abstract_excerpt":"Current scientific fact-checking benchmarks exhibit several shortcomings, such as biases arising from crowd-sourced claims and an over-reliance on text-based evidence. We present SCITAB, a challenging evaluation dataset consisting of 1.2K expert-verified scientific claims that 1) originate from authentic scientific publications and 2) require compositional reasoning for verification. The claims are paired with evidence-containing scientific tables annotated with labels. Through extensive evaluations, we demonstrate that SCITAB poses a significant challenge to state-of-the-art models, including"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13186","kind":"arxiv","version":3},"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/2305.13186/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":"2305.13186","created_at":"2026-07-05T07:03:25.096795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13186v3","created_at":"2026-07-05T07:03:25.096795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13186","created_at":"2026-07-05T07:03:25.096795+00:00"},{"alias_kind":"pith_short_12","alias_value":"X32OJUTKSK7G","created_at":"2026-07-05T07:03:25.096795+00:00"},{"alias_kind":"pith_short_16","alias_value":"X32OJUTKSK7G746Y","created_at":"2026-07-05T07:03:25.096795+00:00"},{"alias_kind":"pith_short_8","alias_value":"X32OJUTK","created_at":"2026-07-05T07:03:25.096795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT","json":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT.json","graph_json":"https://pith.science/api/pith-number/X32OJUTKSK7G746YDDDK22ZAMT/graph.json","events_json":"https://pith.science/api/pith-number/X32OJUTKSK7G746YDDDK22ZAMT/events.json","paper":"https://pith.science/paper/X32OJUTK"},"agent_actions":{"view_html":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT","download_json":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT.json","view_paper":"https://pith.science/paper/X32OJUTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13186&json=true","fetch_graph":"https://pith.science/api/pith-number/X32OJUTKSK7G746YDDDK22ZAMT/graph.json","fetch_events":"https://pith.science/api/pith-number/X32OJUTKSK7G746YDDDK22ZAMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT/action/storage_attestation","attest_author":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT/action/author_attestation","sign_citation":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT/action/citation_signature","submit_replication":"https://pith.science/pith/X32OJUTKSK7G746YDDDK22ZAMT/action/replication_record"}},"created_at":"2026-07-05T07:03:25.096795+00:00","updated_at":"2026-07-05T07:03:25.096795+00:00"}