{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DI6OAOEGOHY23QBBASEPQ77OQL","short_pith_number":"pith:DI6OAOEG","schema_version":"1.0","canonical_sha256":"1a3ce0388671f1adc0210488f87fee82d13fafb893c13db663d96a8b9458df22","source":{"kind":"arxiv","id":"2211.02816","version":1},"attestation_state":"computed","paper":{"title":"PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du, Zihui Gu","submitted_at":"2022-11-05T05:17:38Z","abstract_excerpt":"Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's opinion and affect one's actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table-based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of "},"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":"2211.02816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-05T05:17:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4831bd6712c20986fe82530cce21dca17ba92c4c2cf1d1612533225b40509e5b","abstract_canon_sha256":"321d9a0cc424e881a61ff4ff94a009cfc9fed14e6ea350f4dac77ed088d19709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:21.898743Z","signature_b64":"N5nCgJCHB7R6/G3pIq1IxBjSYsk87aPnd31H+g6nyzuZ8BcZHdIz9LoFo5d58JyX4P54l+b2tYNmGLrcFlHeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a3ce0388671f1adc0210488f87fee82d13fafb893c13db663d96a8b9458df22","last_reissued_at":"2026-07-05T05:13:21.898252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:21.898252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ju Fan, Nan Tang, Preslav Nakov, Xiaoman Zhao, Xiaoyong Du, Zihui Gu","submitted_at":"2022-11-05T05:17:38Z","abstract_excerpt":"Fact verification has attracted a lot of research attention recently, e.g., in journalism, marketing, and policymaking, as misinformation and disinformation online can sway one's opinion and affect one's actions. While fact-checking is a hard task in general, in many cases, false statements can be easily debunked based on analytics over tables with reliable information. Hence, table-based fact verification has recently emerged as an important and growing research area. Yet, progress has been limited due to the lack of datasets that can be used to pre-train language models (LMs) to be aware of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02816","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/2211.02816/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":"2211.02816","created_at":"2026-07-05T05:13:21.898325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02816v1","created_at":"2026-07-05T05:13:21.898325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02816","created_at":"2026-07-05T05:13:21.898325+00:00"},{"alias_kind":"pith_short_12","alias_value":"DI6OAOEGOHY2","created_at":"2026-07-05T05:13:21.898325+00:00"},{"alias_kind":"pith_short_16","alias_value":"DI6OAOEGOHY23QBB","created_at":"2026-07-05T05:13:21.898325+00:00"},{"alias_kind":"pith_short_8","alias_value":"DI6OAOEG","created_at":"2026-07-05T05:13:21.898325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.20208","citing_title":"Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17680","citing_title":"When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL","json":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL.json","graph_json":"https://pith.science/api/pith-number/DI6OAOEGOHY23QBBASEPQ77OQL/graph.json","events_json":"https://pith.science/api/pith-number/DI6OAOEGOHY23QBBASEPQ77OQL/events.json","paper":"https://pith.science/paper/DI6OAOEG"},"agent_actions":{"view_html":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL","download_json":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL.json","view_paper":"https://pith.science/paper/DI6OAOEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02816&json=true","fetch_graph":"https://pith.science/api/pith-number/DI6OAOEGOHY23QBBASEPQ77OQL/graph.json","fetch_events":"https://pith.science/api/pith-number/DI6OAOEGOHY23QBBASEPQ77OQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL/action/storage_attestation","attest_author":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL/action/author_attestation","sign_citation":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL/action/citation_signature","submit_replication":"https://pith.science/pith/DI6OAOEGOHY23QBBASEPQ77OQL/action/replication_record"}},"created_at":"2026-07-05T05:13:21.898325+00:00","updated_at":"2026-07-05T05:13:21.898325+00:00"}