{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MHCGHQCYXKEAFCQD3BR5KDWVS5","short_pith_number":"pith:MHCGHQCY","schema_version":"1.0","canonical_sha256":"61c463c058ba88028a03d863d50ed5974df0e11bc7db4e6c3d0309b9e1e94c4b","source":{"kind":"arxiv","id":"2112.08542","version":2},"attestation_state":"computed","paper":{"title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu, Wenhao Liu","submitted_at":"2021-12-16T00:38:35Z","abstract_excerpt":"Factual consistency is an essential quality of text summarization models in practical settings. Existing work in evaluating this dimension can be broadly categorized into two lines of research, entailment-based and question answering (QA)-based metrics, and different experimental setups often lead to contrasting conclusions as to which paradigm performs the best. In this work, we conduct an extensive comparison of entailment and QA-based metrics, demonstrating that carefully choosing the components of a QA-based metric, especially question generation and answerability classification, is critic"},"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":"2112.08542","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T00:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"47f4a7c3329035696177eb8bed020ba19daed76afd38a6d5fdccd0d0d8f0e97a","abstract_canon_sha256":"5b51d641f7d184aabdc72ca309b2742a61662897ac587251ca841fbcaa31d289"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:50.063263Z","signature_b64":"Xsg0KpEUWqdqdcxHxFym6Yzkk2De+qnX1bXGGwvPza91OxiHEU+JjCvCSLbtRY3QjFW8mZPcmjiQZRf3Jc8SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61c463c058ba88028a03d863d50ed5974df0e11bc7db4e6c3d0309b9e1e94c4b","last_reissued_at":"2026-07-05T04:18:50.062805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:50.062805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander R. Fabbri, Caiming Xiong, Chien-Sheng Wu, Wenhao Liu","submitted_at":"2021-12-16T00:38:35Z","abstract_excerpt":"Factual consistency is an essential quality of text summarization models in practical settings. Existing work in evaluating this dimension can be broadly categorized into two lines of research, entailment-based and question answering (QA)-based metrics, and different experimental setups often lead to contrasting conclusions as to which paradigm performs the best. In this work, we conduct an extensive comparison of entailment and QA-based metrics, demonstrating that carefully choosing the components of a QA-based metric, especially question generation and answerability classification, is critic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08542","kind":"arxiv","version":2},"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/2112.08542/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":"2112.08542","created_at":"2026-07-05T04:18:50.062862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08542v2","created_at":"2026-07-05T04:18:50.062862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08542","created_at":"2026-07-05T04:18:50.062862+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHCGHQCYXKEA","created_at":"2026-07-05T04:18:50.062862+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHCGHQCYXKEAFCQD","created_at":"2026-07-05T04:18:50.062862+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHCGHQCY","created_at":"2026-07-05T04:18:50.062862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05391","citing_title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25651","citing_title":"MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12807","citing_title":"Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08157","citing_title":"Cross Paraphrastic Invariance Learning for Hallucination Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25651","citing_title":"MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":166,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5","json":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5.json","graph_json":"https://pith.science/api/pith-number/MHCGHQCYXKEAFCQD3BR5KDWVS5/graph.json","events_json":"https://pith.science/api/pith-number/MHCGHQCYXKEAFCQD3BR5KDWVS5/events.json","paper":"https://pith.science/paper/MHCGHQCY"},"agent_actions":{"view_html":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5","download_json":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5.json","view_paper":"https://pith.science/paper/MHCGHQCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08542&json=true","fetch_graph":"https://pith.science/api/pith-number/MHCGHQCYXKEAFCQD3BR5KDWVS5/graph.json","fetch_events":"https://pith.science/api/pith-number/MHCGHQCYXKEAFCQD3BR5KDWVS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5/action/storage_attestation","attest_author":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5/action/author_attestation","sign_citation":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5/action/citation_signature","submit_replication":"https://pith.science/pith/MHCGHQCYXKEAFCQD3BR5KDWVS5/action/replication_record"}},"created_at":"2026-07-05T04:18:50.062862+00:00","updated_at":"2026-07-05T04:18:50.062862+00:00"}