{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DSXFND3YAQLDDL2ME546GP33VE","short_pith_number":"pith:DSXFND3Y","schema_version":"1.0","canonical_sha256":"1cae568f78041631af4c2779e33f7ba919764b47752adc0980d33314d9c259d0","source":{"kind":"arxiv","id":"2204.04991","version":3},"attestation_state":"computed","paper":{"title":"TRUE: Re-evaluating Factual Consistency Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinatan Hassidim, Doron Kukliansy, Hagai Taitelbaum, Idan Szpektor, Jonathan Herzig, Or Honovich, Roee Aharoni, Thomas Scialom, Vered Cohen, Yossi Matias","submitted_at":"2022-04-11T10:14:35Z","abstract_excerpt":"Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability. Automatic factual consistency evaluation may help alleviate this limitation by accelerating evaluation cycles, filtering inconsistent outputs and augmenting training data. While attracting increasing attention, such evaluation metrics are usually developed and evaluated in silo for a single task or dataset, slowing their adoption. Moreover, previous meta-evaluation protocols focused on system-level correlations with human annotations, which leave the example-lev"},"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":"2204.04991","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-11T10:14:35Z","cross_cats_sorted":[],"title_canon_sha256":"1dd79ffe6a0c8df1e20ecc758bb7c77ce8abe33400ecff07fbece87d0fdb2a0d","abstract_canon_sha256":"a9dcae59a735870afa27943bede15218eccd18411edc8b11c7ed1365069c4935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:57.956570Z","signature_b64":"MO4OKcDW90dMbXwvf5UASKDTlDtiMdaFc/i0h7RWchg/HECX2GjTpg5Z7439lhu/jHgnR5Mo17+YSqKhUGABDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cae568f78041631af4c2779e33f7ba919764b47752adc0980d33314d9c259d0","last_reissued_at":"2026-07-05T04:19:57.956099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:57.956099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRUE: Re-evaluating Factual Consistency Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avinatan Hassidim, Doron Kukliansy, Hagai Taitelbaum, Idan Szpektor, Jonathan Herzig, Or Honovich, Roee Aharoni, Thomas Scialom, Vered Cohen, Yossi Matias","submitted_at":"2022-04-11T10:14:35Z","abstract_excerpt":"Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability. Automatic factual consistency evaluation may help alleviate this limitation by accelerating evaluation cycles, filtering inconsistent outputs and augmenting training data. While attracting increasing attention, such evaluation metrics are usually developed and evaluated in silo for a single task or dataset, slowing their adoption. Moreover, previous meta-evaluation protocols focused on system-level correlations with human annotations, which leave the example-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04991","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/2204.04991/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":"2204.04991","created_at":"2026-07-05T04:19:57.956152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04991v3","created_at":"2026-07-05T04:19:57.956152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04991","created_at":"2026-07-05T04:19:57.956152+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSXFND3YAQLD","created_at":"2026-07-05T04:19:57.956152+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSXFND3YAQLDDL2M","created_at":"2026-07-05T04:19:57.956152+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSXFND3Y","created_at":"2026-07-05T04:19:57.956152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11127","citing_title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02443","citing_title":"HalluScan: A Systematic Benchmark for Detecting and Mitigating Hallucinations in Instruction-Following LLMs","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24366","citing_title":"On the Factual Consistency of Text-based Explainable Recommendation Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03724","citing_title":"Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19342","citing_title":"Are Large Language Models Economically Viable for Industry Deployment?","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE","json":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE.json","graph_json":"https://pith.science/api/pith-number/DSXFND3YAQLDDL2ME546GP33VE/graph.json","events_json":"https://pith.science/api/pith-number/DSXFND3YAQLDDL2ME546GP33VE/events.json","paper":"https://pith.science/paper/DSXFND3Y"},"agent_actions":{"view_html":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE","download_json":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE.json","view_paper":"https://pith.science/paper/DSXFND3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04991&json=true","fetch_graph":"https://pith.science/api/pith-number/DSXFND3YAQLDDL2ME546GP33VE/graph.json","fetch_events":"https://pith.science/api/pith-number/DSXFND3YAQLDDL2ME546GP33VE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE/action/storage_attestation","attest_author":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE/action/author_attestation","sign_citation":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE/action/citation_signature","submit_replication":"https://pith.science/pith/DSXFND3YAQLDDL2ME546GP33VE/action/replication_record"}},"created_at":"2026-07-05T04:19:57.956152+00:00","updated_at":"2026-07-05T04:19:57.956152+00:00"}