{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BHEHGJ5HIYTZFAOE4H3IBYWAPX","short_pith_number":"pith:BHEHGJ5H","schema_version":"1.0","canonical_sha256":"09c87327a746279281c4e1f680e2c07dcc817f878f8b71cc2179dc3c86aaf59e","source":{"kind":"arxiv","id":"2306.05119","version":1},"attestation_state":"computed","paper":{"title":"Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Jia Su, Mingqi Gao, Xiaojun Wan, Zhefeng Wang","submitted_at":"2023-06-08T11:41:39Z","abstract_excerpt":"Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough. To address this problem, we are the first to manually annotate a FEC dataset for dialogue summarization containing 4000 items and propose FERRANTI, a fine-grained evaluation framework based on reference correction that automatically evaluates the performance of FEC models on different error categories. Using this evaluation framework, we conduct sufficient ex"},"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":"2306.05119","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T11:41:39Z","cross_cats_sorted":[],"title_canon_sha256":"beb55765594d46aad6ead645eb9d7a7fb6cdae83753e0cee8e0c14d42a960630","abstract_canon_sha256":"2f8f24ba3064c9a45194b21a82e3ff31a9a528002a988a9605ce1dbcfcdfcd82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:45.905717Z","signature_b64":"v29PQgwrwuHubwTF2/ZqUxCW4VwdvW189AETkLzLXQoXR4kLsQJLtKBcVaFxIwpoMX0eBSxHzKjvWgx1tfy7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09c87327a746279281c4e1f680e2c07dcc817f878f8b71cc2179dc3c86aaf59e","last_reissued_at":"2026-07-05T06:18:45.905176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:45.905176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Jia Su, Mingqi Gao, Xiaojun Wan, Zhefeng Wang","submitted_at":"2023-06-08T11:41:39Z","abstract_excerpt":"Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies on factuality metrics is not reliable and detailed enough. To address this problem, we are the first to manually annotate a FEC dataset for dialogue summarization containing 4000 items and propose FERRANTI, a fine-grained evaluation framework based on reference correction that automatically evaluates the performance of FEC models on different error categories. Using this evaluation framework, we conduct sufficient ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05119","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/2306.05119/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":"2306.05119","created_at":"2026-07-05T06:18:45.905232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05119v1","created_at":"2026-07-05T06:18:45.905232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05119","created_at":"2026-07-05T06:18:45.905232+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHEHGJ5HIYTZ","created_at":"2026-07-05T06:18:45.905232+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHEHGJ5HIYTZFAOE","created_at":"2026-07-05T06:18:45.905232+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHEHGJ5H","created_at":"2026-07-05T06:18:45.905232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX","json":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX.json","graph_json":"https://pith.science/api/pith-number/BHEHGJ5HIYTZFAOE4H3IBYWAPX/graph.json","events_json":"https://pith.science/api/pith-number/BHEHGJ5HIYTZFAOE4H3IBYWAPX/events.json","paper":"https://pith.science/paper/BHEHGJ5H"},"agent_actions":{"view_html":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX","download_json":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX.json","view_paper":"https://pith.science/paper/BHEHGJ5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05119&json=true","fetch_graph":"https://pith.science/api/pith-number/BHEHGJ5HIYTZFAOE4H3IBYWAPX/graph.json","fetch_events":"https://pith.science/api/pith-number/BHEHGJ5HIYTZFAOE4H3IBYWAPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX/action/storage_attestation","attest_author":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX/action/author_attestation","sign_citation":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX/action/citation_signature","submit_replication":"https://pith.science/pith/BHEHGJ5HIYTZFAOE4H3IBYWAPX/action/replication_record"}},"created_at":"2026-07-05T06:18:45.905232+00:00","updated_at":"2026-07-05T06:18:45.905232+00:00"}