{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4T2BYCYPE2TL6JQCFVDD6Y6UIE","short_pith_number":"pith:4T2BYCYP","schema_version":"1.0","canonical_sha256":"e4f41c0b0f26a6bf26022d463f63d44114a11e0b041e648048a3d69494c24857","source":{"kind":"arxiv","id":"2501.11273","version":1},"attestation_state":"computed","paper":{"title":"Multi-round, Chain-of-thought Post-editing for Unfaithful Summaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jessica Ouyang, Xiangci Li, Yi-Hui Lee","submitted_at":"2025-01-20T04:55:43Z","abstract_excerpt":"Recent large language models (LLMs) have demonstrated a remarkable ability to perform natural language understanding and generation tasks. In this work, we investigate the use of LLMs for evaluating faithfulness in news summarization, finding that it achieves a strong correlation with human judgments. We further investigate LLMs' capabilities as a faithfulness post-editor, experimenting with different chain-of-thought prompts for locating and correcting factual inconsistencies between a generated summary and the source news document and are able to achieve a higher editing success rate than wa"},"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":"2501.11273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T04:55:43Z","cross_cats_sorted":[],"title_canon_sha256":"14a182874b1e2aca9f04daa7c8f9332aabe0f9bfb391d12bf2409e318a51146e","abstract_canon_sha256":"d1220de655e1ab6ffef07f87343217f43e3f576df9d3ba8859cfe2c739bfcecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:06.093701Z","signature_b64":"XJ7Vjx/EktE/P6b4Flceqd7lmge+hsAEcMMJbF+Fg5/0uyUtu5zAgG/djuNmijPi81oCCflCVcbV4YmZ56WmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f41c0b0f26a6bf26022d463f63d44114a11e0b041e648048a3d69494c24857","last_reissued_at":"2026-07-05T10:03:06.093263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:06.093263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-round, Chain-of-thought Post-editing for Unfaithful Summaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jessica Ouyang, Xiangci Li, Yi-Hui Lee","submitted_at":"2025-01-20T04:55:43Z","abstract_excerpt":"Recent large language models (LLMs) have demonstrated a remarkable ability to perform natural language understanding and generation tasks. In this work, we investigate the use of LLMs for evaluating faithfulness in news summarization, finding that it achieves a strong correlation with human judgments. We further investigate LLMs' capabilities as a faithfulness post-editor, experimenting with different chain-of-thought prompts for locating and correcting factual inconsistencies between a generated summary and the source news document and are able to achieve a higher editing success rate than wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11273","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/2501.11273/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":"2501.11273","created_at":"2026-07-05T10:03:06.093324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11273v1","created_at":"2026-07-05T10:03:06.093324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11273","created_at":"2026-07-05T10:03:06.093324+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T2BYCYPE2TL","created_at":"2026-07-05T10:03:06.093324+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T2BYCYPE2TL6JQC","created_at":"2026-07-05T10:03:06.093324+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T2BYCYP","created_at":"2026-07-05T10:03:06.093324+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/4T2BYCYPE2TL6JQCFVDD6Y6UIE","json":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE.json","graph_json":"https://pith.science/api/pith-number/4T2BYCYPE2TL6JQCFVDD6Y6UIE/graph.json","events_json":"https://pith.science/api/pith-number/4T2BYCYPE2TL6JQCFVDD6Y6UIE/events.json","paper":"https://pith.science/paper/4T2BYCYP"},"agent_actions":{"view_html":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE","download_json":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE.json","view_paper":"https://pith.science/paper/4T2BYCYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11273&json=true","fetch_graph":"https://pith.science/api/pith-number/4T2BYCYPE2TL6JQCFVDD6Y6UIE/graph.json","fetch_events":"https://pith.science/api/pith-number/4T2BYCYPE2TL6JQCFVDD6Y6UIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE/action/storage_attestation","attest_author":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE/action/author_attestation","sign_citation":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE/action/citation_signature","submit_replication":"https://pith.science/pith/4T2BYCYPE2TL6JQCFVDD6Y6UIE/action/replication_record"}},"created_at":"2026-07-05T10:03:06.093324+00:00","updated_at":"2026-07-05T10:03:06.093324+00:00"}