{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIQ5W7G52O7DHKFQSOCVSCYGII","short_pith_number":"pith:JIQ5W7G5","schema_version":"1.0","canonical_sha256":"4a21db7cddd3be33a8b09385590b0642383d371dacc68d23cd8cb68e398fb55f","source":{"kind":"arxiv","id":"2502.06185","version":1},"attestation_state":"computed","paper":{"title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diane Litman, Yang Zhong","submitted_at":"2025-02-10T06:30:15Z","abstract_excerpt":"Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows im"},"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":"2502.06185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T06:30:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33c010c119044a4562dc0a88c6588471be3f47904a439eb028f7df9e19fc76a0","abstract_canon_sha256":"018bafda0e962d17cd74ca19f9bfee01cce6adc35ff58d9b0920ecb42509ff00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:48.800985Z","signature_b64":"wgKjLPCfjgtBwBWfaXbBse1aPj6dq5jLXWJZm6BRmk6j5A50JugeUAgJz5pRTiXuVXeSg2MN1LLDX0JtNMbQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a21db7cddd3be33a8b09385590b0642383d371dacc68d23cd8cb68e398fb55f","last_reissued_at":"2026-07-05T10:11:48.800555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:48.800555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Diane Litman, Yang Zhong","submitted_at":"2025-02-10T06:30:15Z","abstract_excerpt":"Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06185","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/2502.06185/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":"2502.06185","created_at":"2026-07-05T10:11:48.800620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06185v1","created_at":"2026-07-05T10:11:48.800620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06185","created_at":"2026-07-05T10:11:48.800620+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIQ5W7G52O7D","created_at":"2026-07-05T10:11:48.800620+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIQ5W7G52O7DHKFQ","created_at":"2026-07-05T10:11:48.800620+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIQ5W7G5","created_at":"2026-07-05T10:11:48.800620+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/JIQ5W7G52O7DHKFQSOCVSCYGII","json":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII.json","graph_json":"https://pith.science/api/pith-number/JIQ5W7G52O7DHKFQSOCVSCYGII/graph.json","events_json":"https://pith.science/api/pith-number/JIQ5W7G52O7DHKFQSOCVSCYGII/events.json","paper":"https://pith.science/paper/JIQ5W7G5"},"agent_actions":{"view_html":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII","download_json":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII.json","view_paper":"https://pith.science/paper/JIQ5W7G5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06185&json=true","fetch_graph":"https://pith.science/api/pith-number/JIQ5W7G52O7DHKFQSOCVSCYGII/graph.json","fetch_events":"https://pith.science/api/pith-number/JIQ5W7G52O7DHKFQSOCVSCYGII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII/action/storage_attestation","attest_author":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII/action/author_attestation","sign_citation":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII/action/citation_signature","submit_replication":"https://pith.science/pith/JIQ5W7G52O7DHKFQSOCVSCYGII/action/replication_record"}},"created_at":"2026-07-05T10:11:48.800620+00:00","updated_at":"2026-07-05T10:11:48.800620+00:00"}