{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VCDCUNLX6ZJGUY5MYEM6G6DNFQ","short_pith_number":"pith:VCDCUNLX","schema_version":"1.0","canonical_sha256":"a8862a3577f6526a63acc119e3786d2c057c03ff56d03c6bbe1c36bbf9764588","source":{"kind":"arxiv","id":"2010.08712","version":2},"attestation_state":"computed","paper":{"title":"Factual Error Correction for Abstractive Summarization Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Jiapeng Wu, Meng Cao, Yue Dong","submitted_at":"2020-10-17T04:24:16Z","abstract_excerpt":"Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge. We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries. The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries. These tr"},"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":"2010.08712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-17T04:24:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d498401c877e665aac10fff5775072c6ea54cad8293a7b07e0febde81b5b79f","abstract_canon_sha256":"a7c0b00a3aabff5424f9e92cffc107082f34a32795c58c0e8deb8c7db13edaee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:32.788072Z","signature_b64":"6U6IiX5Pz8/5IOzrfOw1b22EjvCWFQgB7Qdr/qb92lJJmmaFfA7cg+uUYEzHxcan4ioCLP7T+qTqU83awj3LCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8862a3577f6526a63acc119e3786d2c057c03ff56d03c6bbe1c36bbf9764588","last_reissued_at":"2026-07-05T02:28:32.787621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:32.787621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factual Error Correction for Abstractive Summarization Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jackie Chi Kit Cheung, Jiapeng Wu, Meng Cao, Yue Dong","submitted_at":"2020-10-17T04:24:16Z","abstract_excerpt":"Neural abstractive summarization systems have achieved promising progress, thanks to the availability of large-scale datasets and models pre-trained with self-supervised methods. However, ensuring the factual consistency of the generated summaries for abstractive summarization systems is a challenge. We propose a post-editing corrector module to address this issue by identifying and correcting factual errors in generated summaries. The neural corrector model is pre-trained on artificial examples that are created by applying a series of heuristic transformations on reference summaries. These tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08712","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/2010.08712/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":"2010.08712","created_at":"2026-07-05T02:28:32.787681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08712v2","created_at":"2026-07-05T02:28:32.787681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08712","created_at":"2026-07-05T02:28:32.787681+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCDCUNLX6ZJG","created_at":"2026-07-05T02:28:32.787681+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCDCUNLX6ZJGUY5M","created_at":"2026-07-05T02:28:32.787681+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCDCUNLX","created_at":"2026-07-05T02:28:32.787681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15661","citing_title":"Improving Next Tokens via Second-to-Last Predictions with Generate and Refine","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ","json":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ.json","graph_json":"https://pith.science/api/pith-number/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/graph.json","events_json":"https://pith.science/api/pith-number/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/events.json","paper":"https://pith.science/paper/VCDCUNLX"},"agent_actions":{"view_html":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ","download_json":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ.json","view_paper":"https://pith.science/paper/VCDCUNLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08712&json=true","fetch_graph":"https://pith.science/api/pith-number/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/action/storage_attestation","attest_author":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/action/author_attestation","sign_citation":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/action/citation_signature","submit_replication":"https://pith.science/pith/VCDCUNLX6ZJGUY5MYEM6G6DNFQ/action/replication_record"}},"created_at":"2026-07-05T02:28:32.787681+00:00","updated_at":"2026-07-05T02:28:32.787681+00:00"}