{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PCFIT7NMW5BPQ626R3Z5GGXYGV","short_pith_number":"pith:PCFIT7NM","schema_version":"1.0","canonical_sha256":"788a89fdacb742f87b5e8ef3d31af835654fa7851872998287bd59cefe0d1e97","source":{"kind":"arxiv","id":"2102.09130","version":1},"attestation_state":"computed","paper":{"title":"Entity-level Factual Consistency of Abstractive Text Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Cicero Nogueira dos Santos, Dejiao Zhang, Feng Nan, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Zhiguo Wang","submitted_at":"2021-02-18T03:07:28Z","abstract_excerpt":"A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination, generating names of entities that are not present in the source document. We propose a set of new metrics to quantify the entity-level factual consistency of generated summaries and we show that the entity hallucination problem can be alleviated by simply filtering the training data. In addition, we propose a summary-worthy entity classification task to the 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":"2102.09130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-18T03:07:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95f21d7f7a4ea0bd373aa1db46963fa6f29a763c6eae01eab2c26a8709ce8f1c","abstract_canon_sha256":"602b3e2e084ee42cf2d14d02d42b7471be4473e14ef3d665ca1f18983fc64778"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:19.771734Z","signature_b64":"ZG17fRdV8UX6w5YUB3aAiFNDzR12oAMabYgcUDKxFnRaeyBrNMjfCViHXpnZxM2Gco/7OLF8leW1FTZ4Uz26Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788a89fdacb742f87b5e8ef3d31af835654fa7851872998287bd59cefe0d1e97","last_reissued_at":"2026-07-05T02:16:19.771190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:19.771190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity-level Factual Consistency of Abstractive Text Summarization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Cicero Nogueira dos Santos, Dejiao Zhang, Feng Nan, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Zhiguo Wang","submitted_at":"2021-02-18T03:07:28Z","abstract_excerpt":"A key challenge for abstractive summarization is ensuring factual consistency of the generated summary with respect to the original document. For example, state-of-the-art models trained on existing datasets exhibit entity hallucination, generating names of entities that are not present in the source document. We propose a set of new metrics to quantify the entity-level factual consistency of generated summaries and we show that the entity hallucination problem can be alleviated by simply filtering the training data. In addition, we propose a summary-worthy entity classification task to the tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09130","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/2102.09130/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":"2102.09130","created_at":"2026-07-05T02:16:19.771249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09130v1","created_at":"2026-07-05T02:16:19.771249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09130","created_at":"2026-07-05T02:16:19.771249+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCFIT7NMW5BP","created_at":"2026-07-05T02:16:19.771249+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCFIT7NMW5BPQ626","created_at":"2026-07-05T02:16:19.771249+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCFIT7NM","created_at":"2026-07-05T02:16:19.771249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25476","citing_title":"A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25462","citing_title":"Optimizing Abstractive Summarization With Fine-Tuned PEGASUS","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12807","citing_title":"Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV","json":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV.json","graph_json":"https://pith.science/api/pith-number/PCFIT7NMW5BPQ626R3Z5GGXYGV/graph.json","events_json":"https://pith.science/api/pith-number/PCFIT7NMW5BPQ626R3Z5GGXYGV/events.json","paper":"https://pith.science/paper/PCFIT7NM"},"agent_actions":{"view_html":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV","download_json":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV.json","view_paper":"https://pith.science/paper/PCFIT7NM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09130&json=true","fetch_graph":"https://pith.science/api/pith-number/PCFIT7NMW5BPQ626R3Z5GGXYGV/graph.json","fetch_events":"https://pith.science/api/pith-number/PCFIT7NMW5BPQ626R3Z5GGXYGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV/action/storage_attestation","attest_author":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV/action/author_attestation","sign_citation":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV/action/citation_signature","submit_replication":"https://pith.science/pith/PCFIT7NMW5BPQ626R3Z5GGXYGV/action/replication_record"}},"created_at":"2026-07-05T02:16:19.771249+00:00","updated_at":"2026-07-05T02:16:19.771249+00:00"}