{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EV7POAUTNYC4HPBG7S4ET2A35D","short_pith_number":"pith:EV7POAUT","schema_version":"1.0","canonical_sha256":"257ef702936e05c3bc26fcb849e81be8d8ac0a19294b4ac32a9ce66244de130a","source":{"kind":"arxiv","id":"2104.12918","version":1},"attestation_state":"computed","paper":{"title":"Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashkan Kazemi, Rada Mihalcea, Ver\\'onica P\\'erez-Rosas, Zehua Li","submitted_at":"2021-04-27T00:21:55Z","abstract_excerpt":"In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise."},"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":"2104.12918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-27T00:21:55Z","cross_cats_sorted":[],"title_canon_sha256":"31d9dcfb14514bc35b0563ff08f6f9b700fce33595bae95ffa636607cdbd2401","abstract_canon_sha256":"b866002bd746dc8239ae34800cc97ed07abbe9ac73e55743ca3c099f1a1f2d80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:04.235677Z","signature_b64":"LNDnxyuvzqBHJFbMMErpTxekZXkeoh76N+W6xfC5feGw+s2KPdghEBxoW7/OexvDNANV6uHQWN31m69DDY2aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"257ef702936e05c3bc26fcb849e81be8d8ac0a19294b4ac32a9ce66244de130a","last_reissued_at":"2026-07-05T02:35:04.235335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:04.235335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashkan Kazemi, Rada Mihalcea, Ver\\'onica P\\'erez-Rosas, Zehua Li","submitted_at":"2021-04-27T00:21:55Z","abstract_excerpt":"In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12918","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/2104.12918/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":"2104.12918","created_at":"2026-07-05T02:35:04.235391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12918v1","created_at":"2026-07-05T02:35:04.235391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12918","created_at":"2026-07-05T02:35:04.235391+00:00"},{"alias_kind":"pith_short_12","alias_value":"EV7POAUTNYC4","created_at":"2026-07-05T02:35:04.235391+00:00"},{"alias_kind":"pith_short_16","alias_value":"EV7POAUTNYC4HPBG","created_at":"2026-07-05T02:35:04.235391+00:00"},{"alias_kind":"pith_short_8","alias_value":"EV7POAUT","created_at":"2026-07-05T02:35:04.235391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15202","citing_title":"TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Style","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D","json":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D.json","graph_json":"https://pith.science/api/pith-number/EV7POAUTNYC4HPBG7S4ET2A35D/graph.json","events_json":"https://pith.science/api/pith-number/EV7POAUTNYC4HPBG7S4ET2A35D/events.json","paper":"https://pith.science/paper/EV7POAUT"},"agent_actions":{"view_html":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D","download_json":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D.json","view_paper":"https://pith.science/paper/EV7POAUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12918&json=true","fetch_graph":"https://pith.science/api/pith-number/EV7POAUTNYC4HPBG7S4ET2A35D/graph.json","fetch_events":"https://pith.science/api/pith-number/EV7POAUTNYC4HPBG7S4ET2A35D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D/action/storage_attestation","attest_author":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D/action/author_attestation","sign_citation":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D/action/citation_signature","submit_replication":"https://pith.science/pith/EV7POAUTNYC4HPBG7S4ET2A35D/action/replication_record"}},"created_at":"2026-07-05T02:35:04.235391+00:00","updated_at":"2026-07-05T02:35:04.235391+00:00"}