{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IO6VZLNNQY6KDUUC3Z3V6I2WFQ","short_pith_number":"pith:IO6VZLNN","schema_version":"1.0","canonical_sha256":"43bd5cadad863ca1d282de775f23562c1346bb2172e894136d059fb26ea44259","source":{"kind":"arxiv","id":"2506.04583","version":1},"attestation_state":"computed","paper":{"title":"SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chen Zhao, Hongjun Liu, Yilun Zhao","submitted_at":"2025-06-05T02:58:15Z","abstract_excerpt":"Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial claims, which are intentionally designed by humans to challenge fact-checking systems. To address these challenges, we propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence. Our modular framework, SUCEA, decomposes the task into three steps: 1) Claim Segmentation and Decontextualization that seg"},"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":"2506.04583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T02:58:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c802a99f49aefe50f2626ea53d8fd2ab886a20af142f586cba15a17edf1f119","abstract_canon_sha256":"1bf58eebe2dbdb65688c6e91b7de1b2ca054a5d01efa117637569c45b09dc787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:17.202107Z","signature_b64":"HGloqXzzqPqyc2653amx9dOPNNfsEpq9IeRuqsyhxH54jT1X8UXpa/wL8alwiDNBY7KZeHWAaOFjR/h0R5G/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43bd5cadad863ca1d282de775f23562c1346bb2172e894136d059fb26ea44259","last_reissued_at":"2026-07-05T11:16:17.201580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:17.201580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chen Zhao, Hongjun Liu, Yilun Zhao","submitted_at":"2025-06-05T02:58:15Z","abstract_excerpt":"Automatic fact-checking has recently received more attention as a means of combating misinformation. Despite significant advancements, fact-checking systems based on retrieval-augmented language models still struggle to tackle adversarial claims, which are intentionally designed by humans to challenge fact-checking systems. To address these challenges, we propose a training-free method designed to rephrase the original claim, making it easier to locate supporting evidence. Our modular framework, SUCEA, decomposes the task into three steps: 1) Claim Segmentation and Decontextualization that seg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04583","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/2506.04583/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":"2506.04583","created_at":"2026-07-05T11:16:17.201638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04583v1","created_at":"2026-07-05T11:16:17.201638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04583","created_at":"2026-07-05T11:16:17.201638+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO6VZLNNQY6K","created_at":"2026-07-05T11:16:17.201638+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO6VZLNNQY6KDUUC","created_at":"2026-07-05T11:16:17.201638+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO6VZLNN","created_at":"2026-07-05T11:16:17.201638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ","json":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ.json","graph_json":"https://pith.science/api/pith-number/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/graph.json","events_json":"https://pith.science/api/pith-number/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/events.json","paper":"https://pith.science/paper/IO6VZLNN"},"agent_actions":{"view_html":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ","download_json":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ.json","view_paper":"https://pith.science/paper/IO6VZLNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04583&json=true","fetch_graph":"https://pith.science/api/pith-number/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/action/storage_attestation","attest_author":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/action/author_attestation","sign_citation":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/action/citation_signature","submit_replication":"https://pith.science/pith/IO6VZLNNQY6KDUUC3Z3V6I2WFQ/action/replication_record"}},"created_at":"2026-07-05T11:16:17.201638+00:00","updated_at":"2026-07-05T11:16:17.201638+00:00"}