{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V2CQPE253XRRDEAPKHBOSSJVP2","short_pith_number":"pith:V2CQPE25","schema_version":"1.0","canonical_sha256":"ae8507935ddde311900f51c2e949357e8bde3e5329d10c702e722a3662f27b5a","source":{"kind":"arxiv","id":"2507.03671","version":1},"attestation_state":"computed","paper":{"title":"Recon, Answer, Verify: Agents in Search of Truth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Himanshu Dutta, Pushpak Bhattacharyya, Satyam Shukla","submitted_at":"2025-07-04T15:44:28Z","abstract_excerpt":"Automated fact checking with large language models (LLMs) offers a scalable alternative to manual verification. Evaluating fact checking is challenging as existing benchmark datasets often include post claim analysis and annotator cues, which are absent in real world scenarios where claims are fact checked immediately after being made. This limits the realism of current evaluations. We present Politi Fact Only (PFO), a 5 class benchmark dataset of 2,982 political claims from politifact.com, where all post claim analysis and annotator cues have been removed manually. This ensures that models ar"},"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":"2507.03671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:44:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2dfc9d07d59bb6d64a43500561a972d8d8c99ca3561ac79fc683e1118e7bc76d","abstract_canon_sha256":"a98d0d4b5ae1f898cc7ec806c26e61ad594ca31a22f0c6d35ad2a7cb02fe5506"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:03.492484Z","signature_b64":"pHkvLoLNDZW/Hs01GtL7+lCHG+7lJ2mkvh+qerzb7gIwv+zTYECYRlR7rbgAlc7jAnG3ZQbO8y/PbDJ6baJdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8507935ddde311900f51c2e949357e8bde3e5329d10c702e722a3662f27b5a","last_reissued_at":"2026-07-05T11:32:03.491953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:03.491953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recon, Answer, Verify: Agents in Search of Truth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Himanshu Dutta, Pushpak Bhattacharyya, Satyam Shukla","submitted_at":"2025-07-04T15:44:28Z","abstract_excerpt":"Automated fact checking with large language models (LLMs) offers a scalable alternative to manual verification. Evaluating fact checking is challenging as existing benchmark datasets often include post claim analysis and annotator cues, which are absent in real world scenarios where claims are fact checked immediately after being made. This limits the realism of current evaluations. We present Politi Fact Only (PFO), a 5 class benchmark dataset of 2,982 political claims from politifact.com, where all post claim analysis and annotator cues have been removed manually. This ensures that models ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03671","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/2507.03671/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":"2507.03671","created_at":"2026-07-05T11:32:03.492013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03671v1","created_at":"2026-07-05T11:32:03.492013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03671","created_at":"2026-07-05T11:32:03.492013+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2CQPE253XRR","created_at":"2026-07-05T11:32:03.492013+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2CQPE253XRRDEAP","created_at":"2026-07-05T11:32:03.492013+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2CQPE25","created_at":"2026-07-05T11:32:03.492013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20233","citing_title":"REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2","json":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2.json","graph_json":"https://pith.science/api/pith-number/V2CQPE253XRRDEAPKHBOSSJVP2/graph.json","events_json":"https://pith.science/api/pith-number/V2CQPE253XRRDEAPKHBOSSJVP2/events.json","paper":"https://pith.science/paper/V2CQPE25"},"agent_actions":{"view_html":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2","download_json":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2.json","view_paper":"https://pith.science/paper/V2CQPE25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03671&json=true","fetch_graph":"https://pith.science/api/pith-number/V2CQPE253XRRDEAPKHBOSSJVP2/graph.json","fetch_events":"https://pith.science/api/pith-number/V2CQPE253XRRDEAPKHBOSSJVP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2/action/storage_attestation","attest_author":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2/action/author_attestation","sign_citation":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2/action/citation_signature","submit_replication":"https://pith.science/pith/V2CQPE253XRRDEAPKHBOSSJVP2/action/replication_record"}},"created_at":"2026-07-05T11:32:03.492013+00:00","updated_at":"2026-07-05T11:32:03.492013+00:00"}