{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2YCQSZRS4OWPOXH4G76VHYNTS2","short_pith_number":"pith:2YCQSZRS","schema_version":"1.0","canonical_sha256":"d605096632e3acf75cfc37fd53e1b3969e56c288f2b412743792d0feb62c3f99","source":{"kind":"arxiv","id":"2509.08803","version":1},"attestation_state":"computed","paper":{"title":"Scaling Truth: The Confidence Paradox in AI Fact-Checking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.SI","authors_text":"Abdul H. Azeemi, Abdullah Ghani, Agha A. Raza, Asher Javaid, Ayesha Ali, Ihsan A. Qazi, Muhammad Abdullah Sohail, Wassay Sajjad, Zafar A. Qazi, Zohaib Khan","submitted_at":"2025-09-10T17:36:25Z","abstract_excerpt":"The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet their effectiveness across global contexts remains uncertain. We systematically evaluate nine established LLMs across multiple categories (open/closed-source, multiple sizes, diverse architectures, reasoning-based) using 5,000 claims previously assessed by 174 professional fact-checking organizations across 47 languages. Our methodology tests model generalizability on claims postdating training cutoffs and four prompti"},"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":"2509.08803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SI","submitted_at":"2025-09-10T17:36:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"4767b10a28445e0874c12d3f53746d0915eb8e4a21c19dc7aed324acf02ab3ee","abstract_canon_sha256":"0a76d01d25ad5545826e6b0e8413d16fbd124992baeec4e4b7055670af1673fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:36.581813Z","signature_b64":"p2fTzgtnkvXi6mMb51xx5HVlUypKtIAkEPsVYb+gurgXa0whWgc5Gge94Z/Be4Tk906MabwxYIh7bFPGnNFSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d605096632e3acf75cfc37fd53e1b3969e56c288f2b412743792d0feb62c3f99","last_reissued_at":"2026-07-05T12:08:36.581402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:36.581402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Truth: The Confidence Paradox in AI Fact-Checking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.SI","authors_text":"Abdul H. Azeemi, Abdullah Ghani, Agha A. Raza, Asher Javaid, Ayesha Ali, Ihsan A. Qazi, Muhammad Abdullah Sohail, Wassay Sajjad, Zafar A. Qazi, Zohaib Khan","submitted_at":"2025-09-10T17:36:25Z","abstract_excerpt":"The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet their effectiveness across global contexts remains uncertain. We systematically evaluate nine established LLMs across multiple categories (open/closed-source, multiple sizes, diverse architectures, reasoning-based) using 5,000 claims previously assessed by 174 professional fact-checking organizations across 47 languages. Our methodology tests model generalizability on claims postdating training cutoffs and four prompti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08803","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/2509.08803/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":"2509.08803","created_at":"2026-07-05T12:08:36.581459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08803v1","created_at":"2026-07-05T12:08:36.581459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08803","created_at":"2026-07-05T12:08:36.581459+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YCQSZRS4OWP","created_at":"2026-07-05T12:08:36.581459+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YCQSZRS4OWPOXH4","created_at":"2026-07-05T12:08:36.581459+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YCQSZRS","created_at":"2026-07-05T12:08:36.581459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2","json":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2.json","graph_json":"https://pith.science/api/pith-number/2YCQSZRS4OWPOXH4G76VHYNTS2/graph.json","events_json":"https://pith.science/api/pith-number/2YCQSZRS4OWPOXH4G76VHYNTS2/events.json","paper":"https://pith.science/paper/2YCQSZRS"},"agent_actions":{"view_html":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2","download_json":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2.json","view_paper":"https://pith.science/paper/2YCQSZRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08803&json=true","fetch_graph":"https://pith.science/api/pith-number/2YCQSZRS4OWPOXH4G76VHYNTS2/graph.json","fetch_events":"https://pith.science/api/pith-number/2YCQSZRS4OWPOXH4G76VHYNTS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2/action/storage_attestation","attest_author":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2/action/author_attestation","sign_citation":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2/action/citation_signature","submit_replication":"https://pith.science/pith/2YCQSZRS4OWPOXH4G76VHYNTS2/action/replication_record"}},"created_at":"2026-07-05T12:08:36.581459+00:00","updated_at":"2026-07-05T12:08:36.581459+00:00"}