{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K47FVPCXONKXQLMUD5SWCBUOJP","short_pith_number":"pith:K47FVPCX","schema_version":"1.0","canonical_sha256":"573e5abc577355782d941f6561068e4bcfad29c47a1e6dbd9d58d2478fa46ae8","source":{"kind":"arxiv","id":"2503.08404","version":1},"attestation_state":"computed","paper":{"title":"Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Elizaveta Kuznetsova, Ilaria Vitulano, Martha Stolze, Mykola Makhortykh, Tomas Nagy, Victoria Vziatysheva","submitted_at":"2025-03-11T13:06:40Z","abstract_excerpt":"The purpose of this study is to assess how large language models (LLMs) can be used for fact-checking and contribute to the broader debate on the use of automated means for veracity identification. To achieve this purpose, we use AI auditing methodology that systematically evaluates performance of five LLMs (ChatGPT 4, Llama 3 (70B), Llama 3.1 (405B), Claude 3.5 Sonnet, and Google Gemini) using prompts regarding a large set of statements fact-checked by professional journalists (16,513). Specifically, we use topic modeling and regression analysis to investigate which factors (e.g. topic of the"},"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":"2503.08404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T13:06:40Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"4f3c626225ceb398a428779ed9642d87cfe555fb5dbfc8622601f5f02203f0fc","abstract_canon_sha256":"4e7d5f066a12fb3b1b61355cafdfdee0441fe0c93eb8892e787d62027f8ca38b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:58.868094Z","signature_b64":"dSrBYmQm52+BJeVVwd/B/2a+gYv1h7JfZbSb6YKc04XIkeHqfUoukBgzA0F+hd+ZckCml+nrEeo2YSRU31MrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573e5abc577355782d941f6561068e4bcfad29c47a1e6dbd9d58d2478fa46ae8","last_reissued_at":"2026-07-05T10:28:58.867434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:58.867434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fact-checking with Generative AI: A Systematic Cross-Topic Examination of LLMs Capacity to Detect Veracity of Political Information","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Elizaveta Kuznetsova, Ilaria Vitulano, Martha Stolze, Mykola Makhortykh, Tomas Nagy, Victoria Vziatysheva","submitted_at":"2025-03-11T13:06:40Z","abstract_excerpt":"The purpose of this study is to assess how large language models (LLMs) can be used for fact-checking and contribute to the broader debate on the use of automated means for veracity identification. To achieve this purpose, we use AI auditing methodology that systematically evaluates performance of five LLMs (ChatGPT 4, Llama 3 (70B), Llama 3.1 (405B), Claude 3.5 Sonnet, and Google Gemini) using prompts regarding a large set of statements fact-checked by professional journalists (16,513). Specifically, we use topic modeling and regression analysis to investigate which factors (e.g. topic of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08404","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/2503.08404/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":"2503.08404","created_at":"2026-07-05T10:28:58.867514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08404v1","created_at":"2026-07-05T10:28:58.867514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08404","created_at":"2026-07-05T10:28:58.867514+00:00"},{"alias_kind":"pith_short_12","alias_value":"K47FVPCXONKX","created_at":"2026-07-05T10:28:58.867514+00:00"},{"alias_kind":"pith_short_16","alias_value":"K47FVPCXONKXQLMU","created_at":"2026-07-05T10:28:58.867514+00:00"},{"alias_kind":"pith_short_8","alias_value":"K47FVPCX","created_at":"2026-07-05T10:28:58.867514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30905","citing_title":"How Human Feedback Shapes AI-generated Community Notes","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP","json":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP.json","graph_json":"https://pith.science/api/pith-number/K47FVPCXONKXQLMUD5SWCBUOJP/graph.json","events_json":"https://pith.science/api/pith-number/K47FVPCXONKXQLMUD5SWCBUOJP/events.json","paper":"https://pith.science/paper/K47FVPCX"},"agent_actions":{"view_html":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP","download_json":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP.json","view_paper":"https://pith.science/paper/K47FVPCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08404&json=true","fetch_graph":"https://pith.science/api/pith-number/K47FVPCXONKXQLMUD5SWCBUOJP/graph.json","fetch_events":"https://pith.science/api/pith-number/K47FVPCXONKXQLMUD5SWCBUOJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP/action/storage_attestation","attest_author":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP/action/author_attestation","sign_citation":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP/action/citation_signature","submit_replication":"https://pith.science/pith/K47FVPCXONKXQLMUD5SWCBUOJP/action/replication_record"}},"created_at":"2026-07-05T10:28:58.867514+00:00","updated_at":"2026-07-05T10:28:58.867514+00:00"}