{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DPDQK7E4ZW725F2OZWEDTTJVUA","short_pith_number":"pith:DPDQK7E4","schema_version":"1.0","canonical_sha256":"1bc7057c9ccdbfae974ecd8839cd35a026cd195e35a1325e6143b28cfd063f3c","source":{"kind":"arxiv","id":"2409.00009","version":2},"attestation_state":"computed","paper":{"title":"Web Retrieval Agents for Evidence-Based Misinformation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Hao Yu, Jacob-Junqi Tian, Jean-Francois Godbout, Kellin Pelrine, Mauricio Rivera, Mayank Goel, Reihaneh Rabbany, Tyler Vergho, Yury Orlovskiy, Zachary Yang","submitted_at":"2024-08-15T15:13:16Z","abstract_excerpt":"This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent yields better results than when each tool is used independently. Our approach is robust across multiple models, outperforming alternatives and increasing the macro F1 of misinformation detection by as much as 20 percent compared to LLMs without search. We also conduct extensive analyses on the sources our system leverages and their biases, decisions in the co"},"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":"2409.00009","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-15T15:13:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53a84f0644121df7fb25b840a1bd4134a23af559722490ca27637a3d94954b44","abstract_canon_sha256":"9d5e2a35be2e19f2b31ff3540a66090d08528888f9aa23128da91ec73b1c8ea1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:29.632632Z","signature_b64":"NTlMC6Kdzf2yZXmWo3Srpk0aJ2ETnDTxfx4LlvB7JbcsrD9ZGaN/2ykbGZ4RE0LMBXNtyMkAdiYemo6c5gFGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bc7057c9ccdbfae974ecd8839cd35a026cd195e35a1325e6143b28cfd063f3c","last_reissued_at":"2026-07-05T09:18:29.632143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:29.632143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Web Retrieval Agents for Evidence-Based Misinformation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Hao Yu, Jacob-Junqi Tian, Jean-Francois Godbout, Kellin Pelrine, Mauricio Rivera, Mayank Goel, Reihaneh Rabbany, Tyler Vergho, Yury Orlovskiy, Zachary Yang","submitted_at":"2024-08-15T15:13:16Z","abstract_excerpt":"This paper develops an agent-based automated fact-checking approach for detecting misinformation. We demonstrate that combining a powerful LLM agent, which does not have access to the internet for searches, with an online web search agent yields better results than when each tool is used independently. Our approach is robust across multiple models, outperforming alternatives and increasing the macro F1 of misinformation detection by as much as 20 percent compared to LLMs without search. We also conduct extensive analyses on the sources our system leverages and their biases, decisions in the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00009","kind":"arxiv","version":2},"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/2409.00009/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":"2409.00009","created_at":"2026-07-05T09:18:29.632197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00009v2","created_at":"2026-07-05T09:18:29.632197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00009","created_at":"2026-07-05T09:18:29.632197+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPDQK7E4ZW72","created_at":"2026-07-05T09:18:29.632197+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPDQK7E4ZW725F2O","created_at":"2026-07-05T09:18:29.632197+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPDQK7E4","created_at":"2026-07-05T09:18:29.632197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18285","citing_title":"RELIANCE: Curating and Evaluating Reproductive Health Information on Social Media","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23452","citing_title":"CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08583","citing_title":"Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA","json":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA.json","graph_json":"https://pith.science/api/pith-number/DPDQK7E4ZW725F2OZWEDTTJVUA/graph.json","events_json":"https://pith.science/api/pith-number/DPDQK7E4ZW725F2OZWEDTTJVUA/events.json","paper":"https://pith.science/paper/DPDQK7E4"},"agent_actions":{"view_html":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA","download_json":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA.json","view_paper":"https://pith.science/paper/DPDQK7E4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00009&json=true","fetch_graph":"https://pith.science/api/pith-number/DPDQK7E4ZW725F2OZWEDTTJVUA/graph.json","fetch_events":"https://pith.science/api/pith-number/DPDQK7E4ZW725F2OZWEDTTJVUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA/action/storage_attestation","attest_author":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA/action/author_attestation","sign_citation":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA/action/citation_signature","submit_replication":"https://pith.science/pith/DPDQK7E4ZW725F2OZWEDTTJVUA/action/replication_record"}},"created_at":"2026-07-05T09:18:29.632197+00:00","updated_at":"2026-07-05T09:18:29.632197+00:00"}