{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OAT5G7WXSSLCU2KGJNZAQ6QE62","short_pith_number":"pith:OAT5G7WX","schema_version":"1.0","canonical_sha256":"7027d37ed794962a69464b72087a04f69ad15ef35d2bb94b249fd3005c6ca0f7","source":{"kind":"arxiv","id":"2410.09949","version":2},"attestation_state":"computed","paper":{"title":"MisinfoEval: Generative AI in the Era of \"Alternative Facts\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asu Ozdaglar, Jacob Andreas, James Siderius, Liang Lyu, Marzyeh Ghassemi, Saadia Gabriel","submitted_at":"2024-10-13T18:16:50Z","abstract_excerpt":"The spread of misinformation on social media platforms threatens democratic processes, contributes to massive economic losses, and endangers public health. Many efforts to address misinformation focus on a knowledge deficit model and propose interventions for improving users' critical thinking through access to facts. Such efforts are often hampered by challenges with scalability, and by platform users' personal biases. The emergence of generative AI presents promising opportunities for countering misinformation at scale across ideological barriers.\n  In this paper, we introduce a framework (M"},"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":"2410.09949","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-13T18:16:50Z","cross_cats_sorted":[],"title_canon_sha256":"c47d1ac62070421b76126e8b11ee795e9537c64fc3cb2f40fb855f4e3bda69dc","abstract_canon_sha256":"3f51ffaedf835e5d2af4f5ba629ae59ad496145affb428a4b66a2fc9cb71116a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:25.272802Z","signature_b64":"58jPbt6ZrDgC8IdVdUN/GGrq4GGEmWtAWw6pZdftcNvRj/OxSYeW/rEKUGjiJ/sToHFuQiCYaBP+pKc7VBUIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7027d37ed794962a69464b72087a04f69ad15ef35d2bb94b249fd3005c6ca0f7","last_reissued_at":"2026-07-05T09:20:25.272345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:25.272345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MisinfoEval: Generative AI in the Era of \"Alternative Facts\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asu Ozdaglar, Jacob Andreas, James Siderius, Liang Lyu, Marzyeh Ghassemi, Saadia Gabriel","submitted_at":"2024-10-13T18:16:50Z","abstract_excerpt":"The spread of misinformation on social media platforms threatens democratic processes, contributes to massive economic losses, and endangers public health. Many efforts to address misinformation focus on a knowledge deficit model and propose interventions for improving users' critical thinking through access to facts. Such efforts are often hampered by challenges with scalability, and by platform users' personal biases. The emergence of generative AI presents promising opportunities for countering misinformation at scale across ideological barriers.\n  In this paper, we introduce a framework (M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09949","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/2410.09949/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":"2410.09949","created_at":"2026-07-05T09:20:25.272401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09949v2","created_at":"2026-07-05T09:20:25.272401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09949","created_at":"2026-07-05T09:20:25.272401+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAT5G7WXSSLC","created_at":"2026-07-05T09:20:25.272401+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAT5G7WXSSLCU2KG","created_at":"2026-07-05T09:20:25.272401+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAT5G7WX","created_at":"2026-07-05T09:20:25.272401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.12993","citing_title":"Tailored untruths: How personalisation challenges LLM safeguards","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62","json":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62.json","graph_json":"https://pith.science/api/pith-number/OAT5G7WXSSLCU2KGJNZAQ6QE62/graph.json","events_json":"https://pith.science/api/pith-number/OAT5G7WXSSLCU2KGJNZAQ6QE62/events.json","paper":"https://pith.science/paper/OAT5G7WX"},"agent_actions":{"view_html":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62","download_json":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62.json","view_paper":"https://pith.science/paper/OAT5G7WX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09949&json=true","fetch_graph":"https://pith.science/api/pith-number/OAT5G7WXSSLCU2KGJNZAQ6QE62/graph.json","fetch_events":"https://pith.science/api/pith-number/OAT5G7WXSSLCU2KGJNZAQ6QE62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62/action/storage_attestation","attest_author":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62/action/author_attestation","sign_citation":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62/action/citation_signature","submit_replication":"https://pith.science/pith/OAT5G7WXSSLCU2KGJNZAQ6QE62/action/replication_record"}},"created_at":"2026-07-05T09:20:25.272401+00:00","updated_at":"2026-07-05T09:20:25.272401+00:00"}