{"as_of":"2026-08-11T03:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1a3cab6ca9d32a79bb0335bf029f6b9b61fb7c502c8a7312201a86f5501bfc2e","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:55:14.528553Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2501.14728/citation-record","integrity":"/paper/2501.14728/integrity","json":"/paper/2501.14728/citation-record.json","paper":"/paper/2501.14728"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.364155Z","title":"Fact-Saboteurs: A taxonomy of evidence manipula- tion attacks against fact-verification systems","venue":null,"work_id":"a3fd22fa-1d9f-4610-8fa0-071c45e8fd89","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.317128Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:bd62beb39997576ff0110610bd0d95b0a72c2857c2545f721e93899527653ca5","observation_id":"4c042525-e697-4bf3-a688-7f498be4a594","resolution":{"observed_at":"2026-08-10T14:55:15.369758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.281677Z","title":"FACTIFY3M: A benchmark for multimodal fact verification with explain- ability through 5W question-answering","venue":null,"work_id":"f5736fc5-84f5-4864-b4ac-13043ab3dd2f","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.352062Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:43796ab4cede840e55952f7dbd25cf58ab775545de72962010d5389cbf12a542","observation_id":"145677a3-5d2c-4157-a8fc-f3f73a27aa03","resolution":{"observed_at":"2026-08-10T14:55:15.287764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.262563Z","title":"Can llm- generated misinformation be detected? In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024,","venue":null,"work_id":"39e25bc1-a386-4c1f-a6a0-b117759e028c","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.356830Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:2c59bdd0775850131e94b191b0bcee39e245e961f0f7d40eda5cd2595d5dca7b","observation_id":"5b4caed2-85f7-45a8-954c-e5fdf6677e7e","resolution":{"observed_at":"2026-08-10T14:55:15.269717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.228458Z","title":"Synthetic disinformation attacks on au- tomated fact verification systems","venue":null,"work_id":"975963db-cbc9-4587-afa8-2709a4db939d","year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.366520Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:1b028aa541195514946984b9b9cbe4a00ebe11eaabfbd27ea3d95d6308188d27","observation_id":"91776f8b-6336-4e52-a749-294de6f49606","resolution":{"observed_at":"2026-08-10T14:55:15.233404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.211931Z","title":"A survey on automated fact-checking","venue":null,"work_id":"5486d053-1faf-4ea3-8402-6d3ea33253b8","year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.371568Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:266c9fc372f78ac89cf868188050256dede52b29968f8b9efefd48b11d54b6a8","observation_id":"9dc43579-502b-411f-844b-8f38cbd57c90","resolution":{"observed_at":"2026-08-10T14:55:15.217452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.196333Z","title":"Multimedia se- mantic integrity assessment using joint embedding of im- ages and text","venue":null,"work_id":"afab6e25-ea8c-45b2-9b0c-442aa9a76e42","year":2017},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.377042Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:b27f52da342975b006d72a0fedfd9d4ec8c1591ea39c97bcfa020425b4d6a5c8","observation_id":"41f7158e-2e86-49aa-9437-2e9aa9a96c8b","resolution":{"observed_at":"2026-08-10T14:55:15.201420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.163534Z","title":"Aligning large language models through synthetic feedback","venue":null,"work_id":"8f43f028-0074-4826-b83d-821dd20fd155","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.387571Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:4174177b5af77407351122bd3208a7f2f3f93629bcde8cfaaba4161242a57d6e","observation_id":"c78cc329-e15b-4b8a-a19f-645a4ddc8530","resolution":{"observed_at":"2026-08-10T14:55:15.168629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.03557","last_updated":"2019-08-09T17:57:13Z","snapshot_observed_at":"2026-08-07T01:39:40.489262Z","submitted_at":"2019-08-09T17:57:13Z","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.03557","snapshot_observed_at":"2026-08-10T14:55:14.393636Z","title":"VisualBERT: A simple and performant baseline for vision and language","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.393636Z"},"links":{"cited_paper":"/paper/1908.03557","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:dd287a4ed027b039137e9e26a25da99e65eb304774ae7a4d1998bb565f294a8f","observation_id":"e5ba7479-3a4b-4f7c-ab57-a4921a64ad6d","resolution":{"observed_at":"2026-08-10T14:55:14.393636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.147569Z","title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","venue":null,"work_id":"ee2cb514-7756-4eb9-9545-bcda356e5125","year":2021},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.399925Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:f4a38c7bc31e72ce2e335896590260c9b4c079e593b33d5caca3e56e74522a6c","observation_id":"cf591eff-711f-470c-b647-c0ff99432c40","resolution":{"observed_at":"2026-08-10T14:55:15.152546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.129759Z","title":"Multimodal analytics for real-world news using measures of cross-modal entity consistency","venue":null,"work_id":"84dbf57f-885f-42eb-93a6-a44226aa0cc6","year":2020},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.405752Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:3cce36464fd530289907223628b9d196bb07c8d10d0932f5781baa565bbf2043","observation_id":"8e5a1068-fe2a-4eac-8124-855fef80e046","resolution":{"observed_at":"2026-08-10T14:55:15.135783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T14:55:14.411213Z","title":"GPT-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.411213Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:a8584fea8036d9c22523c418932db4b24f93531de5f47636e04dbfdf306f2e3a","observation_id":"d65b309f-ce05-415c-a6a0-2ec47a2e4408","resolution":{"observed_at":"2026-08-10T14:55:14.411213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.111420Z","title":"Hello GPT-4o,","venue":null,"work_id":"d768395d-079f-4a53-b317-872ba8f677b9","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.416212Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:c1e598ae31b6604d5bee3dd8a09ffbc084459484f4f1a7cc103740207b3c5209","observation_id":"72d48298-1363-4d29-8df9-35d378062f1c","resolution":{"observed_at":"2026-08-10T14:55:15.116517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.095127Z","title":"[Pan et al., 2023a] Liangming Pan, Wenhu Chen, Min-Yen Kan, and William Yang Wang","venue":null,"work_id":"48d35d2e-0d1a-4ea4-a0f1-abf6a7b23bd7","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.421643Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:2317d5a9cb73758debbad7eab3815a706f19ffa9e6b3fdeeb380f0e3ce1beac8","observation_id":"d084ef61-37a0-4bab-9707-f5ef91e0ae53","resolution":{"observed_at":"2026-08-10T14:55:15.100268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.078468Z","title":"On the risk of misinformation pollution with large lan- guage models","venue":null,"work_id":"d593cd21-6860-4d55-a884-9fd6d241a63a","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.427588Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:872c626f506d6c610336f04e3cb163ac985e9a6afefbb79c64ab4b5e7731f0ff","observation_id":"f0be1cd7-4868-49ed-a873-11b1eac192cb","resolution":{"observed_at":"2026-08-10T14:55:15.083879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09939","last_updated":"2024-03-07T11:13:23Z","snapshot_observed_at":"2026-07-06T16:48:37.243305Z","submitted_at":"2023-11-16T14:43:45Z","title":"RED-DOT: Multimodal Fact-checking via Relevant Evidence Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09939","snapshot_observed_at":"2026-08-10T14:55:14.432582Z","title":"Petrantonakis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.432582Z"},"links":{"cited_paper":"/paper/2311.09939","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:023dae1000a97fad4a4e2b697f26550ff0c58ac66c4a18283a67d4f872991545","observation_id":"29cda262-fa81-441f-baea-bd56e9512eb9","resolution":{"observed_at":"2026-08-10T14:55:14.432582Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.060877Z","title":"VERITE: a robust benchmark for multimodal misinformation detection accounting for unimodal bias","venue":null,"work_id":"0661ad4b-cf27-42f2-a4e4-2067c1c94006","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.438415Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:e7c80f0b14094a6c68146994d1ed132eb52d81abbfaf229d8198683e1c7f14cc","observation_id":"5fb0ee58-a529-4c6e-bba4-f730fe9b7c8d","resolution":{"observed_at":"2026-08-10T14:55:15.066586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.042303Z","title":"SNIFFER: Multimodal large language model for explainable out-of-context misinformation de- tection","venue":null,"work_id":"12167b27-ae92-4c03-ad28-62e7121f4711","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.444627Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:156540b3cfb6710dae09b486666bef744f51cb47d59c7d7f2d43943a53b4af21","observation_id":"81d3b382-effe-460c-8895-089d6e10866d","resolution":{"observed_at":"2026-08-10T14:55:15.047711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.449694Z","title":"Learning transferable visual models from nat- ural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.449694Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:104fb7bcf535cf9ba6d83b3f65918f93ad9d77df1c1bb324b3928687828b95dd","observation_id":"77124d3a-f020-4a79-a86c-4341ac25c479","resolution":{"observed_at":"2026-08-10T14:55:14.449694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-10T14:55:14.455035Z","title":"Hierarchi- cal text-conditional image generation with CLIP latents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.455035Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:151064b82e4cb99dc74c64ff44ef746c6add83c803a64de3053d53759040a5ad","observation_id":"edd1df4b-8c6e-4127-b66f-f9be3bbe2056","resolution":{"observed_at":"2026-08-10T14:55:14.455035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.460288Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.460288Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:381347008f924775ab7c2eb3b4191fab8e2ffd56fd1c530b97a24b39b09ec862","observation_id":"e2add05c-6b31-4b78-93f4-65f4e3edb08b","resolution":{"observed_at":"2026-08-10T14:55:14.460288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.001169Z","title":"Countering misinformation via emotional response generation","venue":null,"work_id":"37586161-b57e-4a1a-9c8a-16d1f5744c4b","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.465603Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:b8e4465166f005b2c882c68c3f4ff8577c5898067a0287ceff721e2f09641dd7","observation_id":"02a6aa43-8d99-489a-ae5f-f1594a3ee846","resolution":{"observed_at":"2026-08-10T14:55:15.007488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.982835Z","title":"Deep multimodal image- repurposing detection","venue":null,"work_id":"e2ee36d2-6248-4ded-a4d3-32d794e34b4e","year":2018},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.471055Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:defb8b3d81ea12237a8462324294f3941f943dcd935e39bfc7d9a890bf35a835","observation_id":"ea6f7416-4559-4d9e-a419-d73d504b3f7c","resolution":{"observed_at":"2026-08-10T14:55:14.988168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.932248Z","title":"Position: Will we run out of data? lim- its of LLM scaling based on human-generated data","venue":null,"work_id":"c40e47b8-c0bb-4b40-a560-994534e08135","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.485685Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:7aa57820bb03514713402487587d2c260039cae3720083fe46e783e43d1aa239","observation_id":"1087a163-18e1-4695-a436-1b5ae60fd9c8","resolution":{"observed_at":"2026-08-10T14:55:14.937501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14724","last_updated":"2024-04-19T09:12:32Z","snapshot_observed_at":"2026-07-06T16:37:03.248953Z","submitted_at":"2023-10-23T09:01:13Z","title":"A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14724","snapshot_observed_at":"2026-08-10T14:55:14.490624Z","title":"Wong, and Lidia S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.490624Z"},"links":{"cited_paper":"/paper/2310.14724","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:0f4760a10b7149140ff62e7631a8bfe05f7eb1ab66652fd900a1e1b46803c5f2","observation_id":"d17b12e7-e14a-4f15-9059-52c3bb6bd39c","resolution":{"observed_at":"2026-08-10T14:55:14.490624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.913935Z","title":"Fake news in sheep’s clothing: Robust fake news detection against llm-empowered style attacks","venue":null,"work_id":"c87bbb5a-91dd-4105-a1f3-ce966e7c1462","year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.496008Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:fc8f996b2364bb955cb124cddf346c70410faea72ca33e659dc61dbea1fc6735","observation_id":"2a2398c0-3f4c-4303-88ee-e936c6d99271","resolution":{"observed_at":"2026-08-10T14:55:14.919660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.501726Z","title":"Wagner, Danqi Chen, and Prateek Mittal","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.501726Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:aec09c3840f281e3134fb4182230795f2cb6d7b74e8135ed97c042430337b1c4","observation_id":"f797db4a-0547-4a92-b78b-9322b1b06c0c","resolution":{"observed_at":"2026-08-10T14:55:14.501726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.895569Z","title":"End-to-end multimodal fact-checking and explanation generation: A challenging dataset and models","venue":null,"work_id":"7363d60c-a266-409c-8fe0-5591a0152caf","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.506770Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:5df0cd05c6c4d555e97f0db6f44e76f014757671e31ef54d25eca49893d7f7f4","observation_id":"dfae8f99-7de8-4746-ae19-be743ea6e4ac","resolution":{"observed_at":"2026-08-10T14:55:14.901208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.879196Z","title":"Don’t take this out of con- text!: On the need for contextual models and evaluations for stylistic rewriting","venue":null,"work_id":"ca0a8dfd-db6e-4040-b338-7fc14c843947","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.511985Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:a2cccaf8946b5f15a13abe91b20bb18dabb7577429133f263e8372ab5c88ea6a","observation_id":"1df87265-7a19-49e6-aabe-6615ebcadcb1","resolution":{"observed_at":"2026-08-10T14:55:14.884636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.858171Z","title":"Support or refute: Analyzing the stance of evidence to detect out-of-context mis- and disin- formation","venue":null,"work_id":"3a0965b4-1146-48a3-a104-2cbce122ca73","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.517279Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:8a52a901047312eeb715282dfcb3d311fe2150f9ba5e878dc5dffbab104b7f9d","observation_id":"56508c07-aa32-4881-ac84-3a573d83bb95","resolution":{"observed_at":"2026-08-10T14:55:14.866847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.523015Z","title":"Instruction tuning for large language models: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.523015Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:887c5ad1e6fb5462ccfff17df39fecbb5752df61eb30327507be88afeac54703","observation_id":"e2372caa-6f4a-44ce-99df-52e08a47c394","resolution":{"observed_at":"2026-08-10T14:55:14.523015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07633","last_updated":"2024-04-05T23:39:52Z","snapshot_observed_at":"2026-07-06T15:16:06.215998Z","submitted_at":"2023-04-15T21:11:55Z","title":"Interpretable Detection of Out-of-Context Misinformation with Neural-Symbolic-Enhanced Large Multimodal Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07633","snapshot_observed_at":"2026-08-10T14:55:14.528553Z","title":"Detecting out-of-context multi- modal misinformation with interpretable neural-symbolic model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.528553Z"},"links":{"cited_paper":"/paper/2304.07633","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:94aca9d848238dc52e1276716de9fc9a1742db3e59067a3996cd9793136783de","observation_id":"abed5fce-793c-4a2b-81f8-495374d4546c","resolution":{"observed_at":"2026-08-10T14:55:14.528553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.950538Z","title":"Evidence-based factual error correction","venue":null,"work_id":"10f9cd11-403a-4c62-900e-89903557b7ae","year":2021},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.480642Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:81cd63ea2f572d19334b95036b517717aa162af92686c3a3082460ad6655dec8","observation_id":"339f5757-5da8-4107-9a82-8bd5f1172f60","resolution":{"observed_at":"2026-08-10T14:55:14.956775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.180012Z","title":"Survey of hallucina- tion in natural language generation","venue":null,"work_id":"9b95bd08-b87d-4a66-b68c-dd0bc76d3ea3","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.382654Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:270a701b12584f000631ed80d38e17220c29caf644df609a83065461994aa42c","observation_id":"90163b0e-2176-4407-8686-01f2575cb874","resolution":{"observed_at":"2026-08-10T14:55:15.185055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:14.475927Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.475927Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:0d15308695eef629b56cd2ff61f39660202a25ab4935969461727a71032c781f","observation_id":"cd22ee01-8c4d-47df-89ed-940c53d6a094","resolution":{"observed_at":"2026-08-10T14:55:14.475927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.298247Z","title":"Hallucinated but factual! inspecting the factuality of hallu- cinations in abstractive summarization","venue":null,"work_id":"ca9fe39b-96a7-4f38-a84c-2fea3c0ca464","year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.346327Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:028dbdb34e8af77d0aaf8487871e34536f8920750cfe21c1bd36b0902e5e046a","observation_id":"6cad3fb0-2a4f-432c-a2af-b8372dfcfa6f","resolution":{"observed_at":"2026-08-10T14:55:15.303374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.314403Z","title":"Data scarcity, robustness and extreme multi- label classification","venue":null,"work_id":"5f19d04c-b2d7-4153-9f74-8c847f3c8d3a","year":2019},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.341133Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:d23babe2d8d1b76b7b21d7eabf26972e6fa23eae2b55ed86357531ebef5d1a5e","observation_id":"86adb648-2876-49db-961f-6d2d2d89877d","resolution":{"observed_at":"2026-08-10T14:55:15.319560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.331480Z","title":"Generating label cohesive and well-formed adversarial claims","venue":null,"work_id":"c65d8d4d-64da-48e3-9e2b-c9d236f38ff8","year":2020},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.336080Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:52da924eef88ea918c380082ea6e3fa663247deacec73545d5d3538a58dce894","observation_id":"95581d40-2c8d-489e-b580-5861b3537649","resolution":{"observed_at":"2026-08-10T14:55:15.336734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06278","last_updated":"2021-04-21T18:00:07Z","snapshot_observed_at":"2026-07-06T10:32:56.005642Z","submitted_at":"2021-01-15T19:00:42Z","title":"COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06278","snapshot_observed_at":"2026-08-10T14:55:14.328939Z","title":"Catching out-of-context misinforma- tion with self-supervised learning.CoRR, abs/2101.06278,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.328939Z"},"links":{"cited_paper":"/paper/2101.06278","citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:17546490d27b23c875f66dd2b54c3e0f63f55b19c471e4c4f0cb5208a45aae44","observation_id":"a73e95b7-0eab-4221-b026-94a463bb5f98","resolution":{"observed_at":"2026-08-10T14:55:14.328939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.347593Z","title":"Open-domain, content-based, multi- modal fact-checking of out-of-context images via online resources","venue":null,"work_id":"055b4c16-8ba0-425e-8444-765136fcd39a","year":2022},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.323232Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:4d66f823999b2e79e7efd0ff61af2f9079853335d65ae490a4d64aef0183faed","observation_id":"df05720a-f639-4343-9287-2f1d3cbde40c","resolution":{"observed_at":"2026-08-10T14:55:15.352848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:55:15.245521Z","title":null,"venue":null,"work_id":"b4497203-545a-4e33-87b7-1c2b8bb0cdf3","year":2023},"citing_paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T14:55:14.361709Z"},"links":{"citing_paper":"/paper/2501.14728"},"observation_digest":"sha256:c4ac7f5e7874f2d8a70151426746a35ccecbf4aba5764a8f2df4ff4213c1c295","observation_id":"84106558-a594-4ff4-a210-6eeec63a45a1","resolution":{"observed_at":"2026-08-10T14:55:15.251060Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.14728","last_updated":"2025-01-24T18:59:31Z","latest_version":1,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-11T02:13:34.614840Z","submitted_at":"2025-01-24T18:59:31Z","title":"Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":27},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2501.14728."}