{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FOTCWRCHWAGBCZYWSPC2QS5PHT","short_pith_number":"pith:FOTCWRCH","schema_version":"1.0","canonical_sha256":"2ba62b4447b00c11671693c5a84baf3cc7bbde752fa98609ec429e94db12ee2b","source":{"kind":"arxiv","id":"2104.05893","version":2},"attestation_state":"computed","paper":{"title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Grace Luo, Trevor Darrell","submitted_at":"2021-04-13T01:53:26Z","abstract_excerpt":"Online misinformation is a prevalent societal issue, with adversaries relying on tools ranging from cheap fakes to sophisticated deep fakes. We are motivated by the threat scenario where an image is used out of context to support a certain narrative. While some prior datasets for detecting image-text inconsistency generate samples via text manipulation, we propose a dataset where both image and text are unmanipulated but mismatched. We introduce several strategies for automatically retrieving convincing images for a given caption, capturing cases with inconsistent entities or semantic context."},"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":"2104.05893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-13T01:53:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"af23fcfcef3c1783dd1275f7a98c5aa8c721c59cbdaec5d5b9d7bf867ef3b41f","abstract_canon_sha256":"2fb42af175d2dd4fad91aa4835c24456410fd0f43e8a83703af85b81ebc34d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:31.982953Z","signature_b64":"zXKhtVwtNCUU7KNgd8TNWDBMO7HB5JRinhoXqSs137NKfp2T6yyzhgN98HwN3NmtZYiw+ExZVudUa3MZtnHXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ba62b4447b00c11671693c5a84baf3cc7bbde752fa98609ec429e94db12ee2b","last_reissued_at":"2026-07-05T03:16:31.982525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:31.982525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Grace Luo, Trevor Darrell","submitted_at":"2021-04-13T01:53:26Z","abstract_excerpt":"Online misinformation is a prevalent societal issue, with adversaries relying on tools ranging from cheap fakes to sophisticated deep fakes. We are motivated by the threat scenario where an image is used out of context to support a certain narrative. While some prior datasets for detecting image-text inconsistency generate samples via text manipulation, we propose a dataset where both image and text are unmanipulated but mismatched. We introduce several strategies for automatically retrieving convincing images for a given caption, capturing cases with inconsistent entities or semantic context."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05893","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/2104.05893/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":"2104.05893","created_at":"2026-07-05T03:16:31.982581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05893v2","created_at":"2026-07-05T03:16:31.982581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05893","created_at":"2026-07-05T03:16:31.982581+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOTCWRCHWAGB","created_at":"2026-07-05T03:16:31.982581+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOTCWRCHWAGBCZYW","created_at":"2026-07-05T03:16:31.982581+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOTCWRCH","created_at":"2026-07-05T03:16:31.982581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24627","citing_title":"The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10166","citing_title":"Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22453","citing_title":"XNote: Benchmarking Automated Community Notes Generation for Image-based Contextual Deception","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22933","citing_title":"RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2104.08718","citing_title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10357","citing_title":"RW-Post: Auditable Evidence-Grounded Multimodal Fact-Checking in the Wild","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT","json":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT.json","graph_json":"https://pith.science/api/pith-number/FOTCWRCHWAGBCZYWSPC2QS5PHT/graph.json","events_json":"https://pith.science/api/pith-number/FOTCWRCHWAGBCZYWSPC2QS5PHT/events.json","paper":"https://pith.science/paper/FOTCWRCH"},"agent_actions":{"view_html":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT","download_json":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT.json","view_paper":"https://pith.science/paper/FOTCWRCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05893&json=true","fetch_graph":"https://pith.science/api/pith-number/FOTCWRCHWAGBCZYWSPC2QS5PHT/graph.json","fetch_events":"https://pith.science/api/pith-number/FOTCWRCHWAGBCZYWSPC2QS5PHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT/action/storage_attestation","attest_author":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT/action/author_attestation","sign_citation":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT/action/citation_signature","submit_replication":"https://pith.science/pith/FOTCWRCHWAGBCZYWSPC2QS5PHT/action/replication_record"}},"created_at":"2026-07-05T03:16:31.982581+00:00","updated_at":"2026-07-05T03:16:31.982581+00:00"}