{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5AVEQOF6AAAPEIXMSEOVK5IVPY","short_pith_number":"pith:5AVEQOF6","schema_version":"1.0","canonical_sha256":"e82a4838be0000f222ec911d5575157e3b11c9a2d0890ed7a4a8c786609445fc","source":{"kind":"arxiv","id":"2504.11686","version":1},"attestation_state":"computed","paper":{"title":"Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Yang, Yiran He, Yun Cao, Zeyu Zhang","submitted_at":"2025-04-16T01:02:46Z","abstract_excerpt":"The rapid development of generative AI facilitates content creation and makes image manipulation easier and more difficult to detect. While multimodal Large Language Models (LLMs) have encoded rich world knowledge, they are not inherently tailored for combating AI-generated Content (AIGC) and struggle to comprehend local forgery details. In this work, we investigate the application of multimodal LLMs in forgery detection. We propose a framework capable of evaluating image authenticity, localizing tampered regions, providing evidence, and tracing generation methods based on semantic tampering c"},"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":"2504.11686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T01:02:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc3049a44072e51448a9837a9beb23410e1efb941df7c578ee01b7035e8196c7","abstract_canon_sha256":"432cee523eba3b4781fd03ddd9ab40924f2eef67ba3922cb078c1427953ab098"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:55.524056Z","signature_b64":"zpDkIU3Le0mBQ2WJByYwrb+DeMWFk4sX+YX2yP1Qs2CUfrsFepgVDeLaRCr1jcqadOeAramiuxQs//zKTGMlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82a4838be0000f222ec911d5575157e3b11c9a2d0890ed7a4a8c786609445fc","last_reissued_at":"2026-07-05T10:49:55.523574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:55.523574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bowen Yang, Yiran He, Yun Cao, Zeyu Zhang","submitted_at":"2025-04-16T01:02:46Z","abstract_excerpt":"The rapid development of generative AI facilitates content creation and makes image manipulation easier and more difficult to detect. While multimodal Large Language Models (LLMs) have encoded rich world knowledge, they are not inherently tailored for combating AI-generated Content (AIGC) and struggle to comprehend local forgery details. In this work, we investigate the application of multimodal LLMs in forgery detection. We propose a framework capable of evaluating image authenticity, localizing tampered regions, providing evidence, and tracing generation methods based on semantic tampering c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11686","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/2504.11686/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":"2504.11686","created_at":"2026-07-05T10:49:55.523625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11686v1","created_at":"2026-07-05T10:49:55.523625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11686","created_at":"2026-07-05T10:49:55.523625+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AVEQOF6AAAP","created_at":"2026-07-05T10:49:55.523625+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AVEQOF6AAAPEIXM","created_at":"2026-07-05T10:49:55.523625+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AVEQOF6","created_at":"2026-07-05T10:49:55.523625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY","json":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY.json","graph_json":"https://pith.science/api/pith-number/5AVEQOF6AAAPEIXMSEOVK5IVPY/graph.json","events_json":"https://pith.science/api/pith-number/5AVEQOF6AAAPEIXMSEOVK5IVPY/events.json","paper":"https://pith.science/paper/5AVEQOF6"},"agent_actions":{"view_html":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY","download_json":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY.json","view_paper":"https://pith.science/paper/5AVEQOF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11686&json=true","fetch_graph":"https://pith.science/api/pith-number/5AVEQOF6AAAPEIXMSEOVK5IVPY/graph.json","fetch_events":"https://pith.science/api/pith-number/5AVEQOF6AAAPEIXMSEOVK5IVPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY/action/storage_attestation","attest_author":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY/action/author_attestation","sign_citation":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY/action/citation_signature","submit_replication":"https://pith.science/pith/5AVEQOF6AAAPEIXMSEOVK5IVPY/action/replication_record"}},"created_at":"2026-07-05T10:49:55.523625+00:00","updated_at":"2026-07-05T10:49:55.523625+00:00"}