{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G4ATTNW5LSHMNNDQMWG4EOSQFK","short_pith_number":"pith:G4ATTNW5","schema_version":"1.0","canonical_sha256":"370139b6dd5c8ec6b470658dc23a502aa63ce6c219119e0e13ed174f5210fcbb","source":{"kind":"arxiv","id":"2604.28177","version":2},"attestation_state":"computed","paper":{"title":"AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AEGIS benchmark reveals that even advanced models detect AI-generated academic images at only 48.80 percent overall accuracy.","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Haihong E, Haiyang Sun, Haocheng Gao, Jiacheng Liu, Junpeng Ding, Liangjia Wang, Peilin Gao, Ronghui Xi, Tzu-Yen Ma, Yiling Huang, Yizhuo Zhao, Yuan Liu, Yuanze Li, Yujie Wang, Yuyue Zhang, Zhongjun Yang, Zichen Tang, Zijie Xi, Zirui Wang, Zixin Ding","submitted_at":"2026-04-30T17:56:58Z","abstract_excerpt":"We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing intrinsic forensic difficulty, where even GPT-5.1 reaches 48.80% overall performance and expert models achieve only limited localization accuracy (IoU 30.09%); (2) Diverse Forgery Simulations: modeling four prevalent academic forgery strategies across 25 generative models, with 11 yielding average forensic accuracy b"},"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":"2604.28177","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-30T17:56:58Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"411c5c36ec103f0a9b843aac5d75953fc4368e686a18a5e5aa90cceee23ff54a","abstract_canon_sha256":"2c6db4aa71d650b7b7c3cb76ae018bed1fb5666150a8c1fd6479feb2c8502cfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:03.725341Z","signature_b64":"+fRiOt81Et2Fb9cNYiZTEB2dkRJSY7OxatKMMU6Rn0arBt3BCoVOU9JFViIJOyOfky3s5niw8Dk58h44xoQcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"370139b6dd5c8ec6b470658dc23a502aa63ce6c219119e0e13ed174f5210fcbb","last_reissued_at":"2026-05-22T01:04:03.724447Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:03.724447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AEGIS benchmark reveals that even advanced models detect AI-generated academic images at only 48.80 percent overall accuracy.","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Haihong E, Haiyang Sun, Haocheng Gao, Jiacheng Liu, Junpeng Ding, Liangjia Wang, Peilin Gao, Ronghui Xi, Tzu-Yen Ma, Yiling Huang, Yizhuo Zhao, Yuan Liu, Yuanze Li, Yujie Wang, Yuyue Zhang, Zhongjun Yang, Zichen Tang, Zijie Xi, Zirui Wang, Zixin Ding","submitted_at":"2026-04-30T17:56:58Z","abstract_excerpt":"We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic categories with 39 fine-grained subtypes, exposing intrinsic forensic difficulty, where even GPT-5.1 reaches 48.80% overall performance and expert models achieve only limited localization accuracy (IoU 30.09%); (2) Diverse Forgery Simulations: modeling four prevalent academic forgery strategies across 25 generative models, with 11 yielding average forensic accuracy b"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AEGIS serves as a diagnostic testbed exposing fundamental limitations in academic image forensics, with even GPT-5.1 reaching only 48.80% overall performance and expert models limited to 30.09% IoU localization accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 39 fine-grained academic subtypes and four simulated forgery strategies using 25 generative models sufficiently represent the real-world distribution and difficulty of AI-generated academic images.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AEGIS benchmark reveals that leading AI models achieve only 48.80% overall accuracy and low localization precision when analyzing AI-generated academic images, exposing gaps between generative and forensic capabilities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AEGIS benchmark reveals that even advanced models detect AI-generated academic images at only 48.80 percent overall accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c4eeda82f238ff179a642da188b5c32885c02ab08bbe6c527d2516d0b1454d57"},"source":{"id":"2604.28177","kind":"arxiv","version":2},"verdict":{"id":"163fd9c5-13d6-4b16-b3e1-cc0d068eb3b1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T07:30:38.284435Z","strongest_claim":"AEGIS serves as a diagnostic testbed exposing fundamental limitations in academic image forensics, with even GPT-5.1 reaching only 48.80% overall performance and expert models limited to 30.09% IoU localization accuracy.","one_line_summary":"AEGIS benchmark reveals that leading AI models achieve only 48.80% overall accuracy and low localization precision when analyzing AI-generated academic images, exposing gaps between generative and forensic capabilities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 39 fine-grained academic subtypes and four simulated forgery strategies using 25 generative models sufficiently represent the real-world distribution and difficulty of AI-generated academic images.","pith_extraction_headline":"AEGIS benchmark reveals that even advanced models detect AI-generated academic images at only 48.80 percent overall accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.28177/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:39:31.023454Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:33:07.351969Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a0c1a52141a77c30ce1e620a9dc4c3e2cbaf6e91ffa8789961570ecf4e9ba5ed"},"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":"2604.28177","created_at":"2026-05-22T01:04:03.724560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.28177v2","created_at":"2026-05-22T01:04:03.724560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.28177","created_at":"2026-05-22T01:04:03.724560+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4ATTNW5LSHM","created_at":"2026-05-22T01:04:03.724560+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4ATTNW5LSHMNNDQ","created_at":"2026-05-22T01:04:03.724560+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4ATTNW5","created_at":"2026-05-22T01:04:03.724560+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/G4ATTNW5LSHMNNDQMWG4EOSQFK","json":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK.json","graph_json":"https://pith.science/api/pith-number/G4ATTNW5LSHMNNDQMWG4EOSQFK/graph.json","events_json":"https://pith.science/api/pith-number/G4ATTNW5LSHMNNDQMWG4EOSQFK/events.json","paper":"https://pith.science/paper/G4ATTNW5"},"agent_actions":{"view_html":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK","download_json":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK.json","view_paper":"https://pith.science/paper/G4ATTNW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.28177&json=true","fetch_graph":"https://pith.science/api/pith-number/G4ATTNW5LSHMNNDQMWG4EOSQFK/graph.json","fetch_events":"https://pith.science/api/pith-number/G4ATTNW5LSHMNNDQMWG4EOSQFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK/action/storage_attestation","attest_author":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK/action/author_attestation","sign_citation":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK/action/citation_signature","submit_replication":"https://pith.science/pith/G4ATTNW5LSHMNNDQMWG4EOSQFK/action/replication_record"}},"created_at":"2026-05-22T01:04:03.724560+00:00","updated_at":"2026-05-22T01:04:03.724560+00:00"}