{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KRVHZEIQNLHIA2Q2OX5F3SELOP","short_pith_number":"pith:KRVHZEIQ","schema_version":"1.0","canonical_sha256":"546a7c91106ace806a1a75fa5dc88b73ca40f358f602797278ab35d1a123da8f","source":{"kind":"arxiv","id":"2402.01123","version":2},"attestation_state":"computed","paper":{"title":"A Single Simple Patch is All You Need for AI-generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxuan Chen, Jieteng Yao, Li Niu","submitted_at":"2024-02-02T03:50:45Z","abstract_excerpt":"The recent development of generative models unleashes the potential of generating hyper-realistic fake images. To prevent the malicious usage of fake images, AI-generated image detection aims to distinguish fake images from real images. However, existing method suffer from severe performance drop when detecting images generated by unseen generators. We find that generative models tend to focus on generating the patches with rich textures to make the images more realistic while neglecting the hidden noise caused by camera capture present in simple patches. In this paper, we propose to exploit t"},"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":"2402.01123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-02T03:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"c2a83966622720cfaa735cd9fb66fdf7fdee94c57d62f161648b53909019b6df","abstract_canon_sha256":"dc58dc87bbbbd64d5a5f05bcaee597a6aa393e2e5d47a21eef44d27d4d2d2af3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:23.300914Z","signature_b64":"M/O+o2TMPFSHQk7fNdW1TzUcrzuv7S3jSw7VoNcNnJ2K5KyHIp16qaIG21BgCmuoD1St9tt1dmQDy3CwUj++Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546a7c91106ace806a1a75fa5dc88b73ca40f358f602797278ab35d1a123da8f","last_reissued_at":"2026-07-05T08:10:23.300397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:23.300397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Single Simple Patch is All You Need for AI-generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaxuan Chen, Jieteng Yao, Li Niu","submitted_at":"2024-02-02T03:50:45Z","abstract_excerpt":"The recent development of generative models unleashes the potential of generating hyper-realistic fake images. To prevent the malicious usage of fake images, AI-generated image detection aims to distinguish fake images from real images. However, existing method suffer from severe performance drop when detecting images generated by unseen generators. We find that generative models tend to focus on generating the patches with rich textures to make the images more realistic while neglecting the hidden noise caused by camera capture present in simple patches. In this paper, we propose to exploit t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01123","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/2402.01123/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":"2402.01123","created_at":"2026-07-05T08:10:23.300464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01123v2","created_at":"2026-07-05T08:10:23.300464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01123","created_at":"2026-07-05T08:10:23.300464+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRVHZEIQNLHI","created_at":"2026-07-05T08:10:23.300464+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRVHZEIQNLHIA2Q2","created_at":"2026-07-05T08:10:23.300464+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRVHZEIQ","created_at":"2026-07-05T08:10:23.300464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02224","citing_title":"Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19716","citing_title":"Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12967","citing_title":"ImageAttributionBench: How Far Are We from Generalizable Attribution?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10071","citing_title":"MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09106","citing_title":"Detecting Diffusion-generated Images via Dynamic Assembly Forests","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16879","citing_title":"Adaptive Forensic Feature Refinement via Intrinsic Importance Perception","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP","json":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP.json","graph_json":"https://pith.science/api/pith-number/KRVHZEIQNLHIA2Q2OX5F3SELOP/graph.json","events_json":"https://pith.science/api/pith-number/KRVHZEIQNLHIA2Q2OX5F3SELOP/events.json","paper":"https://pith.science/paper/KRVHZEIQ"},"agent_actions":{"view_html":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP","download_json":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP.json","view_paper":"https://pith.science/paper/KRVHZEIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01123&json=true","fetch_graph":"https://pith.science/api/pith-number/KRVHZEIQNLHIA2Q2OX5F3SELOP/graph.json","fetch_events":"https://pith.science/api/pith-number/KRVHZEIQNLHIA2Q2OX5F3SELOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP/action/storage_attestation","attest_author":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP/action/author_attestation","sign_citation":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP/action/citation_signature","submit_replication":"https://pith.science/pith/KRVHZEIQNLHIA2Q2OX5F3SELOP/action/replication_record"}},"created_at":"2026-07-05T08:10:23.300464+00:00","updated_at":"2026-07-05T08:10:23.300464+00:00"}