{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FROPLFSAYOIX6YAO25CPGG36TK","short_pith_number":"pith:FROPLFSA","schema_version":"1.0","canonical_sha256":"2c5cf59640c3917f600ed744f31b7e9aae5beefc3b757e20b8ef79ffdbe44649","source":{"kind":"arxiv","id":"1912.11035","version":2},"attestation_state":"computed","paper":{"title":"CNN-generated images are surprisingly easy to spot... for now","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Andrew Owens, Oliver Wang, Richard Zhang, Sheng-Yu Wang","submitted_at":"2019-12-23T18:58:58Z","abstract_excerpt":"In this work we ask whether it is possible to create a \"universal\" detector for telling apart real images from these generated by a CNN, regardless of architecture or dataset used. To test this, we collect a dataset consisting of fake images generated by 11 different CNN-based image generator models, chosen to span the space of commonly used architectures today (ProGAN, StyleGAN, BigGAN, CycleGAN, StarGAN, GauGAN, DeepFakes, cascaded refinement networks, implicit maximum likelihood estimation, second-order attention super-resolution, seeing-in-the-dark). We demonstrate that, with careful pre- "},"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":"1912.11035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-23T18:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"80cff78a416dbce0514445634ccd370f411376b1b6f82e358cda0369ac1d10f6","abstract_canon_sha256":"b44d82b5360655e4be160c5245c4f817093ef29667440dea858210ed79b794fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:50.044848Z","signature_b64":"ms/kOlslhKdouPPgbEcJKwors6UyD0xfIESEFnit/VUN24xiYIWo5/VV22CleyokBcEXSCl2a4WRsVv78K/pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c5cf59640c3917f600ed744f31b7e9aae5beefc3b757e20b8ef79ffdbe44649","last_reissued_at":"2026-07-05T00:52:50.044352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:50.044352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CNN-generated images are surprisingly easy to spot... for now","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Andrew Owens, Oliver Wang, Richard Zhang, Sheng-Yu Wang","submitted_at":"2019-12-23T18:58:58Z","abstract_excerpt":"In this work we ask whether it is possible to create a \"universal\" detector for telling apart real images from these generated by a CNN, regardless of architecture or dataset used. To test this, we collect a dataset consisting of fake images generated by 11 different CNN-based image generator models, chosen to span the space of commonly used architectures today (ProGAN, StyleGAN, BigGAN, CycleGAN, StarGAN, GauGAN, DeepFakes, cascaded refinement networks, implicit maximum likelihood estimation, second-order attention super-resolution, seeing-in-the-dark). We demonstrate that, with careful pre- "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11035","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/1912.11035/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":"1912.11035","created_at":"2026-07-05T00:52:50.044417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11035v2","created_at":"2026-07-05T00:52:50.044417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11035","created_at":"2026-07-05T00:52:50.044417+00:00"},{"alias_kind":"pith_short_12","alias_value":"FROPLFSAYOIX","created_at":"2026-07-05T00:52:50.044417+00:00"},{"alias_kind":"pith_short_16","alias_value":"FROPLFSAYOIX6YAO","created_at":"2026-07-05T00:52:50.044417+00:00"},{"alias_kind":"pith_short_8","alias_value":"FROPLFSA","created_at":"2026-07-05T00:52:50.044417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07916","citing_title":"The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.10236","citing_title":"Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08226","citing_title":"SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23016","citing_title":"DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK","json":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK.json","graph_json":"https://pith.science/api/pith-number/FROPLFSAYOIX6YAO25CPGG36TK/graph.json","events_json":"https://pith.science/api/pith-number/FROPLFSAYOIX6YAO25CPGG36TK/events.json","paper":"https://pith.science/paper/FROPLFSA"},"agent_actions":{"view_html":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK","download_json":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK.json","view_paper":"https://pith.science/paper/FROPLFSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11035&json=true","fetch_graph":"https://pith.science/api/pith-number/FROPLFSAYOIX6YAO25CPGG36TK/graph.json","fetch_events":"https://pith.science/api/pith-number/FROPLFSAYOIX6YAO25CPGG36TK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK/action/storage_attestation","attest_author":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK/action/author_attestation","sign_citation":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK/action/citation_signature","submit_replication":"https://pith.science/pith/FROPLFSAYOIX6YAO25CPGG36TK/action/replication_record"}},"created_at":"2026-07-05T00:52:50.044417+00:00","updated_at":"2026-07-05T00:52:50.044417+00:00"}