{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OOXG5UQYCEIZFAYZMSMW5RR2IE","short_pith_number":"pith:OOXG5UQY","schema_version":"1.0","canonical_sha256":"73ae6ed218111192831964996ec63a411c730f106c5ec6819c9d5550afb848fd","source":{"kind":"arxiv","id":"1812.08247","version":1},"attestation_state":"computed","paper":{"title":"Detecting GAN-generated Imagery using Color Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Albright, Scott McCloskey","submitted_at":"2018-12-19T21:12:00Z","abstract_excerpt":"Image forensics is an increasingly relevant problem, as it can potentially address online disinformation campaigns and mitigate problematic aspects of social media. Of particular interest, given its recent successes, is the detection of imagery produced by Generative Adversarial Networks (GANs), e.g. `deepfakes'. Leveraging large training sets and extensive computing resources, recent work has shown that GANs can be trained to generate synthetic imagery which is (in some ways) indistinguishable from real imagery. We analyze the structure of the generating network of a popular GAN implementatio"},"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":"1812.08247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-19T21:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"8813c94e2b9b95fb9ad282138522e0d9a3be691b84d9ccd1dbbfbbccaf5a9b61","abstract_canon_sha256":"b73dca5f19d73af49989be0c63ca01e75443ae396f46a3a7847fb1b5ba151f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:51.827700Z","signature_b64":"7giMIaliCtcEm//NCozx1EXMx6R+SQWNGforAtpGyIbx42f3KFi+OYbc6nmrchJxaynD8RcQ/mLFKx3UrD92Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73ae6ed218111192831964996ec63a411c730f106c5ec6819c9d5550afb848fd","last_reissued_at":"2026-05-17T23:57:51.827179Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:51.827179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting GAN-generated Imagery using Color Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Albright, Scott McCloskey","submitted_at":"2018-12-19T21:12:00Z","abstract_excerpt":"Image forensics is an increasingly relevant problem, as it can potentially address online disinformation campaigns and mitigate problematic aspects of social media. Of particular interest, given its recent successes, is the detection of imagery produced by Generative Adversarial Networks (GANs), e.g. `deepfakes'. Leveraging large training sets and extensive computing resources, recent work has shown that GANs can be trained to generate synthetic imagery which is (in some ways) indistinguishable from real imagery. We analyze the structure of the generating network of a popular GAN implementatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08247","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":""},"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":"1812.08247","created_at":"2026-05-17T23:57:51.827251+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08247v1","created_at":"2026-05-17T23:57:51.827251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08247","created_at":"2026-05-17T23:57:51.827251+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOXG5UQYCEIZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOXG5UQYCEIZFAYZ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOXG5UQY","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.11200","citing_title":"Detecting AI-Generated Content on Social Media with Multi-modal Language Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00606","citing_title":"FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2509.15406","citing_title":"Causal Fingerprints of AI Generative Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08226","citing_title":"SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21904","citing_title":"UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE","json":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE.json","graph_json":"https://pith.science/api/pith-number/OOXG5UQYCEIZFAYZMSMW5RR2IE/graph.json","events_json":"https://pith.science/api/pith-number/OOXG5UQYCEIZFAYZMSMW5RR2IE/events.json","paper":"https://pith.science/paper/OOXG5UQY"},"agent_actions":{"view_html":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE","download_json":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE.json","view_paper":"https://pith.science/paper/OOXG5UQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08247&json=true","fetch_graph":"https://pith.science/api/pith-number/OOXG5UQYCEIZFAYZMSMW5RR2IE/graph.json","fetch_events":"https://pith.science/api/pith-number/OOXG5UQYCEIZFAYZMSMW5RR2IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE/action/storage_attestation","attest_author":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE/action/author_attestation","sign_citation":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE/action/citation_signature","submit_replication":"https://pith.science/pith/OOXG5UQYCEIZFAYZMSMW5RR2IE/action/replication_record"}},"created_at":"2026-05-17T23:57:51.827251+00:00","updated_at":"2026-05-17T23:57:51.827251+00:00"}