{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JK762Q27KBFKAYDBNR2MERTZ45","short_pith_number":"pith:JK762Q27","schema_version":"1.0","canonical_sha256":"4abfed435f504aa060616c74c24679e76885923d441ff91eee08c4b133665d4d","source":{"kind":"arxiv","id":"2106.08749","version":1},"attestation_state":"computed","paper":{"title":"Learning to Disentangle GAN Fingerprint for Fake Image Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Ji, Juan Cao, Lei Li, Qiang Sheng, Sheng Tang, Tianyun Yang, Xirong Li","submitted_at":"2021-06-16T12:50:40Z","abstract_excerpt":"Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake image attribution. Existing works on fake image attribution mainly rely on a direct classification framework. Without additional supervision, the extracted features could include many content-relevant components and generalize poorly. Meanwhile, how to obtain an interpretable GAN fingerprint to explain the decision remains an open question. Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Netw"},"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":"2106.08749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-16T12:50:40Z","cross_cats_sorted":[],"title_canon_sha256":"33a8cbd5ce409694aee662d58fbaf0659456786fe1d6689eedfe6eee393156ac","abstract_canon_sha256":"b33b80704250e086f757b105829b60106f700c26138cb24b239f9c2103230248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:01.099641Z","signature_b64":"rGw+t/KRmxlYzWr3K/Hpbbr91Jry71URtx5BLY14lvmbmwfBFm8tWNZa3UwEzL5aJrIR0xf7LGej5Ud3GQvrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4abfed435f504aa060616c74c24679e76885923d441ff91eee08c4b133665d4d","last_reissued_at":"2026-07-05T02:50:01.099276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:01.099276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Disentangle GAN Fingerprint for Fake Image Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Ji, Juan Cao, Lei Li, Qiang Sheng, Sheng Tang, Tianyun Yang, Xirong Li","submitted_at":"2021-06-16T12:50:40Z","abstract_excerpt":"Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake image attribution. Existing works on fake image attribution mainly rely on a direct classification framework. Without additional supervision, the extracted features could include many content-relevant components and generalize poorly. Meanwhile, how to obtain an interpretable GAN fingerprint to explain the decision remains an open question. Adopting a multi-task framework, we propose a GAN Fingerprint Disentangling Netw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.08749","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/2106.08749/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":"2106.08749","created_at":"2026-07-05T02:50:01.099340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.08749v1","created_at":"2026-07-05T02:50:01.099340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.08749","created_at":"2026-07-05T02:50:01.099340+00:00"},{"alias_kind":"pith_short_12","alias_value":"JK762Q27KBFK","created_at":"2026-07-05T02:50:01.099340+00:00"},{"alias_kind":"pith_short_16","alias_value":"JK762Q27KBFKAYDB","created_at":"2026-07-05T02:50:01.099340+00:00"},{"alias_kind":"pith_short_8","alias_value":"JK762Q27","created_at":"2026-07-05T02:50:01.099340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12967","citing_title":"ImageAttributionBench: How Far Are We from Generalizable Attribution?","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08847","citing_title":"DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45","json":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45.json","graph_json":"https://pith.science/api/pith-number/JK762Q27KBFKAYDBNR2MERTZ45/graph.json","events_json":"https://pith.science/api/pith-number/JK762Q27KBFKAYDBNR2MERTZ45/events.json","paper":"https://pith.science/paper/JK762Q27"},"agent_actions":{"view_html":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45","download_json":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45.json","view_paper":"https://pith.science/paper/JK762Q27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.08749&json=true","fetch_graph":"https://pith.science/api/pith-number/JK762Q27KBFKAYDBNR2MERTZ45/graph.json","fetch_events":"https://pith.science/api/pith-number/JK762Q27KBFKAYDBNR2MERTZ45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45/action/storage_attestation","attest_author":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45/action/author_attestation","sign_citation":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45/action/citation_signature","submit_replication":"https://pith.science/pith/JK762Q27KBFKAYDBNR2MERTZ45/action/replication_record"}},"created_at":"2026-07-05T02:50:01.099340+00:00","updated_at":"2026-07-05T02:50:01.099340+00:00"}