{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V6HS3CLR56BSFZZDLLSFKA4U6Q","short_pith_number":"pith:V6HS3CLR","schema_version":"1.0","canonical_sha256":"af8f2d8971ef8322e7235ae4550394f43505fe1e6ccf0201be6db6bfed6b9bff","source":{"kind":"arxiv","id":"2408.09153","version":1},"attestation_state":"computed","paper":{"title":"Are CLIP features all you need for Universal Synthetic Image Origin Attribution?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Tzelepis, Dario Cioni, Ioannis Patras, Lorenzo Seidenari","submitted_at":"2024-08-17T09:54:21Z","abstract_excerpt":"The steady improvement of Diffusion Models for visual synthesis has given rise to many new and interesting use cases of synthetic images but also has raised concerns about their potential abuse, which poses significant societal threats. To address this, fake images need to be detected and attributed to their source model, and given the frequent release of new generators, realistic applications need to consider an Open-Set scenario where some models are unseen at training time. Existing forensic techniques are either limited to Closed-Set settings or to GAN-generated images, relying on fragile "},"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":"2408.09153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-17T09:54:21Z","cross_cats_sorted":[],"title_canon_sha256":"b26aef287999d32446a9231685e51fcd41c06bc97cbd939d2b20c0ba5d2546ee","abstract_canon_sha256":"b56ef63f45f929393b2412ee39fc43db440327bcf2d171f56cadc9955f75a08f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:11.788416Z","signature_b64":"ZehBZBh/tEywwP5sLEho9Dm6cGlgY2N5yPslx5hKTvQUTKfkAZ+PVF/9OfenXmj4wP/li8ZJGycnRN1DXt8SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af8f2d8971ef8322e7235ae4550394f43505fe1e6ccf0201be6db6bfed6b9bff","last_reissued_at":"2026-07-05T11:13:11.787827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:11.787827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are CLIP features all you need for Universal Synthetic Image Origin Attribution?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Tzelepis, Dario Cioni, Ioannis Patras, Lorenzo Seidenari","submitted_at":"2024-08-17T09:54:21Z","abstract_excerpt":"The steady improvement of Diffusion Models for visual synthesis has given rise to many new and interesting use cases of synthetic images but also has raised concerns about their potential abuse, which poses significant societal threats. To address this, fake images need to be detected and attributed to their source model, and given the frequent release of new generators, realistic applications need to consider an Open-Set scenario where some models are unseen at training time. Existing forensic techniques are either limited to Closed-Set settings or to GAN-generated images, relying on fragile "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09153","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/2408.09153/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":"2408.09153","created_at":"2026-07-05T11:13:11.787893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09153v1","created_at":"2026-07-05T11:13:11.787893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09153","created_at":"2026-07-05T11:13:11.787893+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6HS3CLR56BS","created_at":"2026-07-05T11:13:11.787893+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6HS3CLR56BSFZZD","created_at":"2026-07-05T11:13:11.787893+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6HS3CLR","created_at":"2026-07-05T11:13:11.787893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02224","citing_title":"Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12967","citing_title":"ImageAttributionBench: How Far Are We from Generalizable Attribution?","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q","json":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q.json","graph_json":"https://pith.science/api/pith-number/V6HS3CLR56BSFZZDLLSFKA4U6Q/graph.json","events_json":"https://pith.science/api/pith-number/V6HS3CLR56BSFZZDLLSFKA4U6Q/events.json","paper":"https://pith.science/paper/V6HS3CLR"},"agent_actions":{"view_html":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q","download_json":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q.json","view_paper":"https://pith.science/paper/V6HS3CLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09153&json=true","fetch_graph":"https://pith.science/api/pith-number/V6HS3CLR56BSFZZDLLSFKA4U6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/V6HS3CLR56BSFZZDLLSFKA4U6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q/action/storage_attestation","attest_author":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q/action/author_attestation","sign_citation":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q/action/citation_signature","submit_replication":"https://pith.science/pith/V6HS3CLR56BSFZZDLLSFKA4U6Q/action/replication_record"}},"created_at":"2026-07-05T11:13:11.787893+00:00","updated_at":"2026-07-05T11:13:11.787893+00:00"}