{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3DGTQI4TOW5YOR27R6JLWADYWM","short_pith_number":"pith:3DGTQI4T","schema_version":"1.0","canonical_sha256":"d8cd38239375bb87475f8f92bb0078b308642ffe0eb21a8d39e8077178c1d5de","source":{"kind":"arxiv","id":"2503.21003","version":1},"attestation_state":"computed","paper":{"title":"Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aref Azizpour, Matthew C. Stamm, Tai D. Nguyen","submitted_at":"2025-03-26T21:34:37Z","abstract_excerpt":"The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to generalize to unseen generators due to reliance on features specific to known sources during training. To address this problem, we propose a novel approach that explicitly models forensic microstructures - subtle, pixel-level patterns unique to the image creation process. Using only real images in a self-supervised manner, we learn a set of diverse predictive fi"},"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":"2503.21003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T21:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"44c3cc1ab50fc0742bfd240d3f3113ea6fc4cc76e0829232c56e8c6dbe29cc11","abstract_canon_sha256":"8425fe2eddf32879de2dff87778a7125974dcde4be299e2f716b725ba748a631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:51.527829Z","signature_b64":"/76pF+HZC4Uo8oNRs9ilEpYlH1RMoO4lg35EPvYYpGdRJMVhSIbUOaV+BqN+uP6hsp/Okin5yaHBP6zz9/keAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8cd38239375bb87475f8f92bb0078b308642ffe0eb21a8d39e8077178c1d5de","last_reissued_at":"2026-07-05T10:39:51.527356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:51.527356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aref Azizpour, Matthew C. Stamm, Tai D. Nguyen","submitted_at":"2025-03-26T21:34:37Z","abstract_excerpt":"The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to generalize to unseen generators due to reliance on features specific to known sources during training. To address this problem, we propose a novel approach that explicitly models forensic microstructures - subtle, pixel-level patterns unique to the image creation process. Using only real images in a self-supervised manner, we learn a set of diverse predictive fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21003","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/2503.21003/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":"2503.21003","created_at":"2026-07-05T10:39:51.527407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21003v1","created_at":"2026-07-05T10:39:51.527407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21003","created_at":"2026-07-05T10:39:51.527407+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DGTQI4TOW5Y","created_at":"2026-07-05T10:39:51.527407+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DGTQI4TOW5YOR27","created_at":"2026-07-05T10:39:51.527407+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DGTQI4T","created_at":"2026-07-05T10:39:51.527407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07545","citing_title":"Face-trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM","json":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM.json","graph_json":"https://pith.science/api/pith-number/3DGTQI4TOW5YOR27R6JLWADYWM/graph.json","events_json":"https://pith.science/api/pith-number/3DGTQI4TOW5YOR27R6JLWADYWM/events.json","paper":"https://pith.science/paper/3DGTQI4T"},"agent_actions":{"view_html":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM","download_json":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM.json","view_paper":"https://pith.science/paper/3DGTQI4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21003&json=true","fetch_graph":"https://pith.science/api/pith-number/3DGTQI4TOW5YOR27R6JLWADYWM/graph.json","fetch_events":"https://pith.science/api/pith-number/3DGTQI4TOW5YOR27R6JLWADYWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM/action/storage_attestation","attest_author":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM/action/author_attestation","sign_citation":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM/action/citation_signature","submit_replication":"https://pith.science/pith/3DGTQI4TOW5YOR27R6JLWADYWM/action/replication_record"}},"created_at":"2026-07-05T10:39:51.527407+00:00","updated_at":"2026-07-05T10:39:51.527407+00:00"}