{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y4VQ3KXETWUTWXAEGQXULKEHBQ","short_pith_number":"pith:Y4VQ3KXE","schema_version":"1.0","canonical_sha256":"c72b0daae49da93b5c04342f45a8870c10f182f5357a5fd69bc5015542d3e6c0","source":{"kind":"arxiv","id":"2605.25254","version":1},"attestation_state":"computed","paper":{"title":"Guess the Unified Model: How Much Can We Recover from Generated Images?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Addison J. Wu, Jasin Cekinmez, Ryo Mitsuhashi, Yida Yin","submitted_at":"2026-05-24T20:59:08Z","abstract_excerpt":"With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in LLM-generated text, diffusion model images, and datasets, but the separability of unified model-generated images remains an underexplored area. We address this gap by examining separability across corruption, domains, and prompt languages using images generated by seven unified models. We show that model attribution is highly feasible as our model achieves n"},"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":"2605.25254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T20:59:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db9a27ddcafb878503fa2aee36df236dc7ccdca5e806de9536e4d3b0e939102d","abstract_canon_sha256":"b38e047134d07653febf8798f022c810a64e8eeb5efac76d98a2faf87e7917ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:25.712115Z","signature_b64":"i7OR9h4lu6o0tbUWm+pogvZ5aQGegQDmL1rougVwFMV8DoXtvlz007DcW/NAoT0HXx+lcQgV/x/+vW1WPCqHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c72b0daae49da93b5c04342f45a8870c10f182f5357a5fd69bc5015542d3e6c0","last_reissued_at":"2026-05-26T02:04:25.711267Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:25.711267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guess the Unified Model: How Much Can We Recover from Generated Images?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Addison J. Wu, Jasin Cekinmez, Ryo Mitsuhashi, Yida Yin","submitted_at":"2026-05-24T20:59:08Z","abstract_excerpt":"With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in LLM-generated text, diffusion model images, and datasets, but the separability of unified model-generated images remains an underexplored area. We address this gap by examining separability across corruption, domains, and prompt languages using images generated by seven unified models. We show that model attribution is highly feasible as our model achieves n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25254","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/2605.25254/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":"2605.25254","created_at":"2026-05-26T02:04:25.711432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25254v1","created_at":"2026-05-26T02:04:25.711432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25254","created_at":"2026-05-26T02:04:25.711432+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4VQ3KXETWUT","created_at":"2026-05-26T02:04:25.711432+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4VQ3KXETWUTWXAE","created_at":"2026-05-26T02:04:25.711432+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4VQ3KXE","created_at":"2026-05-26T02:04:25.711432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ","json":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ.json","graph_json":"https://pith.science/api/pith-number/Y4VQ3KXETWUTWXAEGQXULKEHBQ/graph.json","events_json":"https://pith.science/api/pith-number/Y4VQ3KXETWUTWXAEGQXULKEHBQ/events.json","paper":"https://pith.science/paper/Y4VQ3KXE"},"agent_actions":{"view_html":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ","download_json":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ.json","view_paper":"https://pith.science/paper/Y4VQ3KXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25254&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4VQ3KXETWUTWXAEGQXULKEHBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4VQ3KXETWUTWXAEGQXULKEHBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y4VQ3KXETWUTWXAEGQXULKEHBQ/action/replication_record"}},"created_at":"2026-05-26T02:04:25.711432+00:00","updated_at":"2026-05-26T02:04:25.711432+00:00"}