{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P2XVV2UD3CMVVSPUDJBW25AUKI","short_pith_number":"pith:P2XVV2UD","schema_version":"1.0","canonical_sha256":"7eaf5aea83d8995ac9f41a436d74145219f04478d190842e92cbe8ba38124aac","source":{"kind":"arxiv","id":"2207.13744","version":2},"attestation_state":"computed","paper":{"title":"Lighting (In)consistency of Paint by Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Hany Farid","submitted_at":"2022-07-27T18:48:36Z","abstract_excerpt":"Whereas generative adversarial networks are capable of synthesizing highly realistic images of faces, cats, landscapes, or almost any other single category, paint-by-text synthesis engines can -- from a single text prompt -- synthesize realistic images of seemingly endless categories with arbitrary configurations and combinations. This powerful technology poses new challenges to the photo-forensic community. Motivated by the fact that paint by text is not based on explicit geometric or physical models, and the human visual system's general insensitivity to lighting inconsistencies, we provide "},"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":"2207.13744","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-27T18:48:36Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"5a72870acdc3c3c1d55426815bedd0e072d1e2dc143e2d9d452fab0bfb574308","abstract_canon_sha256":"9a49c3d523a10f2fbe806c8060dff70ee5014bf47f87fc5b9b4ef6535cae4c84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:46.533413Z","signature_b64":"CmUHgU2nAIFXRIsaK2qIWaLf9Vr2xF9Hmbc9xEXaYbKoE6LbGQ0w8VVKQrwTc4b75bj+bzQ0hQIiTJQWtcmQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eaf5aea83d8995ac9f41a436d74145219f04478d190842e92cbe8ba38124aac","last_reissued_at":"2026-07-05T04:44:46.532923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:46.532923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lighting (In)consistency of Paint by Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Hany Farid","submitted_at":"2022-07-27T18:48:36Z","abstract_excerpt":"Whereas generative adversarial networks are capable of synthesizing highly realistic images of faces, cats, landscapes, or almost any other single category, paint-by-text synthesis engines can -- from a single text prompt -- synthesize realistic images of seemingly endless categories with arbitrary configurations and combinations. This powerful technology poses new challenges to the photo-forensic community. Motivated by the fact that paint by text is not based on explicit geometric or physical models, and the human visual system's general insensitivity to lighting inconsistencies, we provide "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13744","kind":"arxiv","version":2},"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/2207.13744/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":"2207.13744","created_at":"2026-07-05T04:44:46.532980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13744v2","created_at":"2026-07-05T04:44:46.532980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13744","created_at":"2026-07-05T04:44:46.532980+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2XVV2UD3CMV","created_at":"2026-07-05T04:44:46.532980+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2XVV2UD3CMVVSPU","created_at":"2026-07-05T04:44:46.532980+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2XVV2UD","created_at":"2026-07-05T04:44:46.532980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20707","citing_title":"GEOPHYS: The Geometry of Physical Plausibility","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02224","citing_title":"Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27590","citing_title":"Fake3DGS: A Benchmark for 3D Manipulation Detection in Neural Rendering","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI","json":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI.json","graph_json":"https://pith.science/api/pith-number/P2XVV2UD3CMVVSPUDJBW25AUKI/graph.json","events_json":"https://pith.science/api/pith-number/P2XVV2UD3CMVVSPUDJBW25AUKI/events.json","paper":"https://pith.science/paper/P2XVV2UD"},"agent_actions":{"view_html":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI","download_json":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI.json","view_paper":"https://pith.science/paper/P2XVV2UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13744&json=true","fetch_graph":"https://pith.science/api/pith-number/P2XVV2UD3CMVVSPUDJBW25AUKI/graph.json","fetch_events":"https://pith.science/api/pith-number/P2XVV2UD3CMVVSPUDJBW25AUKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI/action/storage_attestation","attest_author":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI/action/author_attestation","sign_citation":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI/action/citation_signature","submit_replication":"https://pith.science/pith/P2XVV2UD3CMVVSPUDJBW25AUKI/action/replication_record"}},"created_at":"2026-07-05T04:44:46.532980+00:00","updated_at":"2026-07-05T04:44:46.532980+00:00"}