{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RQKUTSSD4TTQ3T33GD6CGBJ5LI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"78fc436a5e8be4ed0e358930f2160154f22323dbfee4075429090f182ad9d31d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T04:51:04Z","title_canon_sha256":"ac11998bdfe6576b53d72b2eeaaa1230aca46f034ea37830b47f0282b70b868c"},"schema_version":"1.0","source":{"id":"2305.14720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14720","created_at":"2026-07-05T06:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14720v2","created_at":"2026-07-05T06:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14720","created_at":"2026-07-05T06:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"RQKUTSSD4TTQ","created_at":"2026-07-05T06:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"RQKUTSSD4TTQ3T33","created_at":"2026-07-05T06:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"RQKUTSSD","created_at":"2026-07-05T06:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:0cc4ce1f8aa9418a1190a8617a2535c3d1a69755510f688aecc439eada1cf115","target":"graph","created_at":"2026-07-05T06:23:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.14720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encod","authors_text":"Dongxu Li, Junnan Li, Steven C.H. Hoi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T04:51:04Z","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14720","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cb6ab7b7a3397a65d7426348d06b965b823100bbd9e4fa6a8f42d655cf430cbc","target":"record","created_at":"2026-07-05T06:23:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"78fc436a5e8be4ed0e358930f2160154f22323dbfee4075429090f182ad9d31d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T04:51:04Z","title_canon_sha256":"ac11998bdfe6576b53d72b2eeaaa1230aca46f034ea37830b47f0282b70b868c"},"schema_version":"1.0","source":{"id":"2305.14720","kind":"arxiv","version":2}},"canonical_sha256":"8c1549ca43e4e70dcf7b30fc23053d5a2e5249d80cb614d2344264d0ce8d0ec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c1549ca43e4e70dcf7b30fc23053d5a2e5249d80cb614d2344264d0ce8d0ec5","first_computed_at":"2026-07-05T06:23:38.176793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:38.176793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YVZIq1tp6fsysrP3gnmGuDQaNSCtRw1+dB28HkfKoKJXM89KZ+GDH6hfJrm6Rko6D2rFFdJ7pKa1cr1nwWMBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:38.177221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb6ab7b7a3397a65d7426348d06b965b823100bbd9e4fa6a8f42d655cf430cbc","sha256:0cc4ce1f8aa9418a1190a8617a2535c3d1a69755510f688aecc439eada1cf115"],"state_sha256":"3f4eadb31d780dca8b694adf094db30484b5b5116cada3d060a45239655d5a07"}