{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G2KTOQ4M2QN3RHGJGXPFOH7MPP","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":"717de147b2bb005f8a2c4d3480629255f7565b94e4c591f9fbf550913a783e79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T16:55:49Z","title_canon_sha256":"6756e6c3b47e24d9323a358d6f6007fd79193375c2e723a825aac1bb616d0856"},"schema_version":"1.0","source":{"id":"2404.05674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05674","created_at":"2026-07-05T08:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05674v1","created_at":"2026-07-05T08:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05674","created_at":"2026-07-05T08:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"G2KTOQ4M2QN3","created_at":"2026-07-05T08:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"G2KTOQ4M2QN3RHGJ","created_at":"2026-07-05T08:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"G2KTOQ4M","created_at":"2026-07-05T08:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:2c8770919261339f5836294d5a24efdb27dfe7b6e633e6eac8bc52de17a7cc63","target":"graph","created_at":"2026-07-05T08:05:44Z","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/2404.05674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly evolve, the demand for robust image-to-image translation grows. Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text prompt information to produce valuable image features, faci","authors_text":"Ahmed Elgammal, Bingchen Liu, Kunpeng Song, Qing Yan, Xiao Yang, Yizhe Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T16:55:49Z","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05674","kind":"arxiv","version":1},"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":"sha256:8d75e47f4194dd17a8a28331500210b4aeab59a7ea123084a8568caa707b1003","target":"record","created_at":"2026-07-05T08:05:44Z","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":"717de147b2bb005f8a2c4d3480629255f7565b94e4c591f9fbf550913a783e79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T16:55:49Z","title_canon_sha256":"6756e6c3b47e24d9323a358d6f6007fd79193375c2e723a825aac1bb616d0856"},"schema_version":"1.0","source":{"id":"2404.05674","kind":"arxiv","version":1}},"canonical_sha256":"369537438cd41bb89cc935de571fec7bec4dde1dd1b34983c1258ed8c6727d94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"369537438cd41bb89cc935de571fec7bec4dde1dd1b34983c1258ed8c6727d94","first_computed_at":"2026-07-05T08:05:44.137467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:44.137467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0MKTKW1ugBAVsxM8LUcVmOaOZWEZ0yirSHhTFtSg1/Z8Bw1SkNx+mcz0zB0BRkbz2Gbx7AFDIGuq07JOErXtBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:44.138010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d75e47f4194dd17a8a28331500210b4aeab59a7ea123084a8568caa707b1003","sha256:2c8770919261339f5836294d5a24efdb27dfe7b6e633e6eac8bc52de17a7cc63"],"state_sha256":"d65cb1c0859eb3f50904d9a2618e15b47b65bfffe5588d225a967db548c1124c"}