{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F4SMRCGGGFNPUJSP2RBVD4CXIT","short_pith_number":"pith:F4SMRCGG","canonical_record":{"source":{"id":"2305.10431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"5023855f30c1aeed7f44e9124d990d4517cd08c6f7ec2672a701b2597e354b3a","abstract_canon_sha256":"b5924f33318f7e965c9535d201257efb1f8f354d373b1b36889e306c4f5f9740"},"schema_version":"1.0"},"canonical_sha256":"2f24c888c6315afa264fd44351f05744c9f5d06236550d09b78191879e6fec19","source":{"kind":"arxiv","id":"2305.10431","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10431","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10431v2","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10431","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"F4SMRCGGGFNP","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"F4SMRCGGGFNPUJSP","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"F4SMRCGG","created_at":"2026-07-05T06:12:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F4SMRCGGGFNPUJSP2RBVD4CXIT","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"5023855f30c1aeed7f44e9124d990d4517cd08c6f7ec2672a701b2597e354b3a","abstract_canon_sha256":"b5924f33318f7e965c9535d201257efb1f8f354d373b1b36889e306c4f5f9740"},"schema_version":"1.0"},"canonical_sha256":"2f24c888c6315afa264fd44351f05744c9f5d06236550d09b78191879e6fec19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:03.344292Z","signature_b64":"CrxMNdwtBbXFO1tg1YeNgVzWxOkevRHoDwLGLoiwZVL1f7m1LRNybiVnDzgSBgm/djxUcuSGFqgrVnrtuNxFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f24c888c6315afa264fd44351f05744c9f5d06236550d09b78191879e6fec19","last_reissued_at":"2026-07-05T06:12:03.343920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:03.343920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10431","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rWAJwWOe4R5+iN0XAihpmgf0vMPWFgoXo4lGu9yvle6gSxlHgp5qOZCUweyEPuZ8LchV9FR08Ty71x/mwR6GBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:49:12.855613Z"},"content_sha256":"17466a7a7cc76df5942b86d2d48a99cb2ebc6f9a97e969a92b5ed8cde7e69d5b","schema_version":"1.0","event_id":"sha256:17466a7a7cc76df5942b86d2d48a99cb2ebc6f9a97e969a92b5ed8cde7e69d5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F4SMRCGGGFNPUJSP2RBVD4CXIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fr\\'edo Durand, Guangxuan Xiao, Song Han, Tianwei Yin, William T. Freeman","submitted_at":"2023-05-17T17:59:55Z","abstract_excerpt":"Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend features among subjects. We present FastComposer which enables efficient, personalized, multi-subject text-to-image generation without fine-tuning. FastComposer uses subject embeddings extracted by an image encoder to augment the generic text co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10431","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/2305.10431/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eueAso7Y1QnFhOK3KNyFElgHQ3Frz19Fi7CL0kXj1j/WkSxDv/bB5COnbzdOiFf6NZU897AEayL8/MWAJXA8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:49:12.856053Z"},"content_sha256":"860d88ec06c7118d46c83cdff4accc4a7334a5b116ee3763736b97099c095ac0","schema_version":"1.0","event_id":"sha256:860d88ec06c7118d46c83cdff4accc4a7334a5b116ee3763736b97099c095ac0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/bundle.json","state_url":"https://pith.science/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T21:49:12Z","links":{"resolver":"https://pith.science/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT","bundle":"https://pith.science/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/bundle.json","state":"https://pith.science/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4SMRCGGGFNPUJSP2RBVD4CXIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F4SMRCGGGFNPUJSP2RBVD4CXIT","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":"b5924f33318f7e965c9535d201257efb1f8f354d373b1b36889e306c4f5f9740","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:59:55Z","title_canon_sha256":"5023855f30c1aeed7f44e9124d990d4517cd08c6f7ec2672a701b2597e354b3a"},"schema_version":"1.0","source":{"id":"2305.10431","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10431","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10431v2","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10431","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_12","alias_value":"F4SMRCGGGFNP","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_16","alias_value":"F4SMRCGGGFNPUJSP","created_at":"2026-07-05T06:12:03Z"},{"alias_kind":"pith_short_8","alias_value":"F4SMRCGG","created_at":"2026-07-05T06:12:03Z"}],"graph_snapshots":[{"event_id":"sha256:860d88ec06c7118d46c83cdff4accc4a7334a5b116ee3763736b97099c095ac0","target":"graph","created_at":"2026-07-05T06:12:03Z","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/2305.10431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend features among subjects. We present FastComposer which enables efficient, personalized, multi-subject text-to-image generation without fine-tuning. FastComposer uses subject embeddings extracted by an image encoder to augment the generic text co","authors_text":"Fr\\'edo Durand, Guangxuan Xiao, Song Han, Tianwei Yin, William T. Freeman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:59:55Z","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10431","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":"sha256:17466a7a7cc76df5942b86d2d48a99cb2ebc6f9a97e969a92b5ed8cde7e69d5b","target":"record","created_at":"2026-07-05T06:12:03Z","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":"b5924f33318f7e965c9535d201257efb1f8f354d373b1b36889e306c4f5f9740","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-17T17:59:55Z","title_canon_sha256":"5023855f30c1aeed7f44e9124d990d4517cd08c6f7ec2672a701b2597e354b3a"},"schema_version":"1.0","source":{"id":"2305.10431","kind":"arxiv","version":2}},"canonical_sha256":"2f24c888c6315afa264fd44351f05744c9f5d06236550d09b78191879e6fec19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f24c888c6315afa264fd44351f05744c9f5d06236550d09b78191879e6fec19","first_computed_at":"2026-07-05T06:12:03.343920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:03.343920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrxMNdwtBbXFO1tg1YeNgVzWxOkevRHoDwLGLoiwZVL1f7m1LRNybiVnDzgSBgm/djxUcuSGFqgrVnrtuNxFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:03.344292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10431","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17466a7a7cc76df5942b86d2d48a99cb2ebc6f9a97e969a92b5ed8cde7e69d5b","sha256:860d88ec06c7118d46c83cdff4accc4a7334a5b116ee3763736b97099c095ac0"],"state_sha256":"f8624f700b6a287213692a60e8bbce39da97ab5ff71b8a6e6cf1d87bfd5f20c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqDe8xC7sEISrRDvdN8NNJiT59pDzsUzMl45wnLYUP34JxydsEBUh+RLeppHPBCHUpISZKpiXSifc2wqUugBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T21:49:12.858213Z","bundle_sha256":"d41c94eaca7c0812dc6c0a48885d2a16a990a2579132cf16c971ec27de64393b"}}