{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TXTJP6RJQO6UA2ZJIEC4ABUDXN","short_pith_number":"pith:TXTJP6RJ","canonical_record":{"source":{"id":"2403.16990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:52:07Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"e4d0e0f91522dd8940c00b29c128166723f4e11c7bd8a486b59b8aa7dfcb1ea6","abstract_canon_sha256":"1faf225813a8669f7261965868fe8ec012427c6f658e58a3a6ba9579a91726a8"},"schema_version":"1.0"},"canonical_sha256":"9de697fa2983bd406b294105c00683bb4246d93e3ed51781d622c0a24c11d574","source":{"kind":"arxiv","id":"2403.16990","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16990","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16990v1","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16990","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"TXTJP6RJQO6U","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"TXTJP6RJQO6UA2ZJ","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"TXTJP6RJ","created_at":"2026-07-05T08:00:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TXTJP6RJQO6UA2ZJIEC4ABUDXN","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:52:07Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"e4d0e0f91522dd8940c00b29c128166723f4e11c7bd8a486b59b8aa7dfcb1ea6","abstract_canon_sha256":"1faf225813a8669f7261965868fe8ec012427c6f658e58a3a6ba9579a91726a8"},"schema_version":"1.0"},"canonical_sha256":"9de697fa2983bd406b294105c00683bb4246d93e3ed51781d622c0a24c11d574","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:23.418874Z","signature_b64":"cT+ajUysiuNtPTaKfXKkny/j4mz2XliKK3/8X1mhQqch/KUCnaZGStkf0sA+9YZWPv0FoINuY8xvbLeFzEkRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9de697fa2983bd406b294105c00683bb4246d93e3ed51781d622c0a24c11d574","last_reissued_at":"2026-07-05T08:00:23.418406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:23.418406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16990","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqxKmjXELq8i916GIjitiUpIv7WJuInhd28d1rdN0/l8NsuuGL0Z2IBYbBOdb087P/TEZPAEF6FnEsAJBMAnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:39:41.408791Z"},"content_sha256":"56234a12e3155b97050f7afce143fada46d62b3d7a05694616fddd766b87b8dd","schema_version":"1.0","event_id":"sha256:56234a12e3155b97050f7afce143fada46d62b3d7a05694616fddd766b87b8dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TXTJP6RJQO6UA2ZJIEC4ABUDXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel Cohen-Or, Kfir Aberman, Omer Dahary, Or Patashnik","submitted_at":"2024-03-25T17:52:07Z","abstract_excerpt":"Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images. However, they often struggle to faithfully capture the intended semantics of complex input prompts that include multiple subjects. Recently, numerous layout-to-image extensions have been introduced to improve user control, aiming to localize subjects represented by specific tokens. Yet, these methods often produce semantically inaccurate images, especially when dealing with multiple semantically or visually similar subjects. In this work, we study and analyze the causes of these limitation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16990","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/2403.16990/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":"2026-07-05T08:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9x00XUABeDWjyZG9BCee1IMVbHiLlcto/oYpbscgNgePwLkKCDHfD1LTS/ypDw0o2s+x1xjcT/kvPrDajHuuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:39:41.409278Z"},"content_sha256":"93b9e8cc822c5fb9c0d9d190092ebe55257ffd5f377dfafb7757bf2d2a9e4cb5","schema_version":"1.0","event_id":"sha256:93b9e8cc822c5fb9c0d9d190092ebe55257ffd5f377dfafb7757bf2d2a9e4cb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/bundle.json","state_url":"https://pith.science/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/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":"2026-08-04T12:39:41Z","links":{"resolver":"https://pith.science/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN","bundle":"https://pith.science/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/bundle.json","state":"https://pith.science/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TXTJP6RJQO6UA2ZJIEC4ABUDXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TXTJP6RJQO6UA2ZJIEC4ABUDXN","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":"1faf225813a8669f7261965868fe8ec012427c6f658e58a3a6ba9579a91726a8","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:52:07Z","title_canon_sha256":"e4d0e0f91522dd8940c00b29c128166723f4e11c7bd8a486b59b8aa7dfcb1ea6"},"schema_version":"1.0","source":{"id":"2403.16990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16990","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16990v1","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16990","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"TXTJP6RJQO6U","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"TXTJP6RJQO6UA2ZJ","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"TXTJP6RJ","created_at":"2026-07-05T08:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:93b9e8cc822c5fb9c0d9d190092ebe55257ffd5f377dfafb7757bf2d2a9e4cb5","target":"graph","created_at":"2026-07-05T08:00:23Z","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/2403.16990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image diffusion models have an unprecedented ability to generate diverse and high-quality images. However, they often struggle to faithfully capture the intended semantics of complex input prompts that include multiple subjects. Recently, numerous layout-to-image extensions have been introduced to improve user control, aiming to localize subjects represented by specific tokens. Yet, these methods often produce semantically inaccurate images, especially when dealing with multiple semantically or visually similar subjects. In this work, we study and analyze the causes of these limitation","authors_text":"Daniel Cohen-Or, Kfir Aberman, Omer Dahary, Or Patashnik","cross_cats":["cs.AI","cs.GR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:52:07Z","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16990","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":"sha256:56234a12e3155b97050f7afce143fada46d62b3d7a05694616fddd766b87b8dd","target":"record","created_at":"2026-07-05T08:00:23Z","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":"1faf225813a8669f7261965868fe8ec012427c6f658e58a3a6ba9579a91726a8","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:52:07Z","title_canon_sha256":"e4d0e0f91522dd8940c00b29c128166723f4e11c7bd8a486b59b8aa7dfcb1ea6"},"schema_version":"1.0","source":{"id":"2403.16990","kind":"arxiv","version":1}},"canonical_sha256":"9de697fa2983bd406b294105c00683bb4246d93e3ed51781d622c0a24c11d574","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9de697fa2983bd406b294105c00683bb4246d93e3ed51781d622c0a24c11d574","first_computed_at":"2026-07-05T08:00:23.418406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:23.418406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cT+ajUysiuNtPTaKfXKkny/j4mz2XliKK3/8X1mhQqch/KUCnaZGStkf0sA+9YZWPv0FoINuY8xvbLeFzEkRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:23.418874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56234a12e3155b97050f7afce143fada46d62b3d7a05694616fddd766b87b8dd","sha256:93b9e8cc822c5fb9c0d9d190092ebe55257ffd5f377dfafb7757bf2d2a9e4cb5"],"state_sha256":"585f0c693c6b983426d2f933fe892edd40525d04d35e0088ec26009c44b69e7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YVYQJvT4MFUYyVir0SUidJoJeH8F5/ui4TvZwd/M80FO/o20Pqp91UlM4wkOTLCyq2slgcZxncLjxqzNO51kAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:39:41.413587Z","bundle_sha256":"7279b404359cb80d8e7fc0fd22179ca63cac7b48e97dc891d10609ae896fb35a"}}