{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AMZY7XPHDNGQIVMCYY5BRXAX2T","short_pith_number":"pith:AMZY7XPH","canonical_record":{"source":{"id":"2410.04932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T11:26:13Z","cross_cats_sorted":[],"title_canon_sha256":"a9e916708d3058b1c1efad6ec1b6bc4f700171575dd581b786caa1c3be0a4a22","abstract_canon_sha256":"0c7e4c2e3dda384cf2e15c8c948085dae54ee8566c4d69e8924fc6e3e1f5e0ca"},"schema_version":"1.0"},"canonical_sha256":"03338fdde71b4d045582c63a18dc17d4d2a42c3552e273fc77c2fa6d1e59e427","source":{"kind":"arxiv","id":"2410.04932","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04932","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04932v1","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04932","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"AMZY7XPHDNGQ","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"AMZY7XPHDNGQIVMC","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"AMZY7XPH","created_at":"2026-07-05T09:16:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AMZY7XPHDNGQIVMCYY5BRXAX2T","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T11:26:13Z","cross_cats_sorted":[],"title_canon_sha256":"a9e916708d3058b1c1efad6ec1b6bc4f700171575dd581b786caa1c3be0a4a22","abstract_canon_sha256":"0c7e4c2e3dda384cf2e15c8c948085dae54ee8566c4d69e8924fc6e3e1f5e0ca"},"schema_version":"1.0"},"canonical_sha256":"03338fdde71b4d045582c63a18dc17d4d2a42c3552e273fc77c2fa6d1e59e427","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:58.879112Z","signature_b64":"ECZQPl54OYetXqn5o6Fy8eNlkBBA2gv72P/FN50edOcTDC4hLGdW6v7b1qXHWLSYJP+XSBfHlWNOMBtoD7BaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03338fdde71b4d045582c63a18dc17d4d2a42c3552e273fc77c2fa6d1e59e427","last_reissued_at":"2026-07-05T09:16:58.878643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:58.878643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04932","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":"2026-07-05T09:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tmeqlpxeTEVmZLMDsAzuXv6Fzfff7pcM8fPVpQ7k/JpOjNTVOlMWLzrKdI1EDqEMRUEEzKXG50aorpzlzMUeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T20:10:10.650926Z"},"content_sha256":"cc7bcc8997014e5e74dfe474ecd591193910809147c83ca85ac795b6c05f81b2","schema_version":"1.0","event_id":"sha256:cc7bcc8997014e5e74dfe474ecd591193910809147c83ca85ac795b6c05f81b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AMZY7XPHDNGQIVMCYY5BRXAX2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingbing Liu, Jing He, Kaiqiang Zhou, Leheng Li, Qing Lian, Weichao Qiu, Xu Yan, Ying-Cong Chen, Yingjie Cai","submitted_at":"2024-10-07T11:26:13Z","abstract_excerpt":"We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be described through text prompts or image references. Given a set of user-defined masks and associated text or image guidance, our objective is to generate an image, where multiple objects are positioned at specified coordinates and their attributes are precisely aligned with the corresponding guidance. This approach significantly expands the scope of text-to-image generation, and elevates it to a more versatile and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04932","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/2410.04932/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":"2026-07-05T09:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcS0zKuRPe6YdFPihd7IbkGUlU73BRB0Ffdo8mI8Ah01sJSFOvHNMErn71sPHiJF6mYkXpEEflvL3I0PqXVICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T20:10:10.651362Z"},"content_sha256":"ce4a9a1f1fb9f5d461c0c33c755fec0441e549b330cb28a1d46f96f1ac59c319","schema_version":"1.0","event_id":"sha256:ce4a9a1f1fb9f5d461c0c33c755fec0441e549b330cb28a1d46f96f1ac59c319"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/bundle.json","state_url":"https://pith.science/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/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":"2026-07-12T20:10:10Z","links":{"resolver":"https://pith.science/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T","bundle":"https://pith.science/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/bundle.json","state":"https://pith.science/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMZY7XPHDNGQIVMCYY5BRXAX2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AMZY7XPHDNGQIVMCYY5BRXAX2T","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":"0c7e4c2e3dda384cf2e15c8c948085dae54ee8566c4d69e8924fc6e3e1f5e0ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T11:26:13Z","title_canon_sha256":"a9e916708d3058b1c1efad6ec1b6bc4f700171575dd581b786caa1c3be0a4a22"},"schema_version":"1.0","source":{"id":"2410.04932","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04932","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04932v1","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04932","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"AMZY7XPHDNGQ","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"AMZY7XPHDNGQIVMC","created_at":"2026-07-05T09:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"AMZY7XPH","created_at":"2026-07-05T09:16:58Z"}],"graph_snapshots":[{"event_id":"sha256:ce4a9a1f1fb9f5d461c0c33c755fec0441e549b330cb28a1d46f96f1ac59c319","target":"graph","created_at":"2026-07-05T09:16:58Z","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/2410.04932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be described through text prompts or image references. Given a set of user-defined masks and associated text or image guidance, our objective is to generate an image, where multiple objects are positioned at specified coordinates and their attributes are precisely aligned with the corresponding guidance. This approach significantly expands the scope of text-to-image generation, and elevates it to a more versatile and p","authors_text":"Bingbing Liu, Jing He, Kaiqiang Zhou, Leheng Li, Qing Lian, Weichao Qiu, Xu Yan, Ying-Cong Chen, Yingjie Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T11:26:13Z","title":"OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04932","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:cc7bcc8997014e5e74dfe474ecd591193910809147c83ca85ac795b6c05f81b2","target":"record","created_at":"2026-07-05T09:16:58Z","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":"0c7e4c2e3dda384cf2e15c8c948085dae54ee8566c4d69e8924fc6e3e1f5e0ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T11:26:13Z","title_canon_sha256":"a9e916708d3058b1c1efad6ec1b6bc4f700171575dd581b786caa1c3be0a4a22"},"schema_version":"1.0","source":{"id":"2410.04932","kind":"arxiv","version":1}},"canonical_sha256":"03338fdde71b4d045582c63a18dc17d4d2a42c3552e273fc77c2fa6d1e59e427","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03338fdde71b4d045582c63a18dc17d4d2a42c3552e273fc77c2fa6d1e59e427","first_computed_at":"2026-07-05T09:16:58.878643Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:58.878643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ECZQPl54OYetXqn5o6Fy8eNlkBBA2gv72P/FN50edOcTDC4hLGdW6v7b1qXHWLSYJP+XSBfHlWNOMBtoD7BaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:58.879112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04932","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc7bcc8997014e5e74dfe474ecd591193910809147c83ca85ac795b6c05f81b2","sha256:ce4a9a1f1fb9f5d461c0c33c755fec0441e549b330cb28a1d46f96f1ac59c319"],"state_sha256":"f1207602f3c75f5ba9201c44a0b9fbb2feca584f2e5e1c286ec786d088da3f04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9CobGZvBN9YCLcznfQmk4fRSAz1fn5QVEsJtYFq2/vo5qn1+OGaBh3pfTobCr1byUpFKLiOhWCRpRyynlKWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T20:10:10.655275Z","bundle_sha256":"b80273f2b79e915450ab7f47936952904b78125425f02522060622841ae9f362"}}