{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CL4ZFNY7OCQT2Z3PMRPOST6RLR","short_pith_number":"pith:CL4ZFNY7","canonical_record":{"source":{"id":"2401.13388","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T11:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"fdb645c8c4ebddc81a8e61b25312d0f26a36657aaff4c93629bb4c45dcc12d16","abstract_canon_sha256":"db2bd6cb050f69ee26a1d2fc65d746f9163a23417177fc2ff2a4ad0d06a923ad"},"schema_version":"1.0"},"canonical_sha256":"12f992b71f70a13d676f645ee94fd15c6b1b2b9f91e72ad6dee05cb9eb696786","source":{"kind":"arxiv","id":"2401.13388","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13388","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13388v3","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13388","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"CL4ZFNY7OCQT","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"CL4ZFNY7OCQT2Z3P","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"CL4ZFNY7","created_at":"2026-07-05T08:28:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CL4ZFNY7OCQT2Z3PMRPOST6RLR","target":"record","payload":{"canonical_record":{"source":{"id":"2401.13388","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T11:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"fdb645c8c4ebddc81a8e61b25312d0f26a36657aaff4c93629bb4c45dcc12d16","abstract_canon_sha256":"db2bd6cb050f69ee26a1d2fc65d746f9163a23417177fc2ff2a4ad0d06a923ad"},"schema_version":"1.0"},"canonical_sha256":"12f992b71f70a13d676f645ee94fd15c6b1b2b9f91e72ad6dee05cb9eb696786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:05.257028Z","signature_b64":"5QYLnQBVu8lSXmtvuXvT2r7sWtiGRlHSnFv2J6+G/JXwzRplSwSMWrcEXa6bTGquU0qMeFu1sxD1LmIvehx6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12f992b71f70a13d676f645ee94fd15c6b1b2b9f91e72ad6dee05cb9eb696786","last_reissued_at":"2026-07-05T08:28:05.256390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:05.256390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.13388","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQxR/j7NXMt7BhGxoqMzMVb3Kde97soMgZ6/AUbeAXEjRASJA8rWhb0FU8MIGCyuLs/oulSuh9PLC0kTYf2LAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:12.106225Z"},"content_sha256":"f7d6aba7b482d82d63ce10dbddea99e0598699a3d452c0846b3ec59e9a0df487","schema_version":"1.0","event_id":"sha256:f7d6aba7b482d82d63ce10dbddea99e0598699a3d452c0846b3ec59e9a0df487"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CL4ZFNY7OCQT2Z3PMRPOST6RLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiachen Liu, Wei Li, Xinyan Xiao, Xue Xu","submitted_at":"2024-01-24T11:36:44Z","abstract_excerpt":"Existing text-to-image diffusion models primarily generate images from text prompts. However, the inherent conciseness of textual descriptions poses challenges in faithfully synthesizing images with intricate details, such as specific entities or scenes. This paper presents UNIMO-G, a simple multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs, which demonstrates a unified ability for both text-driven and subject-driven image generation. UNIMO-G comprises two core components: a Multimodal Large Language Model (MLLM) for encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13388","kind":"arxiv","version":3},"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/2401.13388/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":"2026-07-05T08:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8vzzBAfZnUkwl5+G2+faoR9Pjt9XwmSL5tLsEy8ajcZ9cMO385OEKS8DRL5EEfY3/qzt5lr04WiRtRuBvmVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:03:12.106811Z"},"content_sha256":"2815f6f301a4424977e36a16a363b1a96dcea8ca1eecb80400c9e426e183bf31","schema_version":"1.0","event_id":"sha256:2815f6f301a4424977e36a16a363b1a96dcea8ca1eecb80400c9e426e183bf31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/bundle.json","state_url":"https://pith.science/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/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":"2026-08-04T17:03:12Z","links":{"resolver":"https://pith.science/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR","bundle":"https://pith.science/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/bundle.json","state":"https://pith.science/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CL4ZFNY7OCQT2Z3PMRPOST6RLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CL4ZFNY7OCQT2Z3PMRPOST6RLR","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":"db2bd6cb050f69ee26a1d2fc65d746f9163a23417177fc2ff2a4ad0d06a923ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T11:36:44Z","title_canon_sha256":"fdb645c8c4ebddc81a8e61b25312d0f26a36657aaff4c93629bb4c45dcc12d16"},"schema_version":"1.0","source":{"id":"2401.13388","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13388","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13388v3","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13388","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"CL4ZFNY7OCQT","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"CL4ZFNY7OCQT2Z3P","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"CL4ZFNY7","created_at":"2026-07-05T08:28:05Z"}],"graph_snapshots":[{"event_id":"sha256:2815f6f301a4424977e36a16a363b1a96dcea8ca1eecb80400c9e426e183bf31","target":"graph","created_at":"2026-07-05T08:28:05Z","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/2401.13388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing text-to-image diffusion models primarily generate images from text prompts. However, the inherent conciseness of textual descriptions poses challenges in faithfully synthesizing images with intricate details, such as specific entities or scenes. This paper presents UNIMO-G, a simple multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs, which demonstrates a unified ability for both text-driven and subject-driven image generation. UNIMO-G comprises two core components: a Multimodal Large Language Model (MLLM) for encod","authors_text":"Jiachen Liu, Wei Li, Xinyan Xiao, Xue Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T11:36:44Z","title":"UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13388","kind":"arxiv","version":3},"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:f7d6aba7b482d82d63ce10dbddea99e0598699a3d452c0846b3ec59e9a0df487","target":"record","created_at":"2026-07-05T08:28:05Z","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":"db2bd6cb050f69ee26a1d2fc65d746f9163a23417177fc2ff2a4ad0d06a923ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T11:36:44Z","title_canon_sha256":"fdb645c8c4ebddc81a8e61b25312d0f26a36657aaff4c93629bb4c45dcc12d16"},"schema_version":"1.0","source":{"id":"2401.13388","kind":"arxiv","version":3}},"canonical_sha256":"12f992b71f70a13d676f645ee94fd15c6b1b2b9f91e72ad6dee05cb9eb696786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12f992b71f70a13d676f645ee94fd15c6b1b2b9f91e72ad6dee05cb9eb696786","first_computed_at":"2026-07-05T08:28:05.256390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:05.256390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5QYLnQBVu8lSXmtvuXvT2r7sWtiGRlHSnFv2J6+G/JXwzRplSwSMWrcEXa6bTGquU0qMeFu1sxD1LmIvehx6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:05.257028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13388","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7d6aba7b482d82d63ce10dbddea99e0598699a3d452c0846b3ec59e9a0df487","sha256:2815f6f301a4424977e36a16a363b1a96dcea8ca1eecb80400c9e426e183bf31"],"state_sha256":"796377cc17b55c71342f24cbec92d8275d91ed6bd64c299b2a2a2f35683901a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TlNo+CeGT5CnB7ws2qO3/yukStglg4G73rC3SfGO7COe/NgbKe64FexF1Hd9rUlTP++h59dhESRZU3yUoydkAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:03:12.110594Z","bundle_sha256":"eb31e7e4e229822bb04dfdd011229fcd84821f48ab581886add3982c940eb9ef"}}