{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ETOMXNGTUC3TTM5H3JUVMDLXIH","short_pith_number":"pith:ETOMXNGT","canonical_record":{"source":{"id":"2303.09319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"d7cf5a722bf9a5dcdeca8a548c04e1d9c8b1070c27f80b534120ccb1dea8f79c","abstract_canon_sha256":"9dd4c78be8fc458692bea336a20cc34c15b83c4dfd3ad6dfd036edc2836c12a1"},"schema_version":"1.0"},"canonical_sha256":"24dccbb4d3a0b739b3a7da69560d7741fb805cb242b781f7463710aa41df161e","source":{"kind":"arxiv","id":"2303.09319","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09319","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09319v1","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09319","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"ETOMXNGTUC3T","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"ETOMXNGTUC3TTM5H","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"ETOMXNGT","created_at":"2026-07-05T05:51:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ETOMXNGTUC3TTM5H3JUVMDLXIH","target":"record","payload":{"canonical_record":{"source":{"id":"2303.09319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"d7cf5a722bf9a5dcdeca8a548c04e1d9c8b1070c27f80b534120ccb1dea8f79c","abstract_canon_sha256":"9dd4c78be8fc458692bea336a20cc34c15b83c4dfd3ad6dfd036edc2836c12a1"},"schema_version":"1.0"},"canonical_sha256":"24dccbb4d3a0b739b3a7da69560d7741fb805cb242b781f7463710aa41df161e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:51.800372Z","signature_b64":"ri+EWa2PjoGK/WyG7WAMHFrE525xCoOGZJzNBngvKPsmNcBfeTqr/51HzsmUt4OGIF8VRo+bN3FVPZgbW/z7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24dccbb4d3a0b739b3a7da69560d7741fb805cb242b781f7463710aa41df161e","last_reissued_at":"2026-07-05T05:51:51.799851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:51.799851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.09319","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":"2026-07-05T05:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPCsWBLINZF7KKYrv044RLi4FA9x0qgGfgKnA8xFQs5e7fUlL3w5jtNwichfz85i524/7R9MXlUXlPllVErWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:57:48.165216Z"},"content_sha256":"3b5021bde07b1b848f5e7f1010a90f12fee437a50bfeb1da4106f35d63442719","schema_version":"1.0","event_id":"sha256:3b5021bde07b1b848f5e7f1010a90f12fee437a50bfeb1da4106f35d63442719"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ETOMXNGTUC3TTM5H3JUVMDLXIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huan Yang, Jianlong Fu, Jiaying Liu, Wenjing Wang, Yiyang Ma","submitted_at":"2023-03-16T13:50:20Z","abstract_excerpt":"Language-guided image generation has achieved great success nowadays by using diffusion models. However, texts can be less detailed to describe highly-specific subjects such as a particular dog or a certain car, which makes pure text-to-image generation not accurate enough to satisfy user requirements. In this work, we present a novel Unified Multi-Modal Latent Diffusion (UMM-Diffusion) which takes joint texts and images containing specified subjects as input sequences and generates customized images with the subjects. To be more specific, both input texts and images are encoded into one unifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09319","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/2303.09319/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":"2026-07-05T05:51:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9FNaUPfCjQS4I1cVFspWF2QXNhjzARu9oeshPYMLSJ3cvYGYF74GmH2Ap5FL7dMnHBJTgT5UGC1HMLyVxa1/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:57:48.165587Z"},"content_sha256":"e1f37adb9b8b8e275a703743f73d6193c34404e72e25f17e372d7dc44a45a8ef","schema_version":"1.0","event_id":"sha256:e1f37adb9b8b8e275a703743f73d6193c34404e72e25f17e372d7dc44a45a8ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/bundle.json","state_url":"https://pith.science/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/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":"2026-08-19T22:57:48Z","links":{"resolver":"https://pith.science/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH","bundle":"https://pith.science/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/bundle.json","state":"https://pith.science/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETOMXNGTUC3TTM5H3JUVMDLXIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ETOMXNGTUC3TTM5H3JUVMDLXIH","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":"9dd4c78be8fc458692bea336a20cc34c15b83c4dfd3ad6dfd036edc2836c12a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:50:20Z","title_canon_sha256":"d7cf5a722bf9a5dcdeca8a548c04e1d9c8b1070c27f80b534120ccb1dea8f79c"},"schema_version":"1.0","source":{"id":"2303.09319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09319","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09319v1","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09319","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_12","alias_value":"ETOMXNGTUC3T","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_16","alias_value":"ETOMXNGTUC3TTM5H","created_at":"2026-07-05T05:51:51Z"},{"alias_kind":"pith_short_8","alias_value":"ETOMXNGT","created_at":"2026-07-05T05:51:51Z"}],"graph_snapshots":[{"event_id":"sha256:e1f37adb9b8b8e275a703743f73d6193c34404e72e25f17e372d7dc44a45a8ef","target":"graph","created_at":"2026-07-05T05:51:51Z","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/2303.09319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-guided image generation has achieved great success nowadays by using diffusion models. However, texts can be less detailed to describe highly-specific subjects such as a particular dog or a certain car, which makes pure text-to-image generation not accurate enough to satisfy user requirements. In this work, we present a novel Unified Multi-Modal Latent Diffusion (UMM-Diffusion) which takes joint texts and images containing specified subjects as input sequences and generates customized images with the subjects. To be more specific, both input texts and images are encoded into one unifi","authors_text":"Huan Yang, Jianlong Fu, Jiaying Liu, Wenjing Wang, Yiyang Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:50:20Z","title":"Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09319","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":"sha256:3b5021bde07b1b848f5e7f1010a90f12fee437a50bfeb1da4106f35d63442719","target":"record","created_at":"2026-07-05T05:51:51Z","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":"9dd4c78be8fc458692bea336a20cc34c15b83c4dfd3ad6dfd036edc2836c12a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:50:20Z","title_canon_sha256":"d7cf5a722bf9a5dcdeca8a548c04e1d9c8b1070c27f80b534120ccb1dea8f79c"},"schema_version":"1.0","source":{"id":"2303.09319","kind":"arxiv","version":1}},"canonical_sha256":"24dccbb4d3a0b739b3a7da69560d7741fb805cb242b781f7463710aa41df161e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24dccbb4d3a0b739b3a7da69560d7741fb805cb242b781f7463710aa41df161e","first_computed_at":"2026-07-05T05:51:51.799851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:51.799851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ri+EWa2PjoGK/WyG7WAMHFrE525xCoOGZJzNBngvKPsmNcBfeTqr/51HzsmUt4OGIF8VRo+bN3FVPZgbW/z7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:51.800372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b5021bde07b1b848f5e7f1010a90f12fee437a50bfeb1da4106f35d63442719","sha256:e1f37adb9b8b8e275a703743f73d6193c34404e72e25f17e372d7dc44a45a8ef"],"state_sha256":"dbf53f55a5bd21da08508f986493ac94f8fcebf076e76b3235f1adb2ba6d0bb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lv3t6aKAtdBCDphdT/Yb2zpUAea4MjVuNwZn/GMJUhZ8DFZ2g6GrKMA6jeduA6O2/HzbbSeiF5dkS1snglr6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:57:48.170131Z","bundle_sha256":"a5a69665662d3a6882a636a36a32a5fe161c0d44af3d41474609d6f2c0726664"}}