{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WKL3INGZHWK2JZH7TQVA7H4ESR","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":"83e6453c6684ea4e9d24626ba9f9de7a76bcd3dca04f639c7eebf74e7dc9a0dd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T14:31:20Z","title_canon_sha256":"6838346db7fa54a10c12e72f42f39bdcba8be8a0d6212c41dfa1b2e8824cd3de"},"schema_version":"1.0","source":{"id":"2305.15194","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15194","created_at":"2026-07-05T11:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15194v3","created_at":"2026-07-05T11:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15194","created_at":"2026-07-05T11:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"WKL3INGZHWK2","created_at":"2026-07-05T11:59:03Z"},{"alias_kind":"pith_short_16","alias_value":"WKL3INGZHWK2JZH7","created_at":"2026-07-05T11:59:03Z"},{"alias_kind":"pith_short_8","alias_value":"WKL3INGZ","created_at":"2026-07-05T11:59:03Z"}],"graph_snapshots":[{"event_id":"sha256:8ad20a8afcbffd57104a4f3c808e630ed11ddd23df00412041c3dda4eeab1dc0","target":"graph","created_at":"2026-07-05T11:59:03Z","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/2305.15194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we aim to enhance the capabilities of diffusion-based text-to-image (T2I) generation models by integrating diverse modalities beyond textual descriptions within a unified framework. To this end, we categorize widely used conditional inputs into three modality types: structure, layout, and attribute. We propose a multimodal T2I diffusion model, which is capable of processing all three modalities within a single architecture without modifying the parameters of the pre-trained diffusion model, as only a small subset of components is updated. Our approach sets new benchmarks in mult","authors_text":"Daesik Kim, Junsoo Lee, Kibeom Hong, Namhyuk Ahn, Sungnyun Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T14:31:20Z","title":"DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15194","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:de4a097bea068eaed911c5a10e776cf0de33947c8e75fdb0e5bc1d662b5f56af","target":"record","created_at":"2026-07-05T11:59:03Z","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":"83e6453c6684ea4e9d24626ba9f9de7a76bcd3dca04f639c7eebf74e7dc9a0dd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T14:31:20Z","title_canon_sha256":"6838346db7fa54a10c12e72f42f39bdcba8be8a0d6212c41dfa1b2e8824cd3de"},"schema_version":"1.0","source":{"id":"2305.15194","kind":"arxiv","version":3}},"canonical_sha256":"b297b434d93d95a4e4ff9c2a0f9f849462e7d96d58922abaed931182a6eed231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b297b434d93d95a4e4ff9c2a0f9f849462e7d96d58922abaed931182a6eed231","first_computed_at":"2026-07-05T11:59:03.077494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:03.077494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nzpvOtfm79IaWgl85obUru5Kywn8vSN3K8O8jnjTaqAztaf0LobhiGpnN20Zo9rQDc9dcHh9WJ2R65Hl5BXgCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:03.077949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15194","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de4a097bea068eaed911c5a10e776cf0de33947c8e75fdb0e5bc1d662b5f56af","sha256:8ad20a8afcbffd57104a4f3c808e630ed11ddd23df00412041c3dda4eeab1dc0"],"state_sha256":"f2690883ee456c6a0a67dfd93976a83f51d325fa36fc94da29597f3daacb4e36"}