{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TIKLMLPKB3CZHGRFLPW6TDFEKH","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":"cc0a08593b490f3c3e9ca22e88559f9855854325a2a5b085ded9900a4416eb8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T00:40:12Z","title_canon_sha256":"9db3bc1f980526d6da6f0cdc0e4611aeefb72590d0b5a2bbdaeb4a0ae09e11f5"},"schema_version":"1.0","source":{"id":"2508.07519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07519","created_at":"2026-07-05T11:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07519v1","created_at":"2026-07-05T11:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07519","created_at":"2026-07-05T11:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"TIKLMLPKB3CZ","created_at":"2026-07-05T11:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"TIKLMLPKB3CZHGRF","created_at":"2026-07-05T11:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"TIKLMLPK","created_at":"2026-07-05T11:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:f7a1bf0e8fd8f5c4acbb78adea05082da40cca3e270e2bf1dfd59b2076200ecf","target":"graph","created_at":"2026-07-05T11:51:47Z","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/2508.07519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based diffusion models have recently superseded traditional U-Net architectures, with multimodal diffusion transformers (MM-DiT) emerging as the dominant approach in state-of-the-art models like Stable Diffusion 3 and Flux.1. Previous approaches have relied on unidirectional cross-attention mechanisms, with information flowing from text embeddings to image latents. In contrast, MMDiT introduces a unified attention mechanism that concatenates input projections from both modalities and performs a single full attention operation, allowing bidirectional information flow between text an","authors_text":"Alchan Hwang, Daneul Kim, Jaesik Park, Joonghyuk Shin, Yujin Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T00:40:12Z","title":"Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07519","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":"sha256:6066235ac5d1b62cb42cc8de31fa33fb03abf3a2cbdaf9c91712b227e6749b0d","target":"record","created_at":"2026-07-05T11:51:47Z","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":"cc0a08593b490f3c3e9ca22e88559f9855854325a2a5b085ded9900a4416eb8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T00:40:12Z","title_canon_sha256":"9db3bc1f980526d6da6f0cdc0e4611aeefb72590d0b5a2bbdaeb4a0ae09e11f5"},"schema_version":"1.0","source":{"id":"2508.07519","kind":"arxiv","version":1}},"canonical_sha256":"9a14b62dea0ec5939a255bede98ca451ccf6513499b732a9c8d6a9d5fa69959f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a14b62dea0ec5939a255bede98ca451ccf6513499b732a9c8d6a9d5fa69959f","first_computed_at":"2026-07-05T11:51:47.437037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:47.437037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hTiRMAJ0IyuiXnM+tRDBzYNggpkHq2ObsjAhwHzxzyCpbOAXumEuQA4HcVFcl4ZRmpxa/fTUWVMGH+DH7FtaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:47.437504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6066235ac5d1b62cb42cc8de31fa33fb03abf3a2cbdaf9c91712b227e6749b0d","sha256:f7a1bf0e8fd8f5c4acbb78adea05082da40cca3e270e2bf1dfd59b2076200ecf"],"state_sha256":"3df63f17ef53ff73bb75c68b465a06b963111b265a841ae9b7b4212ae0059025"}