{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:45KTSWNWVJ6JWDHF56V2F3CMLJ","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":"b1142d3b0a46dc468abfbea687f8033d15f1ad2af9575444a254ddf2872cbb16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T16:17:32Z","title_canon_sha256":"abe0af40f83ccdced80c8d402f8c1d5ce24c46e40a1c238e70159d04e15e9109"},"schema_version":"1.0","source":{"id":"2507.04451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04451","created_at":"2026-07-05T11:32:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04451v1","created_at":"2026-07-05T11:32:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04451","created_at":"2026-07-05T11:32:48Z"},{"alias_kind":"pith_short_12","alias_value":"45KTSWNWVJ6J","created_at":"2026-07-05T11:32:48Z"},{"alias_kind":"pith_short_16","alias_value":"45KTSWNWVJ6JWDHF","created_at":"2026-07-05T11:32:48Z"},{"alias_kind":"pith_short_8","alias_value":"45KTSWNW","created_at":"2026-07-05T11:32:48Z"}],"graph_snapshots":[{"event_id":"sha256:7af2af3a30613735853f91ffa6dbb7bd15d504a7fb901467107db08037cf3a0d","target":"graph","created_at":"2026-07-05T11:32:48Z","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/2507.04451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current text-to-image (T2I) generation models struggle to align spatial composition with the input text, especially in complex scenes. Even layout-based approaches yield suboptimal spatial control, as their generation process is decoupled from layout planning, making it difficult to refine the layout during synthesis. We present CoT-Diff, a framework that brings step-by-step CoT-style reasoning into T2I generation by tightly integrating Multimodal Large Language Model (MLLM)-driven 3D layout planning with the diffusion process. CoT-Diff enables layout-aware reasoning inline within a single dif","authors_text":"Fan Wang, Li Yuan, Munan Ning, Qihui Zhang, Shuo Yang, Weihua Chen, Xianzhe Xu, Yibing Song, Yiwei Yang, Zheyuan Liu, Zhongrui Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T16:17:32Z","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04451","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":"sha256:2b322139ea72d36dca9d7da366ad174d5be694cdc68ea0e06d992a738885df59","target":"record","created_at":"2026-07-05T11:32:48Z","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":"b1142d3b0a46dc468abfbea687f8033d15f1ad2af9575444a254ddf2872cbb16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T16:17:32Z","title_canon_sha256":"abe0af40f83ccdced80c8d402f8c1d5ce24c46e40a1c238e70159d04e15e9109"},"schema_version":"1.0","source":{"id":"2507.04451","kind":"arxiv","version":1}},"canonical_sha256":"e7553959b6aa7c9b0ce5efaba2ec4c5a4e9bed61107cc60c1231d22a42f44a92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7553959b6aa7c9b0ce5efaba2ec4c5a4e9bed61107cc60c1231d22a42f44a92","first_computed_at":"2026-07-05T11:32:48.273203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:48.273203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oPL95yxwNAncvL0omtrK67gGoxeDilV6+Yu5svanvSvPBipSRjpSjW4j9PCKHgLJwMoQt7T0YznD1VZS68qsDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:48.273694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b322139ea72d36dca9d7da366ad174d5be694cdc68ea0e06d992a738885df59","sha256:7af2af3a30613735853f91ffa6dbb7bd15d504a7fb901467107db08037cf3a0d"],"state_sha256":"157a2818f36c07faae4d680c448d0c33c5e68f947019e37131205c0ef92ff24b"}