{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B2D5QZK6LAMSMANMHEEEXBUGJ3","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":"28a420feed63777fe163c2e0245db0afa0e87292262addc3d2777510b1779fb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T11:59:58Z","title_canon_sha256":"b3f117a73deebdba3b0ef8a44ece2168e50cd26e8d9b02328c60d630aa29ad21"},"schema_version":"1.0","source":{"id":"2504.10148","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10148","created_at":"2026-07-05T10:51:36Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10148v2","created_at":"2026-07-05T10:51:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10148","created_at":"2026-07-05T10:51:36Z"},{"alias_kind":"pith_short_12","alias_value":"B2D5QZK6LAMS","created_at":"2026-07-05T10:51:36Z"},{"alias_kind":"pith_short_16","alias_value":"B2D5QZK6LAMSMANM","created_at":"2026-07-05T10:51:36Z"},{"alias_kind":"pith_short_8","alias_value":"B2D5QZK6","created_at":"2026-07-05T10:51:36Z"}],"graph_snapshots":[{"event_id":"sha256:4b8fa37689b0b4036855c30f6479897558b8c4e382064f34dd3b7e2ec3f42c29","target":"graph","created_at":"2026-07-05T10:51:36Z","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/2504.10148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image (T2I) generation models often struggle with multi-instance synthesis (MIS), where they must accurately depict multiple distinct instances in a single image based on complex prompts detailing individual features. Traditional MIS control methods for UNet architectures like SD v1.5/SDXL fail to adapt to DiT-based models like FLUX and SD v3.5, which rely on integrated attention between image and text tokens rather than text-image cross-attention. To enhance MIS in DiT, we first analyze the mixed attention mechanism in DiT. Our token-wise and layer-wise analysis of attention maps reve","authors_text":"Chunyang Zhang, Daoyi Dong, Dong Gong, Huadong Mo, Junyan Wang, Yu Zhang, Zhenhong Sun, Zhicheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T11:59:58Z","title":"Hierarchical and Step-Layer-Wise Tuning of Attention Specialty for Multi-Instance Synthesis in Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10148","kind":"arxiv","version":2},"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":"sha256:7378e7c7dee39979d5a2536ce9e6af231032926401186a6e780907b18e6bb923","target":"record","created_at":"2026-07-05T10:51:36Z","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":"28a420feed63777fe163c2e0245db0afa0e87292262addc3d2777510b1779fb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T11:59:58Z","title_canon_sha256":"b3f117a73deebdba3b0ef8a44ece2168e50cd26e8d9b02328c60d630aa29ad21"},"schema_version":"1.0","source":{"id":"2504.10148","kind":"arxiv","version":2}},"canonical_sha256":"0e87d8655e58192601ac39084b86864ec9ad5d5a95949c3d6594e5270f831ed4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e87d8655e58192601ac39084b86864ec9ad5d5a95949c3d6594e5270f831ed4","first_computed_at":"2026-07-05T10:51:36.744970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:36.744970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JcXydf7NvLORTTJWAUOR7I8JNaqDXCJpWHJEVEOGwufAgUbYsHhpzTj3yeFKbjQxyAIHOhQgovFTYTXUWr5MBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:36.745478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10148","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7378e7c7dee39979d5a2536ce9e6af231032926401186a6e780907b18e6bb923","sha256:4b8fa37689b0b4036855c30f6479897558b8c4e382064f34dd3b7e2ec3f42c29"],"state_sha256":"0f5ae29a3728ade946893fbd43a4d23121f3abb5c3b6a8bee4d2406ef17c03b2"}