{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B2D5QZK6LAMSMANMHEEEXBUGJ3","short_pith_number":"pith:B2D5QZK6","canonical_record":{"source":{"id":"2504.10148","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T11:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"b3f117a73deebdba3b0ef8a44ece2168e50cd26e8d9b02328c60d630aa29ad21","abstract_canon_sha256":"28a420feed63777fe163c2e0245db0afa0e87292262addc3d2777510b1779fb4"},"schema_version":"1.0"},"canonical_sha256":"0e87d8655e58192601ac39084b86864ec9ad5d5a95949c3d6594e5270f831ed4","source":{"kind":"arxiv","id":"2504.10148","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B2D5QZK6LAMSMANMHEEEXBUGJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2504.10148","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T11:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"b3f117a73deebdba3b0ef8a44ece2168e50cd26e8d9b02328c60d630aa29ad21","abstract_canon_sha256":"28a420feed63777fe163c2e0245db0afa0e87292262addc3d2777510b1779fb4"},"schema_version":"1.0"},"canonical_sha256":"0e87d8655e58192601ac39084b86864ec9ad5d5a95949c3d6594e5270f831ed4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:36.745478Z","signature_b64":"JcXydf7NvLORTTJWAUOR7I8JNaqDXCJpWHJEVEOGwufAgUbYsHhpzTj3yeFKbjQxyAIHOhQgovFTYTXUWr5MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e87d8655e58192601ac39084b86864ec9ad5d5a95949c3d6594e5270f831ed4","last_reissued_at":"2026-07-05T10:51:36.744970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:36.744970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.10148","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aoVogjzx5vekvH5ccSoCxb/3tlEd7hjow8kEbwktQhKbDCzF17Zp8Zvs1jD/iN3kenx5NtHgzJFYHvvaoGRADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:22.135030Z"},"content_sha256":"7378e7c7dee39979d5a2536ce9e6af231032926401186a6e780907b18e6bb923","schema_version":"1.0","event_id":"sha256:7378e7c7dee39979d5a2536ce9e6af231032926401186a6e780907b18e6bb923"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B2D5QZK6LAMSMANMHEEEXBUGJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical and Step-Layer-Wise Tuning of Attention Specialty for Multi-Instance Synthesis in Diffusion Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyang Zhang, Daoyi Dong, Dong Gong, Huadong Mo, Junyan Wang, Yu Zhang, Zhenhong Sun, Zhicheng Zhang","submitted_at":"2025-04-14T11:59:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10148","kind":"arxiv","version":2},"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/2504.10148/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":"2026-07-05T10:51:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fA1okW/L7tBUKm1Ob7+k86E1q82bazy0e3/eLXNopZhzrxOcseXiPC2AZKioit4nmhlYPe1j0rTqucHHqL1rBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:22.135417Z"},"content_sha256":"4b8fa37689b0b4036855c30f6479897558b8c4e382064f34dd3b7e2ec3f42c29","schema_version":"1.0","event_id":"sha256:4b8fa37689b0b4036855c30f6479897558b8c4e382064f34dd3b7e2ec3f42c29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/bundle.json","state_url":"https://pith.science/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/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":"2026-07-07T07:07:22Z","links":{"resolver":"https://pith.science/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3","bundle":"https://pith.science/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/bundle.json","state":"https://pith.science/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2D5QZK6LAMSMANMHEEEXBUGJ3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtBTZZJUU99JlICx4nVYg5Dh9vXzBweUd13YhMCR5rhnvW895DH/sgsHYZ7QVL0+dCl0YusPIrO9M7KDethQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:07:22.137574Z","bundle_sha256":"0c3614ba83cf833fbbad2180ec60f27a9a5ade49ee95513403aa4dbdf321cf29"}}