{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O3IFCWIAI32NWRYFS4CREBBB3Y","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":"fa2ebc7be288a0d69db9e328b701c1d9d8d180a3a07969a14db91dee3b485d68","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T08:54:28Z","title_canon_sha256":"8040691386429d71daab2bd3f5aed26e2b5c25989dec4f6aec10536bae49a868"},"schema_version":"1.0","source":{"id":"2606.07053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07053","created_at":"2026-06-08T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07053v1","created_at":"2026-06-08T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07053","created_at":"2026-06-08T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"O3IFCWIAI32N","created_at":"2026-06-08T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"O3IFCWIAI32NWRYF","created_at":"2026-06-08T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"O3IFCWIA","created_at":"2026-06-08T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:2a25c9fa18af998a03ac5676cb964a1984817830613d8d7d0be1fdc43477624c","target":"graph","created_at":"2026-06-08T01:04:43Z","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/2606.07053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pose-guided text-to-image generation often suffers from limb distortions and feature crosstalk in complex multi-person scenarios. While existing UNet-based adapters struggle with long-range spatial dependencies, emerging Multimodal Diffusion Transformers (MM-DiTs) offer superior global modeling. However, naive signal concatenation in MM-DiTs severely disrupts pre-trained latent distributions. To address this, we propose TrioPose, a native pose-driven framework built upon the SD3.5M architecture. Specifically, we introduce a Triple-Stream Pose-Aware DiT (TSPA-DiT) that treats pose as an indepen","authors_text":"Dian Gu, Zhengyi Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T08:54:28Z","title":"TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07053","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:ec8b4b0077c18ad747d52bb3764660852d79bc8bf6c3ec336ca6230ea43bbb84","target":"record","created_at":"2026-06-08T01:04:43Z","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":"fa2ebc7be288a0d69db9e328b701c1d9d8d180a3a07969a14db91dee3b485d68","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T08:54:28Z","title_canon_sha256":"8040691386429d71daab2bd3f5aed26e2b5c25989dec4f6aec10536bae49a868"},"schema_version":"1.0","source":{"id":"2606.07053","kind":"arxiv","version":1}},"canonical_sha256":"76d051590046f4db47059705120421de333d37bd7d4fdd2205d559b7b4cc1486","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76d051590046f4db47059705120421de333d37bd7d4fdd2205d559b7b4cc1486","first_computed_at":"2026-06-08T01:04:43.527808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:43.527808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aSrnRwceBE1ghnREtsyMlFmqCgczufUZynykC9bADmH/xHcoJNDKhhNEXKARqY0qp3VPH1xPgaPn1oda/WxBDg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:43.528538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec8b4b0077c18ad747d52bb3764660852d79bc8bf6c3ec336ca6230ea43bbb84","sha256:2a25c9fa18af998a03ac5676cb964a1984817830613d8d7d0be1fdc43477624c"],"state_sha256":"048020ca41f4ba94a8afcb3f900f5ffcdb0af9c774d5149c054076c0cb7b3a22"}