{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O3IFCWIAI32NWRYFS4CREBBB3Y","short_pith_number":"pith:O3IFCWIA","schema_version":"1.0","canonical_sha256":"76d051590046f4db47059705120421de333d37bd7d4fdd2205d559b7b4cc1486","source":{"kind":"arxiv","id":"2606.07053","version":1},"attestation_state":"computed","paper":{"title":"TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dian Gu, Zhengyi Yang","submitted_at":"2026-06-05T08:54:28Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T08:54:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8040691386429d71daab2bd3f5aed26e2b5c25989dec4f6aec10536bae49a868","abstract_canon_sha256":"fa2ebc7be288a0d69db9e328b701c1d9d8d180a3a07969a14db91dee3b485d68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:43.528538Z","signature_b64":"aSrnRwceBE1ghnREtsyMlFmqCgczufUZynykC9bADmH/xHcoJNDKhhNEXKARqY0qp3VPH1xPgaPn1oda/WxBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76d051590046f4db47059705120421de333d37bd7d4fdd2205d559b7b4cc1486","last_reissued_at":"2026-06-08T01:04:43.527808Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:43.527808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dian Gu, Zhengyi Yang","submitted_at":"2026-06-05T08:54:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07053","kind":"arxiv","version":1},"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/2606.07053/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07053","created_at":"2026-06-08T01:04:43.527919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07053v1","created_at":"2026-06-08T01:04:43.527919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07053","created_at":"2026-06-08T01:04:43.527919+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3IFCWIAI32N","created_at":"2026-06-08T01:04:43.527919+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3IFCWIAI32NWRYF","created_at":"2026-06-08T01:04:43.527919+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3IFCWIA","created_at":"2026-06-08T01:04:43.527919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y","json":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y.json","graph_json":"https://pith.science/api/pith-number/O3IFCWIAI32NWRYFS4CREBBB3Y/graph.json","events_json":"https://pith.science/api/pith-number/O3IFCWIAI32NWRYFS4CREBBB3Y/events.json","paper":"https://pith.science/paper/O3IFCWIA"},"agent_actions":{"view_html":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y","download_json":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y.json","view_paper":"https://pith.science/paper/O3IFCWIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07053&json=true","fetch_graph":"https://pith.science/api/pith-number/O3IFCWIAI32NWRYFS4CREBBB3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/O3IFCWIAI32NWRYFS4CREBBB3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y/action/storage_attestation","attest_author":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y/action/author_attestation","sign_citation":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y/action/citation_signature","submit_replication":"https://pith.science/pith/O3IFCWIAI32NWRYFS4CREBBB3Y/action/replication_record"}},"created_at":"2026-06-08T01:04:43.527919+00:00","updated_at":"2026-06-08T01:04:43.527919+00:00"}