{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S433ZWLMBIRRBSMSPMVS4CWR5I","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":"1ba9ee25019d003a38c9e31ed9de6a3163d43895d988519cdfacede8638c8dd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-02T15:57:13Z","title_canon_sha256":"996527522bbc460d54f55d6eb2e7376b48991a6ba80f3e16163d152a1ac98053"},"schema_version":"1.0","source":{"id":"2402.01516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01516","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01516v2","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01516","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"S433ZWLMBIRR","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_16","alias_value":"S433ZWLMBIRRBSMS","created_at":"2026-07-05T08:26:18Z"},{"alias_kind":"pith_short_8","alias_value":"S433ZWLM","created_at":"2026-07-05T08:26:18Z"}],"graph_snapshots":[{"event_id":"sha256:748f57dac837428b05ce5f32a34e4cfc4038fe866953ebfb84fcb2b8b0bcf253","target":"graph","created_at":"2026-07-05T08:26:18Z","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/2402.01516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present X-MDPT ($\\underline{Cross}$-view $\\underline{M}$asked $\\underline{D}$iffusion $\\underline{P}$rediction $\\underline{T}$ransformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction ","authors_text":"Chang D. Yoo, Trung X. Pham, Zhang Kang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-02T15:57:13Z","title":"Cross-view Masked Diffusion Transformers for Person Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01516","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":"sha256:5b54155ae98090562f8a93c7650239e5ff3686d1a0899c463c7d10005ae61e2b","target":"record","created_at":"2026-07-05T08:26:18Z","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":"1ba9ee25019d003a38c9e31ed9de6a3163d43895d988519cdfacede8638c8dd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-02T15:57:13Z","title_canon_sha256":"996527522bbc460d54f55d6eb2e7376b48991a6ba80f3e16163d152a1ac98053"},"schema_version":"1.0","source":{"id":"2402.01516","kind":"arxiv","version":2}},"canonical_sha256":"9737bcd96c0a2310c9927b2b2e0ad1ea2dab8935b1a7d02a494911a3084111b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9737bcd96c0a2310c9927b2b2e0ad1ea2dab8935b1a7d02a494911a3084111b7","first_computed_at":"2026-07-05T08:26:18.577514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:18.577514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"de8SwaQuBeJiZTAi6LT/bAKlTVz3v5vH/A/Pfu1int7EOfrVf6Zpbahnv/ePGGbRLmOIvnaulA5dobzbYHWaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:18.578003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b54155ae98090562f8a93c7650239e5ff3686d1a0899c463c7d10005ae61e2b","sha256:748f57dac837428b05ce5f32a34e4cfc4038fe866953ebfb84fcb2b8b0bcf253"],"state_sha256":"851da7c75c57a34bae659193f6342cf6b9f2397e1047ddded9fa02cef466b678"}