{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3VRCM3WRJISTCIEUMJG6OMV6JJ","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":"db7646db6a546c095d383e62d59436a698bb99b8445d831d834d5e06a227ac30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-25T07:47:21Z","title_canon_sha256":"9d92ca0ec65f255ebba95535c5f5cfb46f3480deb64700f2eb4ce40284b01251"},"schema_version":"1.0","source":{"id":"2303.14389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14389","created_at":"2026-07-05T07:47:42Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14389v2","created_at":"2026-07-05T07:47:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14389","created_at":"2026-07-05T07:47:42Z"},{"alias_kind":"pith_short_12","alias_value":"3VRCM3WRJIST","created_at":"2026-07-05T07:47:42Z"},{"alias_kind":"pith_short_16","alias_value":"3VRCM3WRJISTCIEU","created_at":"2026-07-05T07:47:42Z"},{"alias_kind":"pith_short_8","alias_value":"3VRCM3WR","created_at":"2026-07-05T07:47:42Z"}],"graph_snapshots":[{"event_id":"sha256:9260f2a8ca80ade81ef58df878b1f5e1eb9f6486cd308c6269c1b0cbfec3e168","target":"graph","created_at":"2026-07-05T07:47:42Z","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/2303.14389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs' ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric diffusion transformer is designed to predict masked t","authors_text":"Ming-Ming Cheng, Pan Zhou, Shanghua Gao, Shuicheng Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-25T07:47:21Z","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14389","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":"sha256:79868c58a5a9be137a686e79dff6eb22172c84c857273b9238a0b0ae22310fc2","target":"record","created_at":"2026-07-05T07:47:42Z","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":"db7646db6a546c095d383e62d59436a698bb99b8445d831d834d5e06a227ac30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-25T07:47:21Z","title_canon_sha256":"9d92ca0ec65f255ebba95535c5f5cfb46f3480deb64700f2eb4ce40284b01251"},"schema_version":"1.0","source":{"id":"2303.14389","kind":"arxiv","version":2}},"canonical_sha256":"dd62266ed14a25312094624de732be4a72581951e85920f69780f882dd1192d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd62266ed14a25312094624de732be4a72581951e85920f69780f882dd1192d2","first_computed_at":"2026-07-05T07:47:42.798845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:42.798845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E5BFuvTziEKgbH0s58Yzi19athLv/NfZuBDTXdvDBXYVxtMjS9OgNUh833uux/vwmKOtt9vD2SIFSMAN0EN2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:42.799426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79868c58a5a9be137a686e79dff6eb22172c84c857273b9238a0b0ae22310fc2","sha256:9260f2a8ca80ade81ef58df878b1f5e1eb9f6486cd308c6269c1b0cbfec3e168"],"state_sha256":"18d92e8a64f7ecdeab461c7b27d80342a307f55ed149586831c6a05dd50b3579"}