{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3QAD2RBFB6SKEJBTJOPYOKXT7R","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":"8557eec00cab809be386bd992daa965fecf1f6aa2d6837b2b025a302b3be3ff3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:49:37Z","title_canon_sha256":"90f4a490782181e24e2d8f8857d377bcf0ebf0c7d96fe7a164901aa64c305117"},"schema_version":"1.0","source":{"id":"2405.14832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14832","created_at":"2026-07-05T08:25:54Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14832v2","created_at":"2026-07-05T08:25:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14832","created_at":"2026-07-05T08:25:54Z"},{"alias_kind":"pith_short_12","alias_value":"3QAD2RBFB6SK","created_at":"2026-07-05T08:25:54Z"},{"alias_kind":"pith_short_16","alias_value":"3QAD2RBFB6SKEJBT","created_at":"2026-07-05T08:25:54Z"},{"alias_kind":"pith_short_8","alias_value":"3QAD2RBF","created_at":"2026-07-05T08:25:54Z"}],"graph_snapshots":[{"event_id":"sha256:461f9fa29bdfad9fcf3a86c3a4d6233260edce60c6c7f5202b2a31557b995219","target":"graph","created_at":"2026-07-05T08:25:54Z","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/2405.14832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization. Our approach comprises two primary components: a Direct 3D Variational Auto-Encoder (D3D-VAE) and a Direct 3D Diffusion Transformer (D3D-DiT). D3D-VAE efficiently encodes high-resolution 3D shapes into a compact and continuous laten","authors_text":"Feihu Zhang, Jingxi Xu, Philip Torr, Shuang Wu, Xun Cao, Yao Yao, Yifei Zeng, Youtian Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:49:37Z","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14832","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:b985771ea37206ebb48898a6308d12a52827e74a51df34ea35c07c085d6ef902","target":"record","created_at":"2026-07-05T08:25:54Z","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":"8557eec00cab809be386bd992daa965fecf1f6aa2d6837b2b025a302b3be3ff3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T17:49:37Z","title_canon_sha256":"90f4a490782181e24e2d8f8857d377bcf0ebf0c7d96fe7a164901aa64c305117"},"schema_version":"1.0","source":{"id":"2405.14832","kind":"arxiv","version":2}},"canonical_sha256":"dc003d44250fa4a224334b9f872af3fc6e52fda67efa498256d17b5554234496","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc003d44250fa4a224334b9f872af3fc6e52fda67efa498256d17b5554234496","first_computed_at":"2026-07-05T08:25:54.620369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:54.620369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ts43Oi1oZl5S79xejGVsbsIy4MbfLNGtLpbUpp3M1W/yHqYRi8UfHP3RXkD5oiV3VeIW9ZHxwagpk5pptg4uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:54.620905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b985771ea37206ebb48898a6308d12a52827e74a51df34ea35c07c085d6ef902","sha256:461f9fa29bdfad9fcf3a86c3a4d6233260edce60c6c7f5202b2a31557b995219"],"state_sha256":"c9aebc8f3fad0514d3c277e427e558fc816bf944277b901632def87193618dd0"}