{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LOOU4GYZD4TQVS34HSD3VG2QG6","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":"0f7ae19b8d0c7099e0e213a9582b9fcc0740d7d7f1caddaf86fe5eb935a7ccc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T12:10:11Z","title_canon_sha256":"5f70614c09966d4c70fb6919d4982cdee0457d089fbcf2777681e7cba3b221c4"},"schema_version":"1.0","source":{"id":"2507.00707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00707","created_at":"2026-07-05T11:30:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00707v1","created_at":"2026-07-05T11:30:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00707","created_at":"2026-07-05T11:30:13Z"},{"alias_kind":"pith_short_12","alias_value":"LOOU4GYZD4TQ","created_at":"2026-07-05T11:30:13Z"},{"alias_kind":"pith_short_16","alias_value":"LOOU4GYZD4TQVS34","created_at":"2026-07-05T11:30:13Z"},{"alias_kind":"pith_short_8","alias_value":"LOOU4GYZ","created_at":"2026-07-05T11:30:13Z"}],"graph_snapshots":[{"event_id":"sha256:7fd6a6f8556fc0dded22709af9c1436a9bde7efff082cc00da3f97a96ee293f9","target":"graph","created_at":"2026-07-05T11:30:13Z","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/2507.00707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-view image generation in autonomous driving demands consistent 3D scene understanding across camera views. Most existing methods treat this problem as a 2D image set generation task, lacking explicit 3D modeling. However, we argue that a structured representation is crucial for scene generation, especially for autonomous driving applications. This paper proposes BEV-VAE for consistent and controllable view synthesis. BEV-VAE first trains a multi-view image variational autoencoder for a compact and unified BEV latent space and then generates the scene with a latent diffusion transformer. ","authors_text":"Hang Zhao, Zeming Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T12:10:11Z","title":"BEV-VAE: Multi-view Image Generation with Spatial Consistency for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00707","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:c883a841fed9306a06219180fa2c5022a862bf692ad279bac510a210c81ef3f5","target":"record","created_at":"2026-07-05T11:30:13Z","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":"0f7ae19b8d0c7099e0e213a9582b9fcc0740d7d7f1caddaf86fe5eb935a7ccc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T12:10:11Z","title_canon_sha256":"5f70614c09966d4c70fb6919d4982cdee0457d089fbcf2777681e7cba3b221c4"},"schema_version":"1.0","source":{"id":"2507.00707","kind":"arxiv","version":1}},"canonical_sha256":"5b9d4e1b191f270acb7c3c87ba9b50378bf44c38c3e22051bc74d3f70c3d95d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b9d4e1b191f270acb7c3c87ba9b50378bf44c38c3e22051bc74d3f70c3d95d6","first_computed_at":"2026-07-05T11:30:13.303423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:13.303423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9JkqMSyS6Ev2gcNTOBt1+I2eFm5i3QWCOZU2oi6WJy5nlvz5OZqLN+M7KbA1riyGQ1Xo6aP+sp8EmXDe7/MBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:13.303911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c883a841fed9306a06219180fa2c5022a862bf692ad279bac510a210c81ef3f5","sha256:7fd6a6f8556fc0dded22709af9c1436a9bde7efff082cc00da3f97a96ee293f9"],"state_sha256":"3573ae3c2eb4b8ec820d430f4a11f16bf1210c139914f84118dfc1adc0bfb03e"}