{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IJ4NVZY5VTJV334FJIC5AG2R7B","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":"aee7b2c1d16961debd72461780145ab1ede255f8843d4d65ae5dfecf46519609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T13:15:07Z","title_canon_sha256":"1aafb988941c2fa9e05a25b2e00079de1f750a7e274f31a494799be5b9e5f3ae"},"schema_version":"1.0","source":{"id":"2405.04299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04299","created_at":"2026-07-05T08:43:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04299v2","created_at":"2026-07-05T08:43:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04299","created_at":"2026-07-05T08:43:10Z"},{"alias_kind":"pith_short_12","alias_value":"IJ4NVZY5VTJV","created_at":"2026-07-05T08:43:10Z"},{"alias_kind":"pith_short_16","alias_value":"IJ4NVZY5VTJV334F","created_at":"2026-07-05T08:43:10Z"},{"alias_kind":"pith_short_8","alias_value":"IJ4NVZY5","created_at":"2026-07-05T08:43:10Z"}],"graph_snapshots":[{"event_id":"sha256:63bd07931ca07ea401a9c2375b2416c1bc17922d5a53225015e5228443126902","target":"graph","created_at":"2026-07-05T08:43:10Z","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/2405.04299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D occupancy, an advanced perception technology for driving scenarios, represents the entire scene without distinguishing between foreground and background by quantifying the physical space into a grid map. The widely adopted projection-first deformable attention, efficient in transforming image features into 3D representations, encounters challenges in aggregating multi-view features due to sensor deployment constraints. To address this issue, we propose our learning-first view attention mechanism for effective multi-view feature aggregation. Moreover, we showcase the scalability of our view ","authors_text":"Chonghua Zhou, Dan Zhang, Jinke Li, Xiao He, Xiaoqiang Cheng, Yang Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T13:15:07Z","title":"ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04299","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":"sha256:0e9d5a0ce55462f6c10e52ec56ea81c6c974602f139a9ad19e610149307f994a","target":"record","created_at":"2026-07-05T08:43:10Z","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":"aee7b2c1d16961debd72461780145ab1ede255f8843d4d65ae5dfecf46519609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-07T13:15:07Z","title_canon_sha256":"1aafb988941c2fa9e05a25b2e00079de1f750a7e274f31a494799be5b9e5f3ae"},"schema_version":"1.0","source":{"id":"2405.04299","kind":"arxiv","version":2}},"canonical_sha256":"4278dae71dacd35def854a05d01b51f8617385791c11bc7969acf1dd1ddf17a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4278dae71dacd35def854a05d01b51f8617385791c11bc7969acf1dd1ddf17a6","first_computed_at":"2026-07-05T08:43:10.082541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:10.082541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bS2qmZC+QKDgsfZYXBJlqdMCa0elfEoJrVx/6wwlGlgCKP0ENV16pFzthfcQwq0ewwHEffQ56DzauGfRLCwdDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:10.082998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e9d5a0ce55462f6c10e52ec56ea81c6c974602f139a9ad19e610149307f994a","sha256:63bd07931ca07ea401a9c2375b2416c1bc17922d5a53225015e5228443126902"],"state_sha256":"77b3039030e78169347b9fb5c487f447983c213712275f53ef4f4886aa2942c8"}