{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDZXNLTAW7MSCSOQ4LX54RJC7K","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":"575773374096d338f53d10356c257572448e48d8cb18b8755ff205801fdc3a44","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T03:26:50Z","title_canon_sha256":"a94b23bf7b90f85c6d31b68dab1da875deea65024ebc24a711633585f544ab1e"},"schema_version":"1.0","source":{"id":"2407.12294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12294","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12294v1","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12294","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"VDZXNLTAW7MS","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"VDZXNLTAW7MSCSOQ","created_at":"2026-07-05T08:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"VDZXNLTA","created_at":"2026-07-05T08:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:d18ea0e24ab4e7c946913c60b88ec9773da5cc313c4d9cd79fc2426b074aafe8","target":"graph","created_at":"2026-07-05T08:45:02Z","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/2407.12294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Perceiving the world as 3D occupancy supports embodied agents to avoid collision with any types of obstacle. While open-vocabulary image understanding has prospered recently, how to bind the predicted 3D occupancy grids with open-world semantics still remains under-explored due to limited open-world annotations. Hence, instead of building our model from scratch, we try to blend 2D foundation models, specifically a depth model MiDaS and a semantic model CLIP, to lift the semantics to 3D space, thus fulfilling 3D occupancy. However, building upon these foundation models is not trivial. First, th","authors_text":"Bailan Feng, Chao Ma, Guoqing Wang, Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T03:26:50Z","title":"VEON: Vocabulary-Enhanced Occupancy Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12294","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":"sha256:6a2fa7effe2ccc25818135e167c5877d61145826c5ee48855de9c8059cc08c65","target":"record","created_at":"2026-07-05T08:45:02Z","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":"575773374096d338f53d10356c257572448e48d8cb18b8755ff205801fdc3a44","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T03:26:50Z","title_canon_sha256":"a94b23bf7b90f85c6d31b68dab1da875deea65024ebc24a711633585f544ab1e"},"schema_version":"1.0","source":{"id":"2407.12294","kind":"arxiv","version":1}},"canonical_sha256":"a8f376ae60b7d92149d0e2efde4522faaa1738943f6a673ed045e8ecb1acf433","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8f376ae60b7d92149d0e2efde4522faaa1738943f6a673ed045e8ecb1acf433","first_computed_at":"2026-07-05T08:45:02.596874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:02.596874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QVxMW2dHtWt0xH6yRNPeGJNriC7051vtRXfg7sF4ckIrSJqouKNdt5fBeOUds4SQFF1y3ndgk3wk2eXQiazeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:02.597360Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a2fa7effe2ccc25818135e167c5877d61145826c5ee48855de9c8059cc08c65","sha256:d18ea0e24ab4e7c946913c60b88ec9773da5cc313c4d9cd79fc2426b074aafe8"],"state_sha256":"8e82223558a75cb0704339a09398cc4ae8210b0afee85684461c901813b01a05"}