{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VDZXNLTAW7MSCSOQ4LX54RJC7K","short_pith_number":"pith:VDZXNLTA","schema_version":"1.0","canonical_sha256":"a8f376ae60b7d92149d0e2efde4522faaa1738943f6a673ed045e8ecb1acf433","source":{"kind":"arxiv","id":"2407.12294","version":1},"attestation_state":"computed","paper":{"title":"VEON: Vocabulary-Enhanced Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailan Feng, Chao Ma, Guoqing Wang, Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang","submitted_at":"2024-07-17T03:26:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.12294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T03:26:50Z","cross_cats_sorted":[],"title_canon_sha256":"a94b23bf7b90f85c6d31b68dab1da875deea65024ebc24a711633585f544ab1e","abstract_canon_sha256":"575773374096d338f53d10356c257572448e48d8cb18b8755ff205801fdc3a44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:02.597360Z","signature_b64":"QVxMW2dHtWt0xH6yRNPeGJNriC7051vtRXfg7sF4ckIrSJqouKNdt5fBeOUds4SQFF1y3ndgk3wk2eXQiazeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8f376ae60b7d92149d0e2efde4522faaa1738943f6a673ed045e8ecb1acf433","last_reissued_at":"2026-07-05T08:45:02.596874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:02.596874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VEON: Vocabulary-Enhanced Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailan Feng, Chao Ma, Guoqing Wang, Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang","submitted_at":"2024-07-17T03:26:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12294","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.12294/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.12294","created_at":"2026-07-05T08:45:02.596929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12294v1","created_at":"2026-07-05T08:45:02.596929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12294","created_at":"2026-07-05T08:45:02.596929+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDZXNLTAW7MS","created_at":"2026-07-05T08:45:02.596929+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDZXNLTAW7MSCSOQ","created_at":"2026-07-05T08:45:02.596929+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDZXNLTA","created_at":"2026-07-05T08:45:02.596929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K","json":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K.json","graph_json":"https://pith.science/api/pith-number/VDZXNLTAW7MSCSOQ4LX54RJC7K/graph.json","events_json":"https://pith.science/api/pith-number/VDZXNLTAW7MSCSOQ4LX54RJC7K/events.json","paper":"https://pith.science/paper/VDZXNLTA"},"agent_actions":{"view_html":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K","download_json":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K.json","view_paper":"https://pith.science/paper/VDZXNLTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12294&json=true","fetch_graph":"https://pith.science/api/pith-number/VDZXNLTAW7MSCSOQ4LX54RJC7K/graph.json","fetch_events":"https://pith.science/api/pith-number/VDZXNLTAW7MSCSOQ4LX54RJC7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K/action/storage_attestation","attest_author":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K/action/author_attestation","sign_citation":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K/action/citation_signature","submit_replication":"https://pith.science/pith/VDZXNLTAW7MSCSOQ4LX54RJC7K/action/replication_record"}},"created_at":"2026-07-05T08:45:02.596929+00:00","updated_at":"2026-07-05T08:45:02.596929+00:00"}