{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TIK27IKJH3X3Z2ZRSS4SF2IKHA","short_pith_number":"pith:TIK27IKJ","schema_version":"1.0","canonical_sha256":"9a15afa1493eefbceb3194b922e90a38257045f2a74bc59f8ea68de0cbb9b547","source":{"kind":"arxiv","id":"2305.16133","version":2},"attestation_state":"computed","paper":{"title":"OVO: Open-Vocabulary Occupancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Hang Ji, Hao Li, Weikun Zhang, Zhiyu Tan, Zichao Dong","submitted_at":"2023-05-25T15:07:25Z","abstract_excerpt":"Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the "},"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":"2305.16133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T15:07:25Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"2d84000157e8badb3af7bd286d6e3b044ace259197b789a886d7ff12e123caad","abstract_canon_sha256":"027b169f2c4726472c5eca21b42a06d619616e6ca95347e480bb7bfdac91334d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:44.274296Z","signature_b64":"qLAzdtwUJ1SRMUhiUiBNdY4XAKe/07AUVNkmueXgKxEm9izyiinR+UQWNGBYSTWMZqihxIIFPlnmBdF+a/OvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a15afa1493eefbceb3194b922e90a38257045f2a74bc59f8ea68de0cbb9b547","last_reissued_at":"2026-07-05T06:20:44.273738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:44.273738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OVO: Open-Vocabulary Occupancy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Cheng Zhang, Hang Ji, Hao Li, Weikun Zhang, Zhiyu Tan, Zichao Dong","submitted_at":"2023-05-25T15:07:25Z","abstract_excerpt":"Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16133","kind":"arxiv","version":2},"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/2305.16133/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":"2305.16133","created_at":"2026-07-05T06:20:44.273816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16133v2","created_at":"2026-07-05T06:20:44.273816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16133","created_at":"2026-07-05T06:20:44.273816+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIK27IKJH3X3","created_at":"2026-07-05T06:20:44.273816+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIK27IKJH3X3Z2ZR","created_at":"2026-07-05T06:20:44.273816+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIK27IKJ","created_at":"2026-07-05T06:20:44.273816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":27,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03370","citing_title":"ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA","json":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA.json","graph_json":"https://pith.science/api/pith-number/TIK27IKJH3X3Z2ZRSS4SF2IKHA/graph.json","events_json":"https://pith.science/api/pith-number/TIK27IKJH3X3Z2ZRSS4SF2IKHA/events.json","paper":"https://pith.science/paper/TIK27IKJ"},"agent_actions":{"view_html":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA","download_json":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA.json","view_paper":"https://pith.science/paper/TIK27IKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16133&json=true","fetch_graph":"https://pith.science/api/pith-number/TIK27IKJH3X3Z2ZRSS4SF2IKHA/graph.json","fetch_events":"https://pith.science/api/pith-number/TIK27IKJH3X3Z2ZRSS4SF2IKHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA/action/storage_attestation","attest_author":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA/action/author_attestation","sign_citation":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA/action/citation_signature","submit_replication":"https://pith.science/pith/TIK27IKJH3X3Z2ZRSS4SF2IKHA/action/replication_record"}},"created_at":"2026-07-05T06:20:44.273816+00:00","updated_at":"2026-07-05T06:20:44.273816+00:00"}