{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6H6T7PMGMJ4VUDCNQOYN3QFS7Z","short_pith_number":"pith:6H6T7PMG","schema_version":"1.0","canonical_sha256":"f1fd3fbd8662795a0c4d83b0ddc0b2fe6d548b98827ec473d067f2e99c28c3dd","source":{"kind":"arxiv","id":"2411.16072","version":3},"attestation_state":"computed","paper":{"title":"Language Driven Occupancy Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Pang, Hui-Liang Shen, Lizhe Liu, Maochun Luo, Mingxia Chen, Qiang Li, Runmin Zhang, Sheng Yang, Si-Yuan Cao, Zhu Yu","submitted_at":"2024-11-25T03:47:10Z","abstract_excerpt":"We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as intermediates or noisy and sparse correspondences from voxel-based model-view projections. To alleviate the inaccurate supervision, we propose a semantic transitive labeling pipeline to generate dense and fine-grained 3D language occupancy ground truth. Our pipeline presents a feasible way to dig into the valuable semantic information of images, transferring text labels"},"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":"2411.16072","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T03:47:10Z","cross_cats_sorted":[],"title_canon_sha256":"60c32f5d8e5b68008dee3a14570771b7750c5eb2c0bedf0a099e115de2401584","abstract_canon_sha256":"2d503d585d75881a2a52488c9bc84fc6f704975788e1b9be7002fe0e2fe4d772"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:30.014837Z","signature_b64":"NEqe3E6en3u09fWbkxf/2WHVmcuuBkZyZ85xGgZkHsZYiNu/TQMiR5hG0beI3DBtj/tH3D8FO0E2eZ7vYD4jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1fd3fbd8662795a0c4d83b0ddc0b2fe6d548b98827ec473d067f2e99c28c3dd","last_reissued_at":"2026-07-05T11:45:30.014295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:30.014295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Driven Occupancy Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Pang, Hui-Liang Shen, Lizhe Liu, Maochun Luo, Mingxia Chen, Qiang Li, Runmin Zhang, Sheng Yang, Si-Yuan Cao, Zhu Yu","submitted_at":"2024-11-25T03:47:10Z","abstract_excerpt":"We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as intermediates or noisy and sparse correspondences from voxel-based model-view projections. To alleviate the inaccurate supervision, we propose a semantic transitive labeling pipeline to generate dense and fine-grained 3D language occupancy ground truth. Our pipeline presents a feasible way to dig into the valuable semantic information of images, transferring text labels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16072","kind":"arxiv","version":3},"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/2411.16072/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":"2411.16072","created_at":"2026-07-05T11:45:30.014365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16072v3","created_at":"2026-07-05T11:45:30.014365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16072","created_at":"2026-07-05T11:45:30.014365+00:00"},{"alias_kind":"pith_short_12","alias_value":"6H6T7PMGMJ4V","created_at":"2026-07-05T11:45:30.014365+00:00"},{"alias_kind":"pith_short_16","alias_value":"6H6T7PMGMJ4VUDCN","created_at":"2026-07-05T11:45:30.014365+00:00"},{"alias_kind":"pith_short_8","alias_value":"6H6T7PMG","created_at":"2026-07-05T11:45:30.014365+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":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z","json":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z.json","graph_json":"https://pith.science/api/pith-number/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/graph.json","events_json":"https://pith.science/api/pith-number/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/events.json","paper":"https://pith.science/paper/6H6T7PMG"},"agent_actions":{"view_html":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z","download_json":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z.json","view_paper":"https://pith.science/paper/6H6T7PMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16072&json=true","fetch_graph":"https://pith.science/api/pith-number/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/action/storage_attestation","attest_author":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/action/author_attestation","sign_citation":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/action/citation_signature","submit_replication":"https://pith.science/pith/6H6T7PMGMJ4VUDCNQOYN3QFS7Z/action/replication_record"}},"created_at":"2026-07-05T11:45:30.014365+00:00","updated_at":"2026-07-05T11:45:30.014365+00:00"}