{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XM2BH53IKPXFOKMSVEKYEHQJPL","short_pith_number":"pith:XM2BH53I","schema_version":"1.0","canonical_sha256":"bb3413f76853ee572992a915821e097ae76a727c2e923467d26f465546671376","source":{"kind":"arxiv","id":"2508.10935","version":2},"attestation_state":"computed","paper":{"title":"HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongsong Wang, Lei He, Qi Liu, Yabei Li","submitted_at":"2025-08-12T18:57:18Z","abstract_excerpt":"Traditional closed-set 3D detection frameworks fail to meet the demands of open-world applications like autonomous driving. Existing open-vocabulary 3D detection methods typically adopt a two-stage pipeline consisting of pseudo-label generation followed by semantic alignment. While vision-language models (VLMs) recently have dramatically improved the semantic accuracy of pseudo-labels, their geometric quality, particularly bounding box precision, remains commonly neglected. To address this issue, we propose a High Box Quality Open-Vocabulary 3D Detection (HQ-OV3D) framework, dedicated to gener"},"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":"2508.10935","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T18:57:18Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"f9f4aa91babaae2eb32f40cbb2c274d63820baefdc8b8102d27791e76021fcee","abstract_canon_sha256":"e62e83e8a4be60cadb5e3372d16f8c74ccd83d2a29ebbc120085b4d867fb6f70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:22.377933Z","signature_b64":"LZmxyi/QynwWwMID3+vjahpBkEjEMESqecKrf5R/tGQE8Az7xoAqmXOR0Ap/oWuShygR+A77jyZgDaDCbG1lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3413f76853ee572992a915821e097ae76a727c2e923467d26f465546671376","last_reissued_at":"2026-07-05T11:55:22.377370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:22.377370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HQ-OV3D: A High Box Quality Open-World 3D Detection Framework based on Diffision Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongsong Wang, Lei He, Qi Liu, Yabei Li","submitted_at":"2025-08-12T18:57:18Z","abstract_excerpt":"Traditional closed-set 3D detection frameworks fail to meet the demands of open-world applications like autonomous driving. Existing open-vocabulary 3D detection methods typically adopt a two-stage pipeline consisting of pseudo-label generation followed by semantic alignment. While vision-language models (VLMs) recently have dramatically improved the semantic accuracy of pseudo-labels, their geometric quality, particularly bounding box precision, remains commonly neglected. To address this issue, we propose a High Box Quality Open-Vocabulary 3D Detection (HQ-OV3D) framework, dedicated to gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10935","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/2508.10935/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":"2508.10935","created_at":"2026-07-05T11:55:22.377447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10935v2","created_at":"2026-07-05T11:55:22.377447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10935","created_at":"2026-07-05T11:55:22.377447+00:00"},{"alias_kind":"pith_short_12","alias_value":"XM2BH53IKPXF","created_at":"2026-07-05T11:55:22.377447+00:00"},{"alias_kind":"pith_short_16","alias_value":"XM2BH53IKPXFOKMS","created_at":"2026-07-05T11:55:22.377447+00:00"},{"alias_kind":"pith_short_8","alias_value":"XM2BH53I","created_at":"2026-07-05T11:55:22.377447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL","json":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL.json","graph_json":"https://pith.science/api/pith-number/XM2BH53IKPXFOKMSVEKYEHQJPL/graph.json","events_json":"https://pith.science/api/pith-number/XM2BH53IKPXFOKMSVEKYEHQJPL/events.json","paper":"https://pith.science/paper/XM2BH53I"},"agent_actions":{"view_html":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL","download_json":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL.json","view_paper":"https://pith.science/paper/XM2BH53I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10935&json=true","fetch_graph":"https://pith.science/api/pith-number/XM2BH53IKPXFOKMSVEKYEHQJPL/graph.json","fetch_events":"https://pith.science/api/pith-number/XM2BH53IKPXFOKMSVEKYEHQJPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL/action/storage_attestation","attest_author":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL/action/author_attestation","sign_citation":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL/action/citation_signature","submit_replication":"https://pith.science/pith/XM2BH53IKPXFOKMSVEKYEHQJPL/action/replication_record"}},"created_at":"2026-07-05T11:55:22.377447+00:00","updated_at":"2026-07-05T11:55:22.377447+00:00"}