{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VJSQPVZWJLFMZPBOSMFZXHXRT5","short_pith_number":"pith:VJSQPVZW","schema_version":"1.0","canonical_sha256":"aa6507d7364acaccbc2e930b9b9ef19f7da40e8bde57a4fdf0b09ba3bb53324e","source":{"kind":"arxiv","id":"2310.15670","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chonghao Sima, Hongyang Li, Jingdong Wang, Linyan Huang, Wenhai Wang, Yu Qiao, Zhiqi Li","submitted_at":"2023-10-24T09:29:26Z","abstract_excerpt":"Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain gap between LiDAR and camera features, coupled with the inherent incompatibility in temporal fusion, significantly hinders the effectiveness of distillation-based enhancements for apprentices. Motivated by the success of uni-modal distillation, an apprentice-friendly expert model would predominantly rely on camera features, while still achieving comparable p"},"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":"2310.15670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-24T09:29:26Z","cross_cats_sorted":[],"title_canon_sha256":"ddc7926385bcade173dc5439c16aec24071d3586324fd940e9d1f623151ba9ae","abstract_canon_sha256":"bd9a253e8aa41c0a77a509065192bac49eaabc21480225d41d29c1ffe922c565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:29.352393Z","signature_b64":"BPsn9zJ2A5tWowOXfW+POjqSxN4dX6xDdL4riIAqc6RtviTu0Xit0mTgvyA8VjRnM95fhTiFwlXqtqFloFWyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa6507d7364acaccbc2e930b9b9ef19f7da40e8bde57a4fdf0b09ba3bb53324e","last_reissued_at":"2026-07-05T07:04:29.351983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:29.351983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chonghao Sima, Hongyang Li, Jingdong Wang, Linyan Huang, Wenhai Wang, Yu Qiao, Zhiqi Li","submitted_at":"2023-10-24T09:29:26Z","abstract_excerpt":"Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain gap between LiDAR and camera features, coupled with the inherent incompatibility in temporal fusion, significantly hinders the effectiveness of distillation-based enhancements for apprentices. Motivated by the success of uni-modal distillation, an apprentice-friendly expert model would predominantly rely on camera features, while still achieving comparable p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15670","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/2310.15670/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":"2310.15670","created_at":"2026-07-05T07:04:29.352041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15670v1","created_at":"2026-07-05T07:04:29.352041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15670","created_at":"2026-07-05T07:04:29.352041+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJSQPVZWJLFM","created_at":"2026-07-05T07:04:29.352041+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJSQPVZWJLFMZPBO","created_at":"2026-07-05T07:04:29.352041+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJSQPVZW","created_at":"2026-07-05T07:04:29.352041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20911","citing_title":"TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5","json":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5.json","graph_json":"https://pith.science/api/pith-number/VJSQPVZWJLFMZPBOSMFZXHXRT5/graph.json","events_json":"https://pith.science/api/pith-number/VJSQPVZWJLFMZPBOSMFZXHXRT5/events.json","paper":"https://pith.science/paper/VJSQPVZW"},"agent_actions":{"view_html":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5","download_json":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5.json","view_paper":"https://pith.science/paper/VJSQPVZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15670&json=true","fetch_graph":"https://pith.science/api/pith-number/VJSQPVZWJLFMZPBOSMFZXHXRT5/graph.json","fetch_events":"https://pith.science/api/pith-number/VJSQPVZWJLFMZPBOSMFZXHXRT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5/action/storage_attestation","attest_author":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5/action/author_attestation","sign_citation":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5/action/citation_signature","submit_replication":"https://pith.science/pith/VJSQPVZWJLFMZPBOSMFZXHXRT5/action/replication_record"}},"created_at":"2026-07-05T07:04:29.352041+00:00","updated_at":"2026-07-05T07:04:29.352041+00:00"}