{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2FCCGKKJMIBMAZTXLGFTHHX7H5","short_pith_number":"pith:2FCCGKKJ","schema_version":"1.0","canonical_sha256":"d1442329496202c06677598b339eff3f4948872c2eee8d711d1e3cdd8e22edbc","source":{"kind":"arxiv","id":"2209.09385","version":2},"attestation_state":"computed","paper":{"title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongqiangzi Ye, Hassan Foroosh, Panqu Wang, Weijia Chen, Yufei Xie, Yu Wang, Zixiang Zhou","submitted_at":"2022-09-19T23:39:15Z","abstract_excerpt":"LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the perfo"},"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":"2209.09385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T23:39:15Z","cross_cats_sorted":[],"title_canon_sha256":"bb4313242cebbea58d82b40ce17a74ba3ae787687fae42c8d24c361b19353b0c","abstract_canon_sha256":"b5291a384f60fa614604c5cba0654aa7e32a7d1d32c732c13b1846e05461292d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:33.840025Z","signature_b64":"Dfjw/80Ow57p6F93Jquj3yIAPBAm4YKrHivkGPeHG/3cHWzv1du+yZnZFnjAfDr82iBdDCv4Wa01jugJReLIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1442329496202c06677598b339eff3f4948872c2eee8d711d1e3cdd8e22edbc","last_reissued_at":"2026-07-05T05:53:33.839536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:33.839536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongqiangzi Ye, Hassan Foroosh, Panqu Wang, Weijia Chen, Yufei Xie, Yu Wang, Zixiang Zhou","submitted_at":"2022-09-19T23:39:15Z","abstract_excerpt":"LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult to adapt to each other. This paper presents LidarMultiNet, a LiDAR-based multi-task network that unifies these three major LiDAR perception tasks. Among its many benefits, a multi-task network can reduce the overall cost by sharing weights and computation among multiple tasks. However, it typically underperforms compared to independently combined single-task models. The proposed LidarMultiNet aims to bridge the perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09385","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/2209.09385/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":"2209.09385","created_at":"2026-07-05T05:53:33.839591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09385v2","created_at":"2026-07-05T05:53:33.839591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09385","created_at":"2026-07-05T05:53:33.839591+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FCCGKKJMIBM","created_at":"2026-07-05T05:53:33.839591+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FCCGKKJMIBMAZTX","created_at":"2026-07-05T05:53:33.839591+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FCCGKKJ","created_at":"2026-07-05T05:53:33.839591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10977","citing_title":"QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5","json":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5.json","graph_json":"https://pith.science/api/pith-number/2FCCGKKJMIBMAZTXLGFTHHX7H5/graph.json","events_json":"https://pith.science/api/pith-number/2FCCGKKJMIBMAZTXLGFTHHX7H5/events.json","paper":"https://pith.science/paper/2FCCGKKJ"},"agent_actions":{"view_html":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5","download_json":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5.json","view_paper":"https://pith.science/paper/2FCCGKKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09385&json=true","fetch_graph":"https://pith.science/api/pith-number/2FCCGKKJMIBMAZTXLGFTHHX7H5/graph.json","fetch_events":"https://pith.science/api/pith-number/2FCCGKKJMIBMAZTXLGFTHHX7H5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5/action/storage_attestation","attest_author":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5/action/author_attestation","sign_citation":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5/action/citation_signature","submit_replication":"https://pith.science/pith/2FCCGKKJMIBMAZTXLGFTHHX7H5/action/replication_record"}},"created_at":"2026-07-05T05:53:33.839591+00:00","updated_at":"2026-07-05T05:53:33.839591+00:00"}