{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:POQMHWUAP44BN37OIOEKAHHS2L","short_pith_number":"pith:POQMHWUA","schema_version":"1.0","canonical_sha256":"7ba0c3da807f3816efee4388a01cf2d2ec08c40e7f8420fe6ff58c99ad32cef5","source":{"kind":"arxiv","id":"2501.04004","version":2},"attestation_state":"computed","paper":{"title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hui Shuai, Liang Pan, Lingdong Kong, Qingshan Liu, Xiang Xu, Ziwei Liu","submitted_at":"2025-01-07T18:59:58Z","abstract_excerpt":"LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focus on sparse voxel representation, overlooking the complementary attributes provided by other LiDAR representations. In this work, we propose LiMoE, a framework that integrates the Mixture of Experts (MoE) paradigm into LiDAR data representation learning to synergistically combine multiple representations, such as range images, sparse voxels, and raw points. Our approach consists of three stages: i) Image-to-LiDAR Pre"},"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":"2501.04004","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T18:59:58Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"4f1023107dfb99531616205f24a15b6d091c5cf7ee940078cdd250bf8a68cd83","abstract_canon_sha256":"a0f5a0a5f133ba0c8ec00a030b214eaf3d0523181a6f1555c250bbc546b2f6c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:44.388083Z","signature_b64":"TwFsxrXTw7RRnzVbfFWTqRRELfjuabYHxM0D9szMgidf0Vsew1d/ntvEZIkkPjXKTh10o1kjqjmfKa0toBGADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba0c3da807f3816efee4388a01cf2d2ec08c40e7f8420fe6ff58c99ad32cef5","last_reissued_at":"2026-07-05T10:35:44.386662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:44.386662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hui Shuai, Liang Pan, Lingdong Kong, Qingshan Liu, Xiang Xu, Ziwei Liu","submitted_at":"2025-01-07T18:59:58Z","abstract_excerpt":"LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focus on sparse voxel representation, overlooking the complementary attributes provided by other LiDAR representations. In this work, we propose LiMoE, a framework that integrates the Mixture of Experts (MoE) paradigm into LiDAR data representation learning to synergistically combine multiple representations, such as range images, sparse voxels, and raw points. Our approach consists of three stages: i) Image-to-LiDAR Pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04004","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/2501.04004/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":"2501.04004","created_at":"2026-07-05T10:35:44.387471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04004v2","created_at":"2026-07-05T10:35:44.387471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04004","created_at":"2026-07-05T10:35:44.387471+00:00"},{"alias_kind":"pith_short_12","alias_value":"POQMHWUAP44B","created_at":"2026-07-05T10:35:44.387471+00:00"},{"alias_kind":"pith_short_16","alias_value":"POQMHWUAP44BN37O","created_at":"2026-07-05T10:35:44.387471+00:00"},{"alias_kind":"pith_short_8","alias_value":"POQMHWUA","created_at":"2026-07-05T10:35:44.387471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18105","citing_title":"OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13761","citing_title":"Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L","json":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L.json","graph_json":"https://pith.science/api/pith-number/POQMHWUAP44BN37OIOEKAHHS2L/graph.json","events_json":"https://pith.science/api/pith-number/POQMHWUAP44BN37OIOEKAHHS2L/events.json","paper":"https://pith.science/paper/POQMHWUA"},"agent_actions":{"view_html":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L","download_json":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L.json","view_paper":"https://pith.science/paper/POQMHWUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04004&json=true","fetch_graph":"https://pith.science/api/pith-number/POQMHWUAP44BN37OIOEKAHHS2L/graph.json","fetch_events":"https://pith.science/api/pith-number/POQMHWUAP44BN37OIOEKAHHS2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L/action/storage_attestation","attest_author":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L/action/author_attestation","sign_citation":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L/action/citation_signature","submit_replication":"https://pith.science/pith/POQMHWUAP44BN37OIOEKAHHS2L/action/replication_record"}},"created_at":"2026-07-05T10:35:44.387471+00:00","updated_at":"2026-07-05T10:35:44.387471+00:00"}