{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LTUR6WFGOVE7YTX663UX32GGL3","short_pith_number":"pith:LTUR6WFG","schema_version":"1.0","canonical_sha256":"5ce91f58a67549fc4efef6e97de8c65edd22ae867f7662921ffb821fd069b4c3","source":{"kind":"arxiv","id":"2206.09900","version":7},"attestation_state":"computed","paper":{"title":"Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Dai, Chen Min, Dawei Zhao, Liang Xiao, Xinli Xu, Yiming Nie","submitted_at":"2022-06-20T17:15:50Z","abstract_excerpt":"Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifi"},"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":"2206.09900","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-20T17:15:50Z","cross_cats_sorted":[],"title_canon_sha256":"6ae39b9b4f967c720cf7901f88267d8ca147049beb86a99143cdc4dc4077031d","abstract_canon_sha256":"7641f613df03467c056fe6326f82b37cc86d56c9ee7c0847ff85eb194f8b1be6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:35.918425Z","signature_b64":"L48rqZvS77n+5yZOlpLzA4dVW2qH//cb+lOaKX46A4TZP2XZ08+C+JZg/9snyIckS6j+ufYNAT6AsyUSSpKMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ce91f58a67549fc4efef6e97de8c65edd22ae867f7662921ffb821fd069b4c3","last_reissued_at":"2026-07-05T06:58:35.917955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:35.917955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Dai, Chen Min, Dawei Zhao, Liang Xiao, Xinli Xu, Yiming Nie","submitted_at":"2022-06-20T17:15:50Z","abstract_excerpt":"Current perception models in autonomous driving heavily rely on large-scale labelled 3D data, which is both costly and time-consuming to annotate. This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE). While existing masked point autoencoding methods mainly focus on small-scale indoor point clouds or pillar-based large-scale outdoor LiDAR data, our approach introduces a new self-supervised masked occupancy pre-training method called Occupancy-MAE, specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09900","kind":"arxiv","version":7},"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/2206.09900/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":"2206.09900","created_at":"2026-07-05T06:58:35.918012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09900v7","created_at":"2026-07-05T06:58:35.918012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09900","created_at":"2026-07-05T06:58:35.918012+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTUR6WFGOVE7","created_at":"2026-07-05T06:58:35.918012+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTUR6WFGOVE7YTX6","created_at":"2026-07-05T06:58:35.918012+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTUR6WFG","created_at":"2026-07-05T06:58:35.918012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31570","citing_title":"Mitigating Positional Leakage in 3D Masked Autoencoders for Robust Representation Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3","json":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3.json","graph_json":"https://pith.science/api/pith-number/LTUR6WFGOVE7YTX663UX32GGL3/graph.json","events_json":"https://pith.science/api/pith-number/LTUR6WFGOVE7YTX663UX32GGL3/events.json","paper":"https://pith.science/paper/LTUR6WFG"},"agent_actions":{"view_html":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3","download_json":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3.json","view_paper":"https://pith.science/paper/LTUR6WFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09900&json=true","fetch_graph":"https://pith.science/api/pith-number/LTUR6WFGOVE7YTX663UX32GGL3/graph.json","fetch_events":"https://pith.science/api/pith-number/LTUR6WFGOVE7YTX663UX32GGL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3/action/storage_attestation","attest_author":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3/action/author_attestation","sign_citation":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3/action/citation_signature","submit_replication":"https://pith.science/pith/LTUR6WFGOVE7YTX663UX32GGL3/action/replication_record"}},"created_at":"2026-07-05T06:58:35.918012+00:00","updated_at":"2026-07-05T06:58:35.918012+00:00"}