{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SB245TIPCV2U52KA2AEDQWNKL2","short_pith_number":"pith:SB245TIP","schema_version":"1.0","canonical_sha256":"9075cecd0f15754ee940d0083859aa5ea6cf11d34e395467b43b454ff831f7ff","source":{"kind":"arxiv","id":"2309.10527","version":4},"attestation_state":"computed","paper":{"title":"SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Hongbin Zhou, Jiakang Yuan, Junchi Yan, Ping Luo, Renqiu Xia, Runjian Chen, Tao Chen, Wenqi Shao, Xiangchao Yan, Xinyu Cai, Yu Qiao","submitted_at":"2023-09-19T11:13:01Z","abstract_excerpt":"Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. In this paper, we propose SPOT, namely Scalable Pre-training via Occupancy prediction for learning Transferable 3D representations under such a label-efficient fine-tuning paradigm. SPOT achieves effectiveness on various public datasets with different downstream tasks, showca"},"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":"2309.10527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T11:13:01Z","cross_cats_sorted":[],"title_canon_sha256":"a1775aa7a0ea16a8765b963c4e9120410691ff3d058fc7352b28a1b95832a503","abstract_canon_sha256":"170762905e2edf211aacc0df7e29f48842b7bec31900812c5fefc1923b37786c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:59.125256Z","signature_b64":"fDZgzSNXKwLUEEfHMSD6GamXc1SO3pjBZXnOp2Ng5O9DiAzEIiXrNEV1p06B4Fgv5dL23BzgqisoOg5Rl0OlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9075cecd0f15754ee940d0083859aa5ea6cf11d34e395467b43b454ff831f7ff","last_reissued_at":"2026-07-05T11:37:59.124751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:59.124751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botian Shi, Bo Zhang, Hancheng Ye, Hongbin Zhou, Jiakang Yuan, Junchi Yan, Ping Luo, Renqiu Xia, Runjian Chen, Tao Chen, Wenqi Shao, Xiangchao Yan, Xinyu Cai, Yu Qiao","submitted_at":"2023-09-19T11:13:01Z","abstract_excerpt":"Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g., autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. In this paper, we propose SPOT, namely Scalable Pre-training via Occupancy prediction for learning Transferable 3D representations under such a label-efficient fine-tuning paradigm. SPOT achieves effectiveness on various public datasets with different downstream tasks, showca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10527","kind":"arxiv","version":4},"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/2309.10527/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":"2309.10527","created_at":"2026-07-05T11:37:59.124810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10527v4","created_at":"2026-07-05T11:37:59.124810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10527","created_at":"2026-07-05T11:37:59.124810+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB245TIPCV2U","created_at":"2026-07-05T11:37:59.124810+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB245TIPCV2U52KA","created_at":"2026-07-05T11:37:59.124810+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB245TIP","created_at":"2026-07-05T11:37:59.124810+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/SB245TIPCV2U52KA2AEDQWNKL2","json":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2.json","graph_json":"https://pith.science/api/pith-number/SB245TIPCV2U52KA2AEDQWNKL2/graph.json","events_json":"https://pith.science/api/pith-number/SB245TIPCV2U52KA2AEDQWNKL2/events.json","paper":"https://pith.science/paper/SB245TIP"},"agent_actions":{"view_html":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2","download_json":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2.json","view_paper":"https://pith.science/paper/SB245TIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10527&json=true","fetch_graph":"https://pith.science/api/pith-number/SB245TIPCV2U52KA2AEDQWNKL2/graph.json","fetch_events":"https://pith.science/api/pith-number/SB245TIPCV2U52KA2AEDQWNKL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2/action/storage_attestation","attest_author":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2/action/author_attestation","sign_citation":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2/action/citation_signature","submit_replication":"https://pith.science/pith/SB245TIPCV2U52KA2AEDQWNKL2/action/replication_record"}},"created_at":"2026-07-05T11:37:59.124810+00:00","updated_at":"2026-07-05T11:37:59.124810+00:00"}