{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:27QY4M5UMCGF7DPV3PCWDXQRWC","short_pith_number":"pith:27QY4M5U","schema_version":"1.0","canonical_sha256":"d7e18e33b4608c5f8df5dbc561de11b08c2cc62f5fef691178db894abde24527","source":{"kind":"arxiv","id":"2504.12709","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Li, Jianmin Ji, Jie Peng, Lehan Pan, Lidian Wang, Sha Zhang, Shumin Wang, Yanyong Zhang, Zhipeng Tang, Zhuoran Yang","submitted_at":"2025-04-17T07:26:11Z","abstract_excerpt":"The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this goal, this paper proposes to utilize massive unlabeled data from heterogeneous datasets to pre-train 3D perception models. We introduce a self-supervised pre-training framework that learns effective 3D representations from scratch on unlabeled data, combined with a prompt adapter based domain adaptation strategy to reduce dataset bias. The approach significant"},"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":"2504.12709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-17T07:26:11Z","cross_cats_sorted":[],"title_canon_sha256":"6013f73e1d5f8d2eb81587f01a1177185a163d95145c9ea6cf0659f089473a54","abstract_canon_sha256":"ee7c4c689a14c1fd9a360ad60a9c2296ffb760e6519061b3d4b0d5b50770790e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:21.095503Z","signature_b64":"xZt9S2ExJOslV0piaQJfCFJQoWbIGkaviQ1Ggb/XX+0l3LsIA8zvTDlkF759Zsl1MTHhHhIh8lFmBmBW+yBdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7e18e33b4608c5f8df5dbc561de11b08c2cc62f5fef691178db894abde24527","last_reissued_at":"2026-07-05T10:50:21.094719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:21.094719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Pre-training with Combined Datasets for 3D Perception in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Li, Jianmin Ji, Jie Peng, Lehan Pan, Lidian Wang, Sha Zhang, Shumin Wang, Yanyong Zhang, Zhipeng Tang, Zhuoran Yang","submitted_at":"2025-04-17T07:26:11Z","abstract_excerpt":"The significant achievements of pre-trained models leveraging large volumes of data in the field of NLP and 2D vision inspire us to explore the potential of extensive data pre-training for 3D perception in autonomous driving. Toward this goal, this paper proposes to utilize massive unlabeled data from heterogeneous datasets to pre-train 3D perception models. We introduce a self-supervised pre-training framework that learns effective 3D representations from scratch on unlabeled data, combined with a prompt adapter based domain adaptation strategy to reduce dataset bias. The approach significant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12709","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/2504.12709/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":"2504.12709","created_at":"2026-07-05T10:50:21.094785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12709v1","created_at":"2026-07-05T10:50:21.094785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12709","created_at":"2026-07-05T10:50:21.094785+00:00"},{"alias_kind":"pith_short_12","alias_value":"27QY4M5UMCGF","created_at":"2026-07-05T10:50:21.094785+00:00"},{"alias_kind":"pith_short_16","alias_value":"27QY4M5UMCGF7DPV","created_at":"2026-07-05T10:50:21.094785+00:00"},{"alias_kind":"pith_short_8","alias_value":"27QY4M5U","created_at":"2026-07-05T10:50:21.094785+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/27QY4M5UMCGF7DPV3PCWDXQRWC","json":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC.json","graph_json":"https://pith.science/api/pith-number/27QY4M5UMCGF7DPV3PCWDXQRWC/graph.json","events_json":"https://pith.science/api/pith-number/27QY4M5UMCGF7DPV3PCWDXQRWC/events.json","paper":"https://pith.science/paper/27QY4M5U"},"agent_actions":{"view_html":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC","download_json":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC.json","view_paper":"https://pith.science/paper/27QY4M5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12709&json=true","fetch_graph":"https://pith.science/api/pith-number/27QY4M5UMCGF7DPV3PCWDXQRWC/graph.json","fetch_events":"https://pith.science/api/pith-number/27QY4M5UMCGF7DPV3PCWDXQRWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC/action/storage_attestation","attest_author":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC/action/author_attestation","sign_citation":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC/action/citation_signature","submit_replication":"https://pith.science/pith/27QY4M5UMCGF7DPV3PCWDXQRWC/action/replication_record"}},"created_at":"2026-07-05T10:50:21.094785+00:00","updated_at":"2026-07-05T10:50:21.094785+00:00"}