{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MIT34CK2BB6MMLRLCKZLMLPCB5","short_pith_number":"pith:MIT34CK2","schema_version":"1.0","canonical_sha256":"6227be095a087cc62e2b12b2b62de20f78a1ad411e5d8350bf3e70b0025fbd6d","source":{"kind":"arxiv","id":"2605.21372","version":1},"attestation_state":"computed","paper":{"title":"Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hongzhi Ruan, Jun Ma, Kun Zhan, Pei Liu, Weiliang Ma, Xueyang Zhang, Zhengning Li","submitted_at":"2026-05-20T16:36:26Z","abstract_excerpt":"Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in te"},"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":"2605.21372","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T16:36:26Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"f29f808263e7656fb3849c758318499d8e22fe372a08a45ce5ce387211d13615","abstract_canon_sha256":"ad7956cac39c36e3a31a95b7b3e9d1097b3083888875c4a64af9bbdd7ee89e93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:31.530036Z","signature_b64":"wmDw4uSjXU6helss0y/YLkCDrPEmGW0UZhqOTbIIH2oTq/AriGyHGO9x1Vs5HqJFYeuuzYnX9vMgUARBlLKlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6227be095a087cc62e2b12b2b62de20f78a1ad411e5d8350bf3e70b0025fbd6d","last_reissued_at":"2026-05-21T02:05:31.528804Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:31.528804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hongzhi Ruan, Jun Ma, Kun Zhan, Pei Liu, Weiliang Ma, Xueyang Zhang, Zhengning Li","submitted_at":"2026-05-20T16:36:26Z","abstract_excerpt":"Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world driving data is expensive to annotate and scene-biased, making real-synthetic co-training with near-infinite synthetic data a promising direction. However, naively incorporating all available synthetic data is inefficient and leads to distribution shifts, and optimizing data mixture under practical training budgets remains a critical yet under-explored problem. In this sense, we claim that the mixture of training data requires clear guidance in te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21372","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/2605.21372/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":"2605.21372","created_at":"2026-05-21T02:05:31.528952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21372v1","created_at":"2026-05-21T02:05:31.528952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21372","created_at":"2026-05-21T02:05:31.528952+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIT34CK2BB6M","created_at":"2026-05-21T02:05:31.528952+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIT34CK2BB6MMLRL","created_at":"2026-05-21T02:05:31.528952+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIT34CK2","created_at":"2026-05-21T02:05:31.528952+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/MIT34CK2BB6MMLRLCKZLMLPCB5","json":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5.json","graph_json":"https://pith.science/api/pith-number/MIT34CK2BB6MMLRLCKZLMLPCB5/graph.json","events_json":"https://pith.science/api/pith-number/MIT34CK2BB6MMLRLCKZLMLPCB5/events.json","paper":"https://pith.science/paper/MIT34CK2"},"agent_actions":{"view_html":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5","download_json":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5.json","view_paper":"https://pith.science/paper/MIT34CK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21372&json=true","fetch_graph":"https://pith.science/api/pith-number/MIT34CK2BB6MMLRLCKZLMLPCB5/graph.json","fetch_events":"https://pith.science/api/pith-number/MIT34CK2BB6MMLRLCKZLMLPCB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5/action/storage_attestation","attest_author":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5/action/author_attestation","sign_citation":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5/action/citation_signature","submit_replication":"https://pith.science/pith/MIT34CK2BB6MMLRLCKZLMLPCB5/action/replication_record"}},"created_at":"2026-05-21T02:05:31.528952+00:00","updated_at":"2026-05-21T02:05:31.528952+00:00"}