{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AMBAHFITAPZNGBTEGQHHKGK7PF","short_pith_number":"pith:AMBAHFIT","schema_version":"1.0","canonical_sha256":"030203951303f2d30664340e75195f796c41a1b9f685e66ecffda3e4e601bd4c","source":{"kind":"arxiv","id":"2601.21288","version":2},"attestation_state":"computed","paper":{"title":"Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hangshuo Cao, Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Tianjian Gao, Tianxing Chen, Weitong Lian, Yichen Zhu, Yifei Wang, Yu Zhang, Zecong Tang, Zhejun Cui, Zixu Wang","submitted_at":"2026-01-29T05:41:24Z","abstract_excerpt":"Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high inference latency, while conventional supervised fine-tuning (SFT) often struggles to bridge the capability gaps of small models. To address these limitations, we propose Drive-KD, a framework that decomposes autonomous driving into a \"perception-reasoning-planning\" triad and transfers these capabilities via knowledge distillation. We identify layer-specific att"},"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":"2601.21288","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T05:41:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c246ce15e2c23fc6dedcbb4b64e0e5104a0508ceeab08e883b34b034196631d5","abstract_canon_sha256":"aab6c1b2d42b2368eb81f312a7c7298d10c2955e8927987069259e918b1f7c21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:19.356722Z","signature_b64":"52C1ITXn3jJZldEtgwLIh1SiVeptFToSgPyn2NkqR2gQZpBO4IcXS+zuRyu+4WtvDordIzpeLtlP7lqO1djCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"030203951303f2d30664340e75195f796c41a1b9f685e66ecffda3e4e601bd4c","last_reissued_at":"2026-06-05T01:15:19.356196Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:19.356196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hangshuo Cao, Haoran Li, Kaixuan Wang, Lingyi Meng, Qi Kang, Tengju Ru, Tianjian Gao, Tianxing Chen, Weitong Lian, Yichen Zhu, Yifei Wang, Yu Zhang, Zecong Tang, Zhejun Cui, Zixu Wang","submitted_at":"2026-01-29T05:41:24Z","abstract_excerpt":"Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high inference latency, while conventional supervised fine-tuning (SFT) often struggles to bridge the capability gaps of small models. To address these limitations, we propose Drive-KD, a framework that decomposes autonomous driving into a \"perception-reasoning-planning\" triad and transfers these capabilities via knowledge distillation. We identify layer-specific att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21288","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/2601.21288/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":"2601.21288","created_at":"2026-06-05T01:15:19.356266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21288v2","created_at":"2026-06-05T01:15:19.356266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21288","created_at":"2026-06-05T01:15:19.356266+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMBAHFITAPZN","created_at":"2026-06-05T01:15:19.356266+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMBAHFITAPZNGBTE","created_at":"2026-06-05T01:15:19.356266+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMBAHFIT","created_at":"2026-06-05T01:15:19.356266+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/AMBAHFITAPZNGBTEGQHHKGK7PF","json":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF.json","graph_json":"https://pith.science/api/pith-number/AMBAHFITAPZNGBTEGQHHKGK7PF/graph.json","events_json":"https://pith.science/api/pith-number/AMBAHFITAPZNGBTEGQHHKGK7PF/events.json","paper":"https://pith.science/paper/AMBAHFIT"},"agent_actions":{"view_html":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF","download_json":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF.json","view_paper":"https://pith.science/paper/AMBAHFIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21288&json=true","fetch_graph":"https://pith.science/api/pith-number/AMBAHFITAPZNGBTEGQHHKGK7PF/graph.json","fetch_events":"https://pith.science/api/pith-number/AMBAHFITAPZNGBTEGQHHKGK7PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF/action/storage_attestation","attest_author":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF/action/author_attestation","sign_citation":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF/action/citation_signature","submit_replication":"https://pith.science/pith/AMBAHFITAPZNGBTEGQHHKGK7PF/action/replication_record"}},"created_at":"2026-06-05T01:15:19.356266+00:00","updated_at":"2026-06-05T01:15:19.356266+00:00"}