{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2F7C5IPDHCNAJWJNP3MHMVBSSP","short_pith_number":"pith:2F7C5IPD","schema_version":"1.0","canonical_sha256":"d17e2ea1e3389a04d92d7ed876543293d726096b5a65fad43311cea4e821a382","source":{"kind":"arxiv","id":"2605.21139","version":1},"attestation_state":"computed","paper":{"title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jian Yang, Jin Xie, Qiang Meng, Yang Wu, Youquan Liu, Zhaojiang Liu","submitted_at":"2026-05-20T13:14:28Z","abstract_excerpt":"Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to smarter autonomy, it demands two missing pieces of infrastructure: (1) a cognitive foundation that understands traffic semantics and driving intent, and (2) a foresighted physical environment that can anticipate the consequences of candidate actions. To this end, we propose CoPhy, a CognitivePhysical reinforcement learning framework for autonomous driving. To distill to think, we distill VLM knowledge into the BEV enco"},"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":"2605.21139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T13:14:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5962cf8afffec7b3bd4043395265a0076b942d58cdc20adc4892ba65ba44d0dd","abstract_canon_sha256":"7a47d01b181b67263c79c137a57d922a457ad773907e6d20a94a53fe7cd9d928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:39.496003Z","signature_b64":"0OLbvorXue9lpDs+4Xi4gG4/fanK3yt5BA9crrEelqn47wKm09JGRybe8slnrJCdtciqFOtoIE0iUgoaQAKUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d17e2ea1e3389a04d92d7ed876543293d726096b5a65fad43311cea4e821a382","last_reissued_at":"2026-05-21T01:05:39.495151Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:39.495151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jian Yang, Jin Xie, Qiang Meng, Yang Wu, Youquan Liu, Zhaojiang Liu","submitted_at":"2026-05-20T13:14:28Z","abstract_excerpt":"Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to smarter autonomy, it demands two missing pieces of infrastructure: (1) a cognitive foundation that understands traffic semantics and driving intent, and (2) a foresighted physical environment that can anticipate the consequences of candidate actions. To this end, we propose CoPhy, a CognitivePhysical reinforcement learning framework for autonomous driving. To distill to think, we distill VLM knowledge into the BEV enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21139","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/2605.21139/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":"2605.21139","created_at":"2026-05-21T01:05:39.495299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21139v1","created_at":"2026-05-21T01:05:39.495299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21139","created_at":"2026-05-21T01:05:39.495299+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F7C5IPDHCNA","created_at":"2026-05-21T01:05:39.495299+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F7C5IPDHCNAJWJN","created_at":"2026-05-21T01:05:39.495299+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F7C5IPD","created_at":"2026-05-21T01:05:39.495299+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/2F7C5IPDHCNAJWJNP3MHMVBSSP","json":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP.json","graph_json":"https://pith.science/api/pith-number/2F7C5IPDHCNAJWJNP3MHMVBSSP/graph.json","events_json":"https://pith.science/api/pith-number/2F7C5IPDHCNAJWJNP3MHMVBSSP/events.json","paper":"https://pith.science/paper/2F7C5IPD"},"agent_actions":{"view_html":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP","download_json":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP.json","view_paper":"https://pith.science/paper/2F7C5IPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21139&json=true","fetch_graph":"https://pith.science/api/pith-number/2F7C5IPDHCNAJWJNP3MHMVBSSP/graph.json","fetch_events":"https://pith.science/api/pith-number/2F7C5IPDHCNAJWJNP3MHMVBSSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP/action/storage_attestation","attest_author":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP/action/author_attestation","sign_citation":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP/action/citation_signature","submit_replication":"https://pith.science/pith/2F7C5IPDHCNAJWJNP3MHMVBSSP/action/replication_record"}},"created_at":"2026-05-21T01:05:39.495299+00:00","updated_at":"2026-05-21T01:05:39.495299+00:00"}