{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ERSEYNIOX5UJRMS52V6YW3J4Y","short_pith_number":"pith:3ERSEYNI","schema_version":"1.0","canonical_sha256":"d9232261a875fb44c592eeabec5b69e62625a9308732af941ca16948232eec15","source":{"kind":"arxiv","id":"2506.03568","version":2},"attestation_state":"computed","paper":{"title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hu Chuan, Li Peng, Li Zeqiao, Li Zheng, Wang Haoyu, Wang Yijing, Zuo zhiqiang","submitted_at":"2025-06-04T04:31:10Z","abstract_excerpt":"Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges. Although human-AI collaboration alleviates these issues, it often relies heavily on extensive human intervention, which increases costs and reduces efficiency. This paper develops a confidence-guided human-AI collaboration (C-HAC) strategy to overcome these limitations. First, C-HAC employs a distributional proxy value propagation method within the distributional soft actor-critic (DSAC) "},"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":"2506.03568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-04T04:31:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb670432a0d3131486c69d65753e908d4b76b6308971de2d5fea2438d00d077d","abstract_canon_sha256":"8b6c212ae2ee45d5c16a08102198f9ac1707fc07d8ed005eeac18c5ccea2b765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:10.102287Z","signature_b64":"E3NPJnHdzVZH6+K7aFjDv/t7WPwrQqkvdTLlXeSfRVO396zLYUO1ECADcXfA9l5ja5UHJVooV0SkC4qhjG8xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9232261a875fb44c592eeabec5b69e62625a9308732af941ca16948232eec15","last_reissued_at":"2026-07-05T11:16:10.101640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:10.101640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hu Chuan, Li Peng, Li Zeqiao, Li Zheng, Wang Haoyu, Wang Yijing, Zuo zhiqiang","submitted_at":"2025-06-04T04:31:10Z","abstract_excerpt":"Autonomous driving promises significant advancements in mobility, road safety and traffic efficiency, yet reinforcement learning and imitation learning face safe-exploration and distribution-shift challenges. Although human-AI collaboration alleviates these issues, it often relies heavily on extensive human intervention, which increases costs and reduces efficiency. This paper develops a confidence-guided human-AI collaboration (C-HAC) strategy to overcome these limitations. First, C-HAC employs a distributional proxy value propagation method within the distributional soft actor-critic (DSAC) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03568","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/2506.03568/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":"2506.03568","created_at":"2026-07-05T11:16:10.101704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03568v2","created_at":"2026-07-05T11:16:10.101704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03568","created_at":"2026-07-05T11:16:10.101704+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ERSEYNIOX5U","created_at":"2026-07-05T11:16:10.101704+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ERSEYNIOX5UJRMS","created_at":"2026-07-05T11:16:10.101704+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ERSEYNI","created_at":"2026-07-05T11:16:10.101704+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/3ERSEYNIOX5UJRMS52V6YW3J4Y","json":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y.json","graph_json":"https://pith.science/api/pith-number/3ERSEYNIOX5UJRMS52V6YW3J4Y/graph.json","events_json":"https://pith.science/api/pith-number/3ERSEYNIOX5UJRMS52V6YW3J4Y/events.json","paper":"https://pith.science/paper/3ERSEYNI"},"agent_actions":{"view_html":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y","download_json":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y.json","view_paper":"https://pith.science/paper/3ERSEYNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03568&json=true","fetch_graph":"https://pith.science/api/pith-number/3ERSEYNIOX5UJRMS52V6YW3J4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/3ERSEYNIOX5UJRMS52V6YW3J4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y/action/storage_attestation","attest_author":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y/action/author_attestation","sign_citation":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y/action/citation_signature","submit_replication":"https://pith.science/pith/3ERSEYNIOX5UJRMS52V6YW3J4Y/action/replication_record"}},"created_at":"2026-07-05T11:16:10.101704+00:00","updated_at":"2026-07-05T11:16:10.101704+00:00"}