{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5NSV24JAQAH2XZ756YUL6TYMFH","short_pith_number":"pith:5NSV24JA","schema_version":"1.0","canonical_sha256":"eb655d7120800fabe7fdf628bf4f0c29ddfd3bd67752332a7f572880e491dc88","source":{"kind":"arxiv","id":"2207.00448","version":2},"attestation_state":"computed","paper":{"title":"Safe Decision-making for Lane-change of Autonomous Vehicles via Human Demonstration-aided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Lv, Jingda Wu, Niels de Boer, Wenhui Huang, Xiangkun He, Yanghui Mo","submitted_at":"2022-07-01T14:16:50Z","abstract_excerpt":"Decision-making is critical for lane change in autonomous driving. Reinforcement learning (RL) algorithms aim to identify the values of behaviors in various situations and thus they become a promising pathway to address the decision-making problem. However, poor runtime safety hinders RL-based decision-making strategies from complex driving tasks in practice. To address this problem, human demonstrations are incorporated into the RL-based decision-making strategy in this paper. Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the"},"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":"2207.00448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-07-01T14:16:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b87337f1e6385739ef710eeffd7e5a1a6226734776aab41d680bffad019dbea","abstract_canon_sha256":"60af6f45645f9a041bc53aadf30cdd80be709044019ea19d6053e55d22223c70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:15.932756Z","signature_b64":"vPY26pTmPa+RffjRQuz82Ym+6Xox/ukT7jM4h8eybGjLPH8n2JQsTqIxUzssjmmba/OBu4sQkNE0R4wd8hYlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb655d7120800fabe7fdf628bf4f0c29ddfd3bd67752332a7f572880e491dc88","last_reissued_at":"2026-07-05T04:38:15.932302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:15.932302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Decision-making for Lane-change of Autonomous Vehicles via Human Demonstration-aided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chen Lv, Jingda Wu, Niels de Boer, Wenhui Huang, Xiangkun He, Yanghui Mo","submitted_at":"2022-07-01T14:16:50Z","abstract_excerpt":"Decision-making is critical for lane change in autonomous driving. Reinforcement learning (RL) algorithms aim to identify the values of behaviors in various situations and thus they become a promising pathway to address the decision-making problem. However, poor runtime safety hinders RL-based decision-making strategies from complex driving tasks in practice. To address this problem, human demonstrations are incorporated into the RL-based decision-making strategy in this paper. Decisions made by human subjects in a driving simulator are treated as safe demonstrations, which are stored into the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00448","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/2207.00448/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":"2207.00448","created_at":"2026-07-05T04:38:15.932368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.00448v2","created_at":"2026-07-05T04:38:15.932368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00448","created_at":"2026-07-05T04:38:15.932368+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NSV24JAQAH2","created_at":"2026-07-05T04:38:15.932368+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NSV24JAQAH2XZ75","created_at":"2026-07-05T04:38:15.932368+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NSV24JA","created_at":"2026-07-05T04:38:15.932368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14903","citing_title":"CoMoCAVs: Cohesive Decision-Guided Motion Planning for Connected and Autonomous Vehicles with Multi-Policy Reinforcement Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH","json":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH.json","graph_json":"https://pith.science/api/pith-number/5NSV24JAQAH2XZ756YUL6TYMFH/graph.json","events_json":"https://pith.science/api/pith-number/5NSV24JAQAH2XZ756YUL6TYMFH/events.json","paper":"https://pith.science/paper/5NSV24JA"},"agent_actions":{"view_html":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH","download_json":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH.json","view_paper":"https://pith.science/paper/5NSV24JA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.00448&json=true","fetch_graph":"https://pith.science/api/pith-number/5NSV24JAQAH2XZ756YUL6TYMFH/graph.json","fetch_events":"https://pith.science/api/pith-number/5NSV24JAQAH2XZ756YUL6TYMFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH/action/storage_attestation","attest_author":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH/action/author_attestation","sign_citation":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH/action/citation_signature","submit_replication":"https://pith.science/pith/5NSV24JAQAH2XZ756YUL6TYMFH/action/replication_record"}},"created_at":"2026-07-05T04:38:15.932368+00:00","updated_at":"2026-07-05T04:38:15.932368+00:00"}