{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FLGZLM3Q5G2Q7EPDTJCIPDYN2O","short_pith_number":"pith:FLGZLM3Q","schema_version":"1.0","canonical_sha256":"2acd95b370e9b50f91e39a44878f0dd3a352b68a3d175bf5ba3f7f9220566f08","source":{"kind":"arxiv","id":"2505.04231","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning-based Cooperative Autonomous Driving in Smart Intersections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Kei Sakaguchi, Kui Wang, Tao Yu, Taoyuan Yu, Zongdian Li","submitted_at":"2025-05-07T08:27:52Z","abstract_excerpt":"Unsignalized intersections pose significant safety and efficiency challenges due to complex traffic flows. This paper proposes a novel roadside unit (RSU)-centric cooperative driving system leveraging global perception and vehicle-to-infrastructure (V2I) communication. The core of the system is an RSU-based decision-making module using a two-stage hybrid reinforcement learning (RL) framework. At first, policies are pre-trained offline using conservative Q-learning (CQL) combined with behavior cloning (BC) on collected dataset. Subsequently, these policies are fine-tuned in the simulation using"},"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":"2505.04231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-07T08:27:52Z","cross_cats_sorted":["cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"086c59f72c4db904e91a6596033d7f4271e86ef6d3878fbc334c7418be7c60c4","abstract_canon_sha256":"0a414b8eadf4dc371dde4f00ff41bb9b66059b84eae9a34d1e9005a4ee418af1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:38.500742Z","signature_b64":"wzhkqxSuZB9ZPEILRI0wRbOHwfcdvWH8nU/gsL+W68g2SnXOOnjHqIn8R6JCfnx9mPZVkNSMSHuxlRmSDk9aDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2acd95b370e9b50f91e39a44878f0dd3a352b68a3d175bf5ba3f7f9220566f08","last_reissued_at":"2026-07-05T10:59:38.500299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:38.500299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning-based Cooperative Autonomous Driving in Smart Intersections","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Kei Sakaguchi, Kui Wang, Tao Yu, Taoyuan Yu, Zongdian Li","submitted_at":"2025-05-07T08:27:52Z","abstract_excerpt":"Unsignalized intersections pose significant safety and efficiency challenges due to complex traffic flows. This paper proposes a novel roadside unit (RSU)-centric cooperative driving system leveraging global perception and vehicle-to-infrastructure (V2I) communication. The core of the system is an RSU-based decision-making module using a two-stage hybrid reinforcement learning (RL) framework. At first, policies are pre-trained offline using conservative Q-learning (CQL) combined with behavior cloning (BC) on collected dataset. Subsequently, these policies are fine-tuned in the simulation using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04231","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/2505.04231/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":"2505.04231","created_at":"2026-07-05T10:59:38.500364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04231v1","created_at":"2026-07-05T10:59:38.500364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04231","created_at":"2026-07-05T10:59:38.500364+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLGZLM3Q5G2Q","created_at":"2026-07-05T10:59:38.500364+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLGZLM3Q5G2Q7EPD","created_at":"2026-07-05T10:59:38.500364+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLGZLM3Q","created_at":"2026-07-05T10:59:38.500364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O","json":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O.json","graph_json":"https://pith.science/api/pith-number/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/graph.json","events_json":"https://pith.science/api/pith-number/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/events.json","paper":"https://pith.science/paper/FLGZLM3Q"},"agent_actions":{"view_html":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O","download_json":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O.json","view_paper":"https://pith.science/paper/FLGZLM3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04231&json=true","fetch_graph":"https://pith.science/api/pith-number/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/graph.json","fetch_events":"https://pith.science/api/pith-number/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/action/storage_attestation","attest_author":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/action/author_attestation","sign_citation":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/action/citation_signature","submit_replication":"https://pith.science/pith/FLGZLM3Q5G2Q7EPDTJCIPDYN2O/action/replication_record"}},"created_at":"2026-07-05T10:59:38.500364+00:00","updated_at":"2026-07-05T10:59:38.500364+00:00"}