{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4QTQJTTRQHTXGJLFVRYH6HYQQ","short_pith_number":"pith:W4QTQJTT","schema_version":"1.0","canonical_sha256":"b7213826738c0f3b992b2d6383f8f884269dffad07ddd069f7f7326a23a3c7f6","source":{"kind":"arxiv","id":"2502.20065","version":1},"attestation_state":"computed","paper":{"title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Ahmet Onur Akman, Anastasia Psarou, Grzegorz Jamr\\'oz, {\\L}ukasz Gorczyca, Rafa{\\l} Kucharski, Zolt\\'an Gy\\\"orgy Varga","submitted_at":"2025-02-27T13:13:09Z","abstract_excerpt":"RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation, facilitating the testing and development of efficient route choice strategies for autonomous vehicles (AVs). The proposed framework simulates the daily route choices of driver agents in a city, including two types: human drivers, emulated using behavioral route choice models, and AVs, modeled as MARL agents optimizing their policies for a predefined objective. RouteRL aims to advance research in MARL, transport modeling, and human-AI interaction for transportation appli"},"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":"2502.20065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-02-27T13:13:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b18a51f32780d7f762b752b3c30a0817e5a557248ef7571f58f9e9295b06ab5f","abstract_canon_sha256":"fd300773dd9a1e72023cb94949557fcaf99df7072624a5835e9690cc7a08b8fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:08.844091Z","signature_b64":"NhcvaKOopQh8Za0c3hqPaTOeJKR6bX76REPBjXZI5h4VWn3Y4Zm2X1/U+4PG1BZy3iwku6wz5ZrRSaysoCJ+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7213826738c0f3b992b2d6383f8f884269dffad07ddd069f7f7326a23a3c7f6","last_reissued_at":"2026-07-05T10:21:08.843522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:08.843522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Ahmet Onur Akman, Anastasia Psarou, Grzegorz Jamr\\'oz, {\\L}ukasz Gorczyca, Rafa{\\l} Kucharski, Zolt\\'an Gy\\\"orgy Varga","submitted_at":"2025-02-27T13:13:09Z","abstract_excerpt":"RouteRL is a novel framework that integrates multi-agent reinforcement learning (MARL) with a microscopic traffic simulation, facilitating the testing and development of efficient route choice strategies for autonomous vehicles (AVs). The proposed framework simulates the daily route choices of driver agents in a city, including two types: human drivers, emulated using behavioral route choice models, and AVs, modeled as MARL agents optimizing their policies for a predefined objective. RouteRL aims to advance research in MARL, transport modeling, and human-AI interaction for transportation appli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20065","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/2502.20065/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":"2502.20065","created_at":"2026-07-05T10:21:08.843581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20065v1","created_at":"2026-07-05T10:21:08.843581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20065","created_at":"2026-07-05T10:21:08.843581+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4QTQJTTRQHT","created_at":"2026-07-05T10:21:08.843581+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4QTQJTTRQHTXGJL","created_at":"2026-07-05T10:21:08.843581+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4QTQJTT","created_at":"2026-07-05T10:21:08.843581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22966","citing_title":"Detection of coordinated fleet vehicles in route choice urban games. Part I. Inverse fleet assignment theory","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ","json":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ.json","graph_json":"https://pith.science/api/pith-number/W4QTQJTTRQHTXGJLFVRYH6HYQQ/graph.json","events_json":"https://pith.science/api/pith-number/W4QTQJTTRQHTXGJLFVRYH6HYQQ/events.json","paper":"https://pith.science/paper/W4QTQJTT"},"agent_actions":{"view_html":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ","download_json":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ.json","view_paper":"https://pith.science/paper/W4QTQJTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20065&json=true","fetch_graph":"https://pith.science/api/pith-number/W4QTQJTTRQHTXGJLFVRYH6HYQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/W4QTQJTTRQHTXGJLFVRYH6HYQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ/action/storage_attestation","attest_author":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ/action/author_attestation","sign_citation":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ/action/citation_signature","submit_replication":"https://pith.science/pith/W4QTQJTTRQHTXGJLFVRYH6HYQQ/action/replication_record"}},"created_at":"2026-07-05T10:21:08.843581+00:00","updated_at":"2026-07-05T10:21:08.843581+00:00"}