{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3QX237ZV6VG3UV6CQLAUXU2A5P","short_pith_number":"pith:3QX237ZV","canonical_record":{"source":{"id":"1908.03761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"1e68ee2310b256b4b4c138e81da125225f78a7989f3220484282800013ab5267","abstract_canon_sha256":"9b2e82151eece2e0c687a4892da10e60574783808d2dea8a1d405bdf15a26deb"},"schema_version":"1.0"},"canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","source":{"kind":"arxiv","id":"1908.03761","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03761","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03761v2","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03761","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"3QX237ZV6VG3","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_16","alias_value":"3QX237ZV6VG3UV6C","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_8","alias_value":"3QX237ZV","created_at":"2026-07-05T03:13:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3QX237ZV6VG3UV6CQLAUXU2A5P","target":"record","payload":{"canonical_record":{"source":{"id":"1908.03761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"1e68ee2310b256b4b4c138e81da125225f78a7989f3220484282800013ab5267","abstract_canon_sha256":"9b2e82151eece2e0c687a4892da10e60574783808d2dea8a1d405bdf15a26deb"},"schema_version":"1.0"},"canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:19.944493Z","signature_b64":"fMiXFeSh7DXgreJZp1CYeL3Nsx3yW+93/bu2VrNCMIswADfNe/Kf1ZnjfsNBb/BHJyyCL455afNkzC8I2QyoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","last_reissued_at":"2026-07-05T03:13:19.944064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:19.944064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.03761","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gb8i+uhxvn7Nze60DYNbpPSWhwKE86oz8WTZrPvsDXYkR74O1x7VIjuGXwM7jqDLEnIco54yZT8z53Kh35dcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:18:11.423622Z"},"content_sha256":"b814ef67248644370c76fb62da7fbc4680956def3202a59a3b670854f0346bf8","schema_version":"1.0","event_id":"sha256:b814ef67248644370c76fb62da7fbc4680956def3202a59a3b670854f0346bf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3QX237ZV6VG3UV6CQLAUXU2A5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Liangjun Ke, Xiaoqiang Wang, Xinghua Chai, Zhimin Qiao","submitted_at":"2019-08-10T14:19:21Z","abstract_excerpt":"Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multi-Agent Reinforcement Learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this paper, a new MARL, called Cooperative double Q-learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q-learning method based on double estimators and the UCB policy, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03761","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/1908.03761/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:13:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZPz/W/lN0PaTpkddtZ8LcPzhwhxFMHz/xfVa5Zv8JhN1WXllLTVyA6+vcPPBdgr84FrEnIim6wi/n9e95rCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:18:11.424561Z"},"content_sha256":"91475ebc47d45830f7e4a096255bf6a3299bee703c9269c39139ee20a864e3c9","schema_version":"1.0","event_id":"sha256:91475ebc47d45830f7e4a096255bf6a3299bee703c9269c39139ee20a864e3c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/bundle.json","state_url":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T01:18:11Z","links":{"resolver":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P","bundle":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/bundle.json","state":"https://pith.science/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3QX237ZV6VG3UV6CQLAUXU2A5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3QX237ZV6VG3UV6CQLAUXU2A5P","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9b2e82151eece2e0c687a4892da10e60574783808d2dea8a1d405bdf15a26deb","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","title_canon_sha256":"1e68ee2310b256b4b4c138e81da125225f78a7989f3220484282800013ab5267"},"schema_version":"1.0","source":{"id":"1908.03761","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.03761","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"1908.03761v2","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03761","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"3QX237ZV6VG3","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_16","alias_value":"3QX237ZV6VG3UV6C","created_at":"2026-07-05T03:13:19Z"},{"alias_kind":"pith_short_8","alias_value":"3QX237ZV","created_at":"2026-07-05T03:13:19Z"}],"graph_snapshots":[{"event_id":"sha256:91475ebc47d45830f7e4a096255bf6a3299bee703c9269c39139ee20a864e3c9","target":"graph","created_at":"2026-07-05T03:13:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.03761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multi-Agent Reinforcement Learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this paper, a new MARL, called Cooperative double Q-learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q-learning method based on double estimators and the UCB policy, wh","authors_text":"Liangjun Ke, Xiaoqiang Wang, Xinghua Chai, Zhimin Qiao","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","title":"Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03761","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b814ef67248644370c76fb62da7fbc4680956def3202a59a3b670854f0346bf8","target":"record","created_at":"2026-07-05T03:13:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9b2e82151eece2e0c687a4892da10e60574783808d2dea8a1d405bdf15a26deb","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-10T14:19:21Z","title_canon_sha256":"1e68ee2310b256b4b4c138e81da125225f78a7989f3220484282800013ab5267"},"schema_version":"1.0","source":{"id":"1908.03761","kind":"arxiv","version":2}},"canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc2fadff35f54dba57c282c14bd340ebe17f4a5f22c56bba8f169b9b89dc0acb","first_computed_at":"2026-07-05T03:13:19.944064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:19.944064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fMiXFeSh7DXgreJZp1CYeL3Nsx3yW+93/bu2VrNCMIswADfNe/Kf1ZnjfsNBb/BHJyyCL455afNkzC8I2QyoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:19.944493Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.03761","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b814ef67248644370c76fb62da7fbc4680956def3202a59a3b670854f0346bf8","sha256:91475ebc47d45830f7e4a096255bf6a3299bee703c9269c39139ee20a864e3c9"],"state_sha256":"ae46fdf356bcc780167a13bcfc17efc78204ed49b81d8ea0fc7fe4130db389e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5MBvWu6EAxyNNb8h8Q5qpMJXKFadr3CvmfueofHcjJxw6DlzugjVAz1yem8kiT7GvvdWKSB1gkYhfMM1vSpAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:18:11.434491Z","bundle_sha256":"49982d743d7f4e6126a66393b96b9a0ef28d7b753eb39a4f0a3e4c97fce85d55"}}