{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JKVJIHE3MHSZLRGOER4EIV4FJV","short_pith_number":"pith:JKVJIHE3","canonical_record":{"source":{"id":"1904.09503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"a0d76b40973af4dadcd0d1c71e9ddfb4b54e3b37503e7756784f77638722edf3","abstract_canon_sha256":"352ceb42d338d804ea32c5f332ea8f8366ad1cb90f274641ba1657fcecf292d3"},"schema_version":"1.0"},"canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","source":{"kind":"arxiv","id":"1904.09503","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09503","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09503v2","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09503","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"JKVJIHE3MHSZ","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"JKVJIHE3MHSZLRGO","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"JKVJIHE3","created_at":"2026-07-05T00:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JKVJIHE3MHSZLRGOER4EIV4FJV","target":"record","payload":{"canonical_record":{"source":{"id":"1904.09503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"a0d76b40973af4dadcd0d1c71e9ddfb4b54e3b37503e7756784f77638722edf3","abstract_canon_sha256":"352ceb42d338d804ea32c5f332ea8f8366ad1cb90f274641ba1657fcecf292d3"},"schema_version":"1.0"},"canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:44.926341Z","signature_b64":"MNunEbfo5XSazoAE3q1+3QuNv04uHK08R4017CEHnq6PSO80OHqZZh5/SIJ0tat2bBLF6N7HxMZJc8mHotg0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","last_reissued_at":"2026-07-05T00:13:44.925874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:44.925874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.09503","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":"2026-07-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CpwXVHkfGh87fhhoTdESBPKiv36mhKG/JWvHFZJxiXJwL9pwuPYK9fEXI1Rnj0/h1ZOl3/6D5PO2792hU30gBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:08.617733Z"},"content_sha256":"ee6157c08e768d9c3a0b9e5fb6f33d847f1772a1c6d26997ca95eaadaa487883","schema_version":"1.0","event_id":"sha256:ee6157c08e768d9c3a0b9e5fb6f33d847f1772a1c6d26997ca95eaadaa487883"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JKVJIHE3MHSZLRGOER4EIV4FJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Bodi Yuan, Jianyu Chen, Masayoshi Tomizuka","submitted_at":"2019-04-20T22:02:45Z","abstract_excerpt":"Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09503","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/1904.09503/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":"2026-07-05T00:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyBG/hshwKb4OS605pqyGuOdpjG14Uz+oNPIIy79pL06cAMs4Q1CTDaMiURohmL/mQZcuyluhHxnwW1E+rMrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:08.618245Z"},"content_sha256":"ea4e510a02b29f10258637a4ed70381aa290523f3e72b18f97a3a36183ad841a","schema_version":"1.0","event_id":"sha256:ea4e510a02b29f10258637a4ed70381aa290523f3e72b18f97a3a36183ad841a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/bundle.json","state_url":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/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":"2026-08-08T20:58:08Z","links":{"resolver":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV","bundle":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/bundle.json","state":"https://pith.science/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKVJIHE3MHSZLRGOER4EIV4FJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JKVJIHE3MHSZLRGOER4EIV4FJV","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":"352ceb42d338d804ea32c5f332ea8f8366ad1cb90f274641ba1657fcecf292d3","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","title_canon_sha256":"a0d76b40973af4dadcd0d1c71e9ddfb4b54e3b37503e7756784f77638722edf3"},"schema_version":"1.0","source":{"id":"1904.09503","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.09503","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.09503v2","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09503","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"JKVJIHE3MHSZ","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"JKVJIHE3MHSZLRGO","created_at":"2026-07-05T00:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"JKVJIHE3","created_at":"2026-07-05T00:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:ea4e510a02b29f10258637a4ed70381aa290523f3e72b18f97a3a36183ad841a","target":"graph","created_at":"2026-07-05T00:13:44Z","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/1904.09503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea","authors_text":"Bodi Yuan, Jianyu Chen, Masayoshi Tomizuka","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","title":"Model-free Deep Reinforcement Learning for Urban Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09503","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:ee6157c08e768d9c3a0b9e5fb6f33d847f1772a1c6d26997ca95eaadaa487883","target":"record","created_at":"2026-07-05T00:13:44Z","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":"352ceb42d338d804ea32c5f332ea8f8366ad1cb90f274641ba1657fcecf292d3","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-20T22:02:45Z","title_canon_sha256":"a0d76b40973af4dadcd0d1c71e9ddfb4b54e3b37503e7756784f77638722edf3"},"schema_version":"1.0","source":{"id":"1904.09503","kind":"arxiv","version":2}},"canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aaa941c9b61e595c4ce24784457854d503039f55711d172acd8a4884c44f30b","first_computed_at":"2026-07-05T00:13:44.925874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:44.925874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MNunEbfo5XSazoAE3q1+3QuNv04uHK08R4017CEHnq6PSO80OHqZZh5/SIJ0tat2bBLF6N7HxMZJc8mHotg0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:44.926341Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.09503","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee6157c08e768d9c3a0b9e5fb6f33d847f1772a1c6d26997ca95eaadaa487883","sha256:ea4e510a02b29f10258637a4ed70381aa290523f3e72b18f97a3a36183ad841a"],"state_sha256":"fa35faa2b3b2c142faa7f36417df90cabae3cffe454f770f3328f819de6d66c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QZtodfyOsJV/OTEGyWCKniXG3JEVKoZYjWmFyv6X6LkDW0GkfKkpmI+hrznuuTqEa4D1moXq8chzfS7EPKtRDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:58:08.622053Z","bundle_sha256":"14572e56be5425eeefbf403ee6d65d891ab9d71b6bdf3560a41a14832bcdd3a2"}}