{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WBPQ5VFUC2KNLBVEKMFZGMKXOQ","short_pith_number":"pith:WBPQ5VFU","canonical_record":{"source":{"id":"1811.11329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:56:57Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"1635ceb2b5456ffb85d1c1e19922268b187f4787db9c16797f967f83e7c4e61e","abstract_canon_sha256":"ce9294a7dbd1b3bafcd0bd504ba6995f614d26e28b9daf25e3155c2251ea5c53"},"schema_version":"1.0"},"canonical_sha256":"b05f0ed4b41694d586a4530b9331577416416b38a910e2e725bae808e12148fd","source":{"kind":"arxiv","id":"1811.11329","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11329","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11329v3","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11329","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"WBPQ5VFUC2KN","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WBPQ5VFUC2KNLBVE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WBPQ5VFU","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WBPQ5VFUC2KNLBVEKMFZGMKXOQ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.11329","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:56:57Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"1635ceb2b5456ffb85d1c1e19922268b187f4787db9c16797f967f83e7c4e61e","abstract_canon_sha256":"ce9294a7dbd1b3bafcd0bd504ba6995f614d26e28b9daf25e3155c2251ea5c53"},"schema_version":"1.0"},"canonical_sha256":"b05f0ed4b41694d586a4530b9331577416416b38a910e2e725bae808e12148fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:52.467783Z","signature_b64":"pttjRDi4Z4bTR6r0gXLJC2Bruh7KG8yQxfVmxX92lFXgZp2/WuwOm68cJilwdH2M8nYJPUeeWaQu6xk+FxcJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05f0ed4b41694d586a4530b9331577416416b38a910e2e725bae808e12148fd","last_reissued_at":"2026-05-17T23:45:52.467292Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:52.467292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.11329","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cjRwS67TBQMDWAWXWfHLpNKcsM96vmCVd7VOvR7f2h4PFThhM28pWZTRWr+etRdyyrlDHMml392IzfrLs1RFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:44:11.659099Z"},"content_sha256":"54c916ec60b5d7dff8ab2758971e5d0efcf157d0265668f6ca66af371e37ef71","schema_version":"1.0","event_id":"sha256:54c916ec60b5d7dff8ab2758971e5d0efcf157d0265668f6ca66af371e37ef71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WBPQ5VFUC2KNLBVEKMFZGMKXOQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Daoyuan Jia, Sen Wang, Xinshuo Weng","submitted_at":"2018-11-28T00:56:57Z","abstract_excerpt":"Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in real world are extreme complex and action spaces are continuous and fine control is required. Moreover, the autonomous driving vehicles must also keep functional safety under the complex environments. To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11329","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wODqMxfTVkmFKEbI4lPDnx83l+Gd28wh74IdX0050ib2DZ3xUibwLwOMKIF/KmdChG4n4xeM4Mi1GdygxptdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:44:11.659788Z"},"content_sha256":"7603fb8360679f32f552baba2942c66fdee9a1a1e53fb9ca16fc22dcd4d03d4d","schema_version":"1.0","event_id":"sha256:7603fb8360679f32f552baba2942c66fdee9a1a1e53fb9ca16fc22dcd4d03d4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/bundle.json","state_url":"https://pith.science/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/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":"2026-05-26T10:44:11Z","links":{"resolver":"https://pith.science/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ","bundle":"https://pith.science/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/bundle.json","state":"https://pith.science/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBPQ5VFUC2KNLBVEKMFZGMKXOQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WBPQ5VFUC2KNLBVEKMFZGMKXOQ","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":"ce9294a7dbd1b3bafcd0bd504ba6995f614d26e28b9daf25e3155c2251ea5c53","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:56:57Z","title_canon_sha256":"1635ceb2b5456ffb85d1c1e19922268b187f4787db9c16797f967f83e7c4e61e"},"schema_version":"1.0","source":{"id":"1811.11329","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11329","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11329v3","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11329","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"WBPQ5VFUC2KN","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WBPQ5VFUC2KNLBVE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WBPQ5VFU","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:7603fb8360679f32f552baba2942c66fdee9a1a1e53fb9ca16fc22dcd4d03d4d","target":"graph","created_at":"2026-05-17T23:45:52Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in real world are extreme complex and action spaces are continuous and fine control is required. Moreover, the autonomous driving vehicles must also keep functional safety under the complex environments. To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action ","authors_text":"Daoyuan Jia, Sen Wang, Xinshuo Weng","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:56:57Z","title":"Deep Reinforcement Learning for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11329","kind":"arxiv","version":3},"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":"sha256:54c916ec60b5d7dff8ab2758971e5d0efcf157d0265668f6ca66af371e37ef71","target":"record","created_at":"2026-05-17T23:45:52Z","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":"ce9294a7dbd1b3bafcd0bd504ba6995f614d26e28b9daf25e3155c2251ea5c53","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T00:56:57Z","title_canon_sha256":"1635ceb2b5456ffb85d1c1e19922268b187f4787db9c16797f967f83e7c4e61e"},"schema_version":"1.0","source":{"id":"1811.11329","kind":"arxiv","version":3}},"canonical_sha256":"b05f0ed4b41694d586a4530b9331577416416b38a910e2e725bae808e12148fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b05f0ed4b41694d586a4530b9331577416416b38a910e2e725bae808e12148fd","first_computed_at":"2026-05-17T23:45:52.467292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:52.467292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pttjRDi4Z4bTR6r0gXLJC2Bruh7KG8yQxfVmxX92lFXgZp2/WuwOm68cJilwdH2M8nYJPUeeWaQu6xk+FxcJDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:52.467783Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.11329","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c916ec60b5d7dff8ab2758971e5d0efcf157d0265668f6ca66af371e37ef71","sha256:7603fb8360679f32f552baba2942c66fdee9a1a1e53fb9ca16fc22dcd4d03d4d"],"state_sha256":"dd189621edc8fda6861954d9b0d99b130aa0245983f237428242bc5276a10a5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QGV9mnwigtQ3sdEeHPzbhcN/GdYIuTRxwj0VcwGR3UZ3oFvEGN34oQDLtlB8ghq8lA2CXl2thlXU0T/EwJ0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:44:11.663394Z","bundle_sha256":"92119c6f2708f096516e4bb081de7f9022bbc736c6f0598ded996135e9a3e3d2"}}