{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PM6H6OUGI3NPXTXF7IWIBQO75Q","short_pith_number":"pith:PM6H6OUG","canonical_record":{"source":{"id":"1803.09200","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-25T04:42:57Z","cross_cats_sorted":[],"title_canon_sha256":"f0fb0778531c1ae061246b647e2169ebdaf7a9d9995cb01cc969f8b9c8216788","abstract_canon_sha256":"597c7de70a505fd978b74f0358afff3e51401c933a51ed3f8bea94845eb80f0e"},"schema_version":"1.0"},"canonical_sha256":"7b3c7f3a8646dafbcee5fa2c80c1dfec16dbeec942422c701b9c360a4c2843af","source":{"kind":"arxiv","id":"1803.09200","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09200","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09200v3","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09200","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"PM6H6OUGI3NP","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PM6H6OUGI3NPXTXF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PM6H6OUG","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PM6H6OUGI3NPXTXF7IWIBQO75Q","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09200","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-25T04:42:57Z","cross_cats_sorted":[],"title_canon_sha256":"f0fb0778531c1ae061246b647e2169ebdaf7a9d9995cb01cc969f8b9c8216788","abstract_canon_sha256":"597c7de70a505fd978b74f0358afff3e51401c933a51ed3f8bea94845eb80f0e"},"schema_version":"1.0"},"canonical_sha256":"7b3c7f3a8646dafbcee5fa2c80c1dfec16dbeec942422c701b9c360a4c2843af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:34.537988Z","signature_b64":"u0X57uZfZ2mENaBaY37aH+dFncJewsQC84gB3yg+Q9PTB8Ckb8nPg3GJOI7JVi2IYe9gEAr37KEzZrh5lu48Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3c7f3a8646dafbcee5fa2c80c1dfec16dbeec942422c701b9c360a4c2843af","last_reissued_at":"2026-05-17T23:55:34.537552Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:34.537552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09200","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":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LGFiv8T0G4g0P3Eehp6AneCDBWiNPqK2yFjAku3XHygLoRNMByA8bO1JQQiFyRh3hoi46lEcgEJgCN3nQm+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:03:07.819805Z"},"content_sha256":"772e09f42649f999a1ae0be41a84b428085920a822a4a4ba7ce3081bf8cdf8dd","schema_version":"1.0","event_id":"sha256:772e09f42649f999a1ae0be41a84b428085920a822a4a4ba7ce3081bf8cdf8dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PM6H6OUGI3NPXTXF7IWIBQO75Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Driving Maneuvers under Interactive Environment based on Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ching-Yao Chan, Hanhan Li, Pin Wang","submitted_at":"2018-03-25T04:42:57Z","abstract_excerpt":"Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their interactions with the ego vehicle. One of the state-of-the-art approaches is to apply Reinforcement Learning (RL) to learn a time-sequential driving policy, to execute proper control strategy or tracking trajectory in dynamic situations. However, direct application of RL algorithms is not satisfactorily enough to deal with the cases in the autonomous driving domain, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09200","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":"2026-05-17T23:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAI1nJ0TncO6TmqhGUgzYcdEUKECXUTcdJW/F8OPuoxuPZ81f5EcPG4yMfZbcfaEwBwGZzbBybskkjSWx7pODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:03:07.820506Z"},"content_sha256":"20c4c8a3007bcca1b73f8f16929504ef84d6aecae58d1e7ccc1e4d0821eb6388","schema_version":"1.0","event_id":"sha256:20c4c8a3007bcca1b73f8f16929504ef84d6aecae58d1e7ccc1e4d0821eb6388"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/bundle.json","state_url":"https://pith.science/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/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":"2026-05-27T13:03:07Z","links":{"resolver":"https://pith.science/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q","bundle":"https://pith.science/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/bundle.json","state":"https://pith.science/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PM6H6OUGI3NPXTXF7IWIBQO75Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PM6H6OUGI3NPXTXF7IWIBQO75Q","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":"597c7de70a505fd978b74f0358afff3e51401c933a51ed3f8bea94845eb80f0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-25T04:42:57Z","title_canon_sha256":"f0fb0778531c1ae061246b647e2169ebdaf7a9d9995cb01cc969f8b9c8216788"},"schema_version":"1.0","source":{"id":"1803.09200","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09200","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09200v3","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09200","created_at":"2026-05-17T23:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"PM6H6OUGI3NP","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PM6H6OUGI3NPXTXF","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PM6H6OUG","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:20c4c8a3007bcca1b73f8f16929504ef84d6aecae58d1e7ccc1e4d0821eb6388","target":"graph","created_at":"2026-05-17T23:55:34Z","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":"Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their interactions with the ego vehicle. One of the state-of-the-art approaches is to apply Reinforcement Learning (RL) to learn a time-sequential driving policy, to execute proper control strategy or tracking trajectory in dynamic situations. However, direct application of RL algorithms is not satisfactorily enough to deal with the cases in the autonomous driving domain, ","authors_text":"Ching-Yao Chan, Hanhan Li, Pin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-25T04:42:57Z","title":"Automated Driving Maneuvers under Interactive Environment based on Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09200","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":"sha256:772e09f42649f999a1ae0be41a84b428085920a822a4a4ba7ce3081bf8cdf8dd","target":"record","created_at":"2026-05-17T23:55:34Z","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":"597c7de70a505fd978b74f0358afff3e51401c933a51ed3f8bea94845eb80f0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-25T04:42:57Z","title_canon_sha256":"f0fb0778531c1ae061246b647e2169ebdaf7a9d9995cb01cc969f8b9c8216788"},"schema_version":"1.0","source":{"id":"1803.09200","kind":"arxiv","version":3}},"canonical_sha256":"7b3c7f3a8646dafbcee5fa2c80c1dfec16dbeec942422c701b9c360a4c2843af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b3c7f3a8646dafbcee5fa2c80c1dfec16dbeec942422c701b9c360a4c2843af","first_computed_at":"2026-05-17T23:55:34.537552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:34.537552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0X57uZfZ2mENaBaY37aH+dFncJewsQC84gB3yg+Q9PTB8Ckb8nPg3GJOI7JVi2IYe9gEAr37KEzZrh5lu48Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:34.537988Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09200","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:772e09f42649f999a1ae0be41a84b428085920a822a4a4ba7ce3081bf8cdf8dd","sha256:20c4c8a3007bcca1b73f8f16929504ef84d6aecae58d1e7ccc1e4d0821eb6388"],"state_sha256":"d0f0aa5444886f471d4a7a2fa96642cba5ea038e433b21d22c4464fcb271b825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XCGI8F0D0+bwJ0H2F9uhwLRdfhOc8ByVDp1Tr/oI0iz25vUZrItYk8FnWAxI+9VOS1pGZHZu9y3os4/GJ3jOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:03:07.824364Z","bundle_sha256":"1858ebe75d429800d57502d98f2b46e0868bbbfbcbf7e7dc30f0bba4fd1e6141"}}