{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BAKBOIAJTYRDNI7MVCW5OJ3HXV","short_pith_number":"pith:BAKBOIAJ","schema_version":"1.0","canonical_sha256":"08141720099e2236a3eca8add72767bd7eabbeca175a136446d13fd93f28454b","source":{"kind":"arxiv","id":"2103.09726","version":1},"attestation_state":"computed","paper":{"title":"Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Richard Bowden, Saber Fallah, Sampo Kuutti","submitted_at":"2021-03-17T15:30:36Z","abstract_excerpt":"The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision im"},"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":"2103.09726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-17T15:30:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"87ebe4978b3956a751121cb1de27c860958677076c49dc1de8cd1b967d1ec442","abstract_canon_sha256":"2ca99e60472d82b6c00a7c3148a9386a1f50c592e121e0aa3346cbd50f3edf16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:06.754966Z","signature_b64":"ky2l+rXCoB3cRf+cwZQ7r6Obxo/IThIq7WLWIfTV9IzIlpI0K5aM/Kn7uLYN84cO2Yk1Dgq20ysiwM66VohvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08141720099e2236a3eca8add72767bd7eabbeca175a136446d13fd93f28454b","last_reissued_at":"2026-07-05T02:24:06.754563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:06.754563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Richard Bowden, Saber Fallah, Sampo Kuutti","submitted_at":"2021-03-17T15:30:36Z","abstract_excerpt":"The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement learning based approach to autonomous vehicle longitudinal control, where the rule-based safety cages provide enhanced safety for the vehicle as well as weak supervision to the reinforcement learning agent. By guiding the agent to meaningful states and actions, this weak supervision im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09726","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/2103.09726/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":"2103.09726","created_at":"2026-07-05T02:24:06.754626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09726v1","created_at":"2026-07-05T02:24:06.754626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09726","created_at":"2026-07-05T02:24:06.754626+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAKBOIAJTYRD","created_at":"2026-07-05T02:24:06.754626+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAKBOIAJTYRDNI7M","created_at":"2026-07-05T02:24:06.754626+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAKBOIAJ","created_at":"2026-07-05T02:24:06.754626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV","json":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV.json","graph_json":"https://pith.science/api/pith-number/BAKBOIAJTYRDNI7MVCW5OJ3HXV/graph.json","events_json":"https://pith.science/api/pith-number/BAKBOIAJTYRDNI7MVCW5OJ3HXV/events.json","paper":"https://pith.science/paper/BAKBOIAJ"},"agent_actions":{"view_html":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV","download_json":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV.json","view_paper":"https://pith.science/paper/BAKBOIAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09726&json=true","fetch_graph":"https://pith.science/api/pith-number/BAKBOIAJTYRDNI7MVCW5OJ3HXV/graph.json","fetch_events":"https://pith.science/api/pith-number/BAKBOIAJTYRDNI7MVCW5OJ3HXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV/action/storage_attestation","attest_author":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV/action/author_attestation","sign_citation":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV/action/citation_signature","submit_replication":"https://pith.science/pith/BAKBOIAJTYRDNI7MVCW5OJ3HXV/action/replication_record"}},"created_at":"2026-07-05T02:24:06.754626+00:00","updated_at":"2026-07-05T02:24:06.754626+00:00"}