{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UOKS7LN2XAYPSPCAX2EI5ZB2KF","short_pith_number":"pith:UOKS7LN2","schema_version":"1.0","canonical_sha256":"a3952fadbab830f93c40be888ee43a515e1f4e159b2b5b05e16b5e18654a53a4","source":{"kind":"arxiv","id":"2605.30576","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ahmed Abouelazm, Felix Klingebiel, J. Marius Z\\\"ollner, Philip Sch\\\"orner","submitted_at":"2026-05-28T21:09:44Z","abstract_excerpt":"Exploration in reinforcement learning for autonomous driving is inherently unsafe: agents must experience novel behaviors to learn, yet exploration can lead to collisions or off-road driving. We propose an uncertainty-aware framework that leverages expert advice to guide exploration while avoiding long-term dependence. Advice is triggered when epistemic or aleatoric uncertainty exceeds adaptive thresholds derived from rolling buffers, ensuring advice evolves with the agent's confidence. A commitment-cooldown strategy with a stochastic early-stop heuristic regulates the duration and frequency o"},"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":"2605.30576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T21:09:44Z","cross_cats_sorted":[],"title_canon_sha256":"803edee786fac682403c39721a24787db59238e71d6428867fceba92258ef913","abstract_canon_sha256":"40164bb186da5575f199f4cd7e2e3f9a44aa519ebd0b6dd29ad8ad2f4cdba867"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:02.108463Z","signature_b64":"OJjXMBeEb81RyIUcyiwUR/aKlnCRpLhGKVJB6i/fvIad/3IcABQoqbWLLEXRE1PhZf71p9vv2SyAwBiWuE7uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3952fadbab830f93c40be888ee43a515e1f4e159b2b5b05e16b5e18654a53a4","last_reissued_at":"2026-06-01T01:03:02.107543Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:02.107543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ahmed Abouelazm, Felix Klingebiel, J. Marius Z\\\"ollner, Philip Sch\\\"orner","submitted_at":"2026-05-28T21:09:44Z","abstract_excerpt":"Exploration in reinforcement learning for autonomous driving is inherently unsafe: agents must experience novel behaviors to learn, yet exploration can lead to collisions or off-road driving. We propose an uncertainty-aware framework that leverages expert advice to guide exploration while avoiding long-term dependence. Advice is triggered when epistemic or aleatoric uncertainty exceeds adaptive thresholds derived from rolling buffers, ensuring advice evolves with the agent's confidence. A commitment-cooldown strategy with a stochastic early-stop heuristic regulates the duration and frequency o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30576","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/2605.30576/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":"2605.30576","created_at":"2026-06-01T01:03:02.107699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30576v1","created_at":"2026-06-01T01:03:02.107699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30576","created_at":"2026-06-01T01:03:02.107699+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOKS7LN2XAYP","created_at":"2026-06-01T01:03:02.107699+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOKS7LN2XAYPSPCA","created_at":"2026-06-01T01:03:02.107699+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOKS7LN2","created_at":"2026-06-01T01:03:02.107699+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/UOKS7LN2XAYPSPCAX2EI5ZB2KF","json":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF.json","graph_json":"https://pith.science/api/pith-number/UOKS7LN2XAYPSPCAX2EI5ZB2KF/graph.json","events_json":"https://pith.science/api/pith-number/UOKS7LN2XAYPSPCAX2EI5ZB2KF/events.json","paper":"https://pith.science/paper/UOKS7LN2"},"agent_actions":{"view_html":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF","download_json":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF.json","view_paper":"https://pith.science/paper/UOKS7LN2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30576&json=true","fetch_graph":"https://pith.science/api/pith-number/UOKS7LN2XAYPSPCAX2EI5ZB2KF/graph.json","fetch_events":"https://pith.science/api/pith-number/UOKS7LN2XAYPSPCAX2EI5ZB2KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF/action/storage_attestation","attest_author":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF/action/author_attestation","sign_citation":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF/action/citation_signature","submit_replication":"https://pith.science/pith/UOKS7LN2XAYPSPCAX2EI5ZB2KF/action/replication_record"}},"created_at":"2026-06-01T01:03:02.107699+00:00","updated_at":"2026-06-01T01:03:02.107699+00:00"}