{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZUES2QTW6CSKJW4K4DBIKMDPAJ","short_pith_number":"pith:ZUES2QTW","schema_version":"1.0","canonical_sha256":"cd092d4276f0a4a4db8ae0c285306f024d834bc761de100df11349a105ec8bb7","source":{"kind":"arxiv","id":"2607.23617","version":1},"attestation_state":"computed","paper":{"title":"Optimal Reward Shaping: Autonomous Car Parking Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Emre \\\"Ozkaya, Nicolas R. Gauger","submitted_at":"2026-07-26T11:49:23Z","abstract_excerpt":"Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance. In this work, we present a parameterized reward shaping framework featuring coverage-gated alignment feedback, drive-direction switch regularization, and an aligned episode termination mechanism evaluated on an autonomous parallel parking task. Crucially, we show that environmental reward parameters and algorithmic hyperparameters are deeply co-dependent, "},"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":"2607.23617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:49:23Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"5b63ab759728e7bc52a860c15e150cc54f3836451e99ccac70076fd0165b30b9","abstract_canon_sha256":"9344ebb6e8bd76db735ae6f4a82fd4ad5093222c564ecc8e819d3b9772057403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:02.146996Z","signature_b64":"tTdYHp4WxJVHib9LZtbnmCbiDVIYErJby2QTPY5UHx5TDLKKTVbp0Buf/36ppHk7KKF4LkIgoCQWnUGBlVunBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd092d4276f0a4a4db8ae0c285306f024d834bc761de100df11349a105ec8bb7","last_reissued_at":"2026-07-28T01:23:02.146170Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:02.146170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Reward Shaping: Autonomous Car Parking Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Emre \\\"Ozkaya, Nicolas R. Gauger","submitted_at":"2026-07-26T11:49:23Z","abstract_excerpt":"Designing effective reward functions for model-free reinforcement learning under non-holonomic constraints remains a persistent challenge, often resulting in severe local minima such as policy paralysis or over-conservative hazard avoidance. In this work, we present a parameterized reward shaping framework featuring coverage-gated alignment feedback, drive-direction switch regularization, and an aligned episode termination mechanism evaluated on an autonomous parallel parking task. Crucially, we show that environmental reward parameters and algorithmic hyperparameters are deeply co-dependent, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23617","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/2607.23617/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":"2607.23617","created_at":"2026-07-28T01:23:02.146599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23617v1","created_at":"2026-07-28T01:23:02.146599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23617","created_at":"2026-07-28T01:23:02.146599+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUES2QTW6CSK","created_at":"2026-07-28T01:23:02.146599+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUES2QTW6CSKJW4K","created_at":"2026-07-28T01:23:02.146599+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUES2QTW","created_at":"2026-07-28T01:23:02.146599+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/ZUES2QTW6CSKJW4K4DBIKMDPAJ","json":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ.json","graph_json":"https://pith.science/api/pith-number/ZUES2QTW6CSKJW4K4DBIKMDPAJ/graph.json","events_json":"https://pith.science/api/pith-number/ZUES2QTW6CSKJW4K4DBIKMDPAJ/events.json","paper":"https://pith.science/paper/ZUES2QTW"},"agent_actions":{"view_html":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ","download_json":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ.json","view_paper":"https://pith.science/paper/ZUES2QTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23617&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUES2QTW6CSKJW4K4DBIKMDPAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUES2QTW6CSKJW4K4DBIKMDPAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZUES2QTW6CSKJW4K4DBIKMDPAJ/action/replication_record"}},"created_at":"2026-07-28T01:23:02.146599+00:00","updated_at":"2026-07-28T01:23:02.146599+00:00"}