{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ABCFEGSQM4GAXNJJ5DM4XAB2X","short_pith_number":"pith:6ABCFEGS","schema_version":"1.0","canonical_sha256":"f0022290d28338605da94f46ce5c01d5f626a77469e5b4a8b8a8ce132e315f28","source":{"kind":"arxiv","id":"2412.16201","version":1},"attestation_state":"computed","paper":{"title":"CLIP-RLDrive: Human-Aligned Autonomous Driving via CLIP-Based Reward Shaping in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Erfan Doroudian, Hamid Taghavifar","submitted_at":"2024-12-17T00:12:45Z","abstract_excerpt":"This paper presents CLIP-RLDrive, a new reinforcement learning (RL)-based framework for improving the decision-making of autonomous vehicles (AVs) in complex urban driving scenarios, particularly in unsignalized intersections. To achieve this goal, the decisions for AVs are aligned with human-like preferences through Contrastive Language-Image Pretraining (CLIP)-based reward shaping. One of the primary difficulties in RL scheme is designing a suitable reward model, which can often be challenging to achieve manually due to the complexity of the interactions and the driving scenarios. To deal wi"},"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":"2412.16201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T00:12:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"319937c151de191bd6d9d7a06035faa401a7a75b82eaf98847f7b97e032ab761","abstract_canon_sha256":"6fe16533a7b58fb171e344cf0b2d38869a32ebd339dc4bbba04c4967e832b4ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:42.960382Z","signature_b64":"u2bv862N7fdGVNZk6WQDzLWT0k0JpvKKuZbxL2bvLW4H0cT54PEHKfYtzHMa2+E1j8rTs638CqPLPBSUH6DLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0022290d28338605da94f46ce5c01d5f626a77469e5b4a8b8a8ce132e315f28","last_reissued_at":"2026-07-05T09:52:42.959947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:42.959947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-RLDrive: Human-Aligned Autonomous Driving via CLIP-Based Reward Shaping in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Erfan Doroudian, Hamid Taghavifar","submitted_at":"2024-12-17T00:12:45Z","abstract_excerpt":"This paper presents CLIP-RLDrive, a new reinforcement learning (RL)-based framework for improving the decision-making of autonomous vehicles (AVs) in complex urban driving scenarios, particularly in unsignalized intersections. To achieve this goal, the decisions for AVs are aligned with human-like preferences through Contrastive Language-Image Pretraining (CLIP)-based reward shaping. One of the primary difficulties in RL scheme is designing a suitable reward model, which can often be challenging to achieve manually due to the complexity of the interactions and the driving scenarios. To deal wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16201","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/2412.16201/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":"2412.16201","created_at":"2026-07-05T09:52:42.959998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16201v1","created_at":"2026-07-05T09:52:42.959998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16201","created_at":"2026-07-05T09:52:42.959998+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ABCFEGSQM4G","created_at":"2026-07-05T09:52:42.959998+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ABCFEGSQM4GAXNJ","created_at":"2026-07-05T09:52:42.959998+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ABCFEGS","created_at":"2026-07-05T09:52:42.959998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27994","citing_title":"Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27994","citing_title":"Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X","json":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X.json","graph_json":"https://pith.science/api/pith-number/6ABCFEGSQM4GAXNJJ5DM4XAB2X/graph.json","events_json":"https://pith.science/api/pith-number/6ABCFEGSQM4GAXNJJ5DM4XAB2X/events.json","paper":"https://pith.science/paper/6ABCFEGS"},"agent_actions":{"view_html":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X","download_json":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X.json","view_paper":"https://pith.science/paper/6ABCFEGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16201&json=true","fetch_graph":"https://pith.science/api/pith-number/6ABCFEGSQM4GAXNJJ5DM4XAB2X/graph.json","fetch_events":"https://pith.science/api/pith-number/6ABCFEGSQM4GAXNJJ5DM4XAB2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X/action/storage_attestation","attest_author":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X/action/author_attestation","sign_citation":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X/action/citation_signature","submit_replication":"https://pith.science/pith/6ABCFEGSQM4GAXNJJ5DM4XAB2X/action/replication_record"}},"created_at":"2026-07-05T09:52:42.959998+00:00","updated_at":"2026-07-05T09:52:42.959998+00:00"}