{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KNRSITMYXWZ3HEYQVGK7XABJKD","short_pith_number":"pith:KNRSITMY","schema_version":"1.0","canonical_sha256":"5363244d98bdb3b39310a995fb802950d7d278d0e86f6b746cf569e6c7387d9d","source":{"kind":"arxiv","id":"2401.00125","version":1},"attestation_state":"computed","paper":{"title":"LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Francesco Pittaluga, Manmohan Chandraker, S P Sharan, Vijay Kumar B G","submitted_at":"2023-12-30T02:53:45Z","abstract_excerpt":"Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On the other hand, rule-based planners generalize well, but might fail to handle scenarios that require complex driving maneuvers. To address these limitations, we investigate the possibility of leveraging the common-sense reasoning capabilities of Large Language Models (LLMs) such as GPT4 and Llama2 "},"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":"2401.00125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-30T02:53:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4fe2ff6a93937bbdf062e9dc91ddb0d45920952ae7a968b497ae1815cce27ffc","abstract_canon_sha256":"3eb5060684d2ba75973441e1107f640a056108b894e33558a3ddd65902a6d7a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:01.062813Z","signature_b64":"QVPeneBo7eOnZa3Cea2mWGyFkfxzljxb8xKPilEwXszeq4Nnx+rPgzd5WrghQRC/zUvZ06VUaquOvJDCo1cICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5363244d98bdb3b39310a995fb802950d7d278d0e86f6b746cf569e6c7387d9d","last_reissued_at":"2026-07-05T07:29:01.062380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:01.062380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Francesco Pittaluga, Manmohan Chandraker, S P Sharan, Vijay Kumar B G","submitted_at":"2023-12-30T02:53:45Z","abstract_excerpt":"Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On the other hand, rule-based planners generalize well, but might fail to handle scenarios that require complex driving maneuvers. To address these limitations, we investigate the possibility of leveraging the common-sense reasoning capabilities of Large Language Models (LLMs) such as GPT4 and Llama2 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00125","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/2401.00125/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":"2401.00125","created_at":"2026-07-05T07:29:01.062441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00125v1","created_at":"2026-07-05T07:29:01.062441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00125","created_at":"2026-07-05T07:29:01.062441+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNRSITMYXWZ3","created_at":"2026-07-05T07:29:01.062441+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNRSITMYXWZ3HEYQ","created_at":"2026-07-05T07:29:01.062441+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNRSITMY","created_at":"2026-07-05T07:29:01.062441+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25509","citing_title":"ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17209","citing_title":"LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19220","citing_title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06040","citing_title":"Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD","json":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD.json","graph_json":"https://pith.science/api/pith-number/KNRSITMYXWZ3HEYQVGK7XABJKD/graph.json","events_json":"https://pith.science/api/pith-number/KNRSITMYXWZ3HEYQVGK7XABJKD/events.json","paper":"https://pith.science/paper/KNRSITMY"},"agent_actions":{"view_html":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD","download_json":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD.json","view_paper":"https://pith.science/paper/KNRSITMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00125&json=true","fetch_graph":"https://pith.science/api/pith-number/KNRSITMYXWZ3HEYQVGK7XABJKD/graph.json","fetch_events":"https://pith.science/api/pith-number/KNRSITMYXWZ3HEYQVGK7XABJKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD/action/storage_attestation","attest_author":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD/action/author_attestation","sign_citation":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD/action/citation_signature","submit_replication":"https://pith.science/pith/KNRSITMYXWZ3HEYQVGK7XABJKD/action/replication_record"}},"created_at":"2026-07-05T07:29:01.062441+00:00","updated_at":"2026-07-05T07:29:01.062441+00:00"}