{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZE5N333XVRCEHU6ZK3ESQUI7WM","short_pith_number":"pith:ZE5N333X","schema_version":"1.0","canonical_sha256":"c93addef77ac4443d3d956c928511fb3293a601d2c39d9eca6ecde276a4d7ed0","source":{"kind":"arxiv","id":"2505.17659","version":4},"attestation_state":"computed","paper":{"title":"Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Meina Kan, Shiguang Shan, Xiaolong Tang, Xilin Chen","submitted_at":"2025-05-23T09:22:19Z","abstract_excerpt":"Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting undesirable behaviors such as speeding from suboptimal human driving data. Inspired by the success of large language models, we propose Plan-R1, a two-stage trajectory planning framework that decouples principle alignment from behavior learning. In the first stage, a general trajectory predictor is pre-trained on expert data to capture diverse, human-li"},"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":"2505.17659","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-23T09:22:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7257ed6d8d536ea4db09ef87e2e00faf96e0dceea6e937b613bdeca103ca2423","abstract_canon_sha256":"81ff315adb02de4c19c61a5a16d01526f6dcc3905fd0ec1295220678d80eb8bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:06.210752Z","signature_b64":"7AQUUmi0E1XlYZE9lz1CYwyfyQO42fn4UUWiEFw7rvojJM+9g/Vmp4s0i72d1w0n3FaGeeSE04jHXPk3KOFDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c93addef77ac4443d3d956c928511fb3293a601d2c39d9eca6ecde276a4d7ed0","last_reissued_at":"2026-06-02T02:04:06.210273Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:06.210273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Meina Kan, Shiguang Shan, Xiaolong Tang, Xilin Chen","submitted_at":"2025-05-23T09:22:19Z","abstract_excerpt":"Safe and feasible trajectory planning is critical for real-world autonomous driving systems. However, existing learning-based planners rely heavily on expert demonstrations, which not only lack explicit safety awareness but also risk inheriting undesirable behaviors such as speeding from suboptimal human driving data. Inspired by the success of large language models, we propose Plan-R1, a two-stage trajectory planning framework that decouples principle alignment from behavior learning. In the first stage, a general trajectory predictor is pre-trained on expert data to capture diverse, human-li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17659","kind":"arxiv","version":4},"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/2505.17659/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":"2505.17659","created_at":"2026-06-02T02:04:06.210346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17659v4","created_at":"2026-06-02T02:04:06.210346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17659","created_at":"2026-06-02T02:04:06.210346+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZE5N333XVRCE","created_at":"2026-06-02T02:04:06.210346+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZE5N333XVRCEHU6Z","created_at":"2026-06-02T02:04:06.210346+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZE5N333X","created_at":"2026-06-02T02:04:06.210346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2603.13842","citing_title":"Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11734","citing_title":"SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11734","citing_title":"SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative Driving","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM","json":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM.json","graph_json":"https://pith.science/api/pith-number/ZE5N333XVRCEHU6ZK3ESQUI7WM/graph.json","events_json":"https://pith.science/api/pith-number/ZE5N333XVRCEHU6ZK3ESQUI7WM/events.json","paper":"https://pith.science/paper/ZE5N333X"},"agent_actions":{"view_html":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM","download_json":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM.json","view_paper":"https://pith.science/paper/ZE5N333X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17659&json=true","fetch_graph":"https://pith.science/api/pith-number/ZE5N333XVRCEHU6ZK3ESQUI7WM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZE5N333XVRCEHU6ZK3ESQUI7WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM/action/storage_attestation","attest_author":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM/action/author_attestation","sign_citation":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM/action/citation_signature","submit_replication":"https://pith.science/pith/ZE5N333XVRCEHU6ZK3ESQUI7WM/action/replication_record"}},"created_at":"2026-06-02T02:04:06.210346+00:00","updated_at":"2026-06-02T02:04:06.210346+00:00"}