{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FO3UGST5RMJL6OUDLXCE2LDPQ6","short_pith_number":"pith:FO3UGST5","schema_version":"1.0","canonical_sha256":"2bb7434a7d8b12bf3a835dc44d2c6f87a480da1b3e937c2f9ab0a5e9a46c0ce6","source":{"kind":"arxiv","id":"2512.00470","version":4},"attestation_state":"computed","paper":{"title":"LAP: Fast LAtent Diffusion Planner for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haoming Song, Jie Mei, Jinhao Zhang, Wenlong Xia, Youmin Gong, Zhexuan Zhou","submitted_at":"2025-11-29T12:45:05Z","abstract_excerpt":"Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial latency, and operating directly on raw trajectory points forces the model to spend capacity on low-level kinematics, rather than high-level multi-modal semantics. To address these limitations, we propose LAtent Planner (LAP), a framework that plans in a VAE-learned latent space that disentangles high-level intents from low-level kinematics, enabling our planner to capture rich, multi-modal driving strategies. To bridge "},"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":"2512.00470","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-29T12:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"3fabe4dc2ce6f51916cb1257e55d660569c59a16dcf24526631cec74b4da7710","abstract_canon_sha256":"562240c7d8f3e3adc3c584ad552b2665e84c0df68ce9e34230b649271657245c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:11.686529Z","signature_b64":"M4rwMzz/KGE2AQlvnEUYzC2amPNZaQ2YcYRIkJvX6l7SCLKS/TY5ItbZVZU7PBqWXc49mi7hZYcYde9wJuIBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bb7434a7d8b12bf3a835dc44d2c6f87a480da1b3e937c2f9ab0a5e9a46c0ce6","last_reissued_at":"2026-06-02T02:04:11.686012Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:11.686012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAP: Fast LAtent Diffusion Planner for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haoming Song, Jie Mei, Jinhao Zhang, Wenlong Xia, Youmin Gong, Zhexuan Zhou","submitted_at":"2025-11-29T12:45:05Z","abstract_excerpt":"Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial latency, and operating directly on raw trajectory points forces the model to spend capacity on low-level kinematics, rather than high-level multi-modal semantics. To address these limitations, we propose LAtent Planner (LAP), a framework that plans in a VAE-learned latent space that disentangles high-level intents from low-level kinematics, enabling our planner to capture rich, multi-modal driving strategies. To bridge "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00470","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/2512.00470/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":"2512.00470","created_at":"2026-06-02T02:04:11.686074+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.00470v4","created_at":"2026-06-02T02:04:11.686074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00470","created_at":"2026-06-02T02:04:11.686074+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO3UGST5RMJL","created_at":"2026-06-02T02:04:11.686074+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO3UGST5RMJL6OUD","created_at":"2026-06-02T02:04:11.686074+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO3UGST5","created_at":"2026-06-02T02:04:11.686074+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.09465","citing_title":"EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6","json":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6.json","graph_json":"https://pith.science/api/pith-number/FO3UGST5RMJL6OUDLXCE2LDPQ6/graph.json","events_json":"https://pith.science/api/pith-number/FO3UGST5RMJL6OUDLXCE2LDPQ6/events.json","paper":"https://pith.science/paper/FO3UGST5"},"agent_actions":{"view_html":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6","download_json":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6.json","view_paper":"https://pith.science/paper/FO3UGST5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.00470&json=true","fetch_graph":"https://pith.science/api/pith-number/FO3UGST5RMJL6OUDLXCE2LDPQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/FO3UGST5RMJL6OUDLXCE2LDPQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6/action/storage_attestation","attest_author":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6/action/author_attestation","sign_citation":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6/action/citation_signature","submit_replication":"https://pith.science/pith/FO3UGST5RMJL6OUDLXCE2LDPQ6/action/replication_record"}},"created_at":"2026-06-02T02:04:11.686074+00:00","updated_at":"2026-06-02T02:04:11.686074+00:00"}