{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PWWGJR2LIQGM7YDU6IKKGGUCB","short_pith_number":"pith:3PWWGJR2","schema_version":"1.0","canonical_sha256":"dbed63263a5a20667f03a790a518d41065864a9bea9c7dd7d310fc704301c7de","source":{"kind":"arxiv","id":"2407.00959","version":1},"attestation_state":"computed","paper":{"title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Boris Ivanovic, Boyi Li, Edward Schmerling, Marco Pavone, Ran Tian, Xinshuo Weng, Yue Wang, Yuxiao Chen","submitted_at":"2024-07-01T04:34:50Z","abstract_excerpt":"The autonomous driving industry is increasingly adopting end-to-end learning from sensory inputs to minimize human biases in system design. Traditional end-to-end driving models, however, suffer from long-tail events due to rare or unseen inputs within their training distributions. To address this, we propose TOKEN, a novel Multi-Modal Large Language Model (MM-LLM) that tokenizes the world into object-level knowledge, enabling better utilization of LLM's reasoning capabilities to enhance autonomous vehicle planning in long-tail scenarios. TOKEN effectively alleviates data scarcity and ineffici"},"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":"2407.00959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-01T04:34:50Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"725966bee69cec68cb08f1a9edfd1235c7f8ed40793473c25bc570de2b9ff115","abstract_canon_sha256":"7ae7b1b0b81cb08dbf5b8b93954ceb069b2246e0d41e6dcdda8571065aed24b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:26.874134Z","signature_b64":"x1OrlbK4z/VJmFsTUi3Ix3hpb17++Nn2C+pCxT3jGNanxAszs7g8LJ2YbHWqPH4iYPfUpRLcPHrRL7JIt8yNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbed63263a5a20667f03a790a518d41065864a9bea9c7dd7d310fc704301c7de","last_reissued_at":"2026-07-05T08:38:26.873694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:26.873694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Boris Ivanovic, Boyi Li, Edward Schmerling, Marco Pavone, Ran Tian, Xinshuo Weng, Yue Wang, Yuxiao Chen","submitted_at":"2024-07-01T04:34:50Z","abstract_excerpt":"The autonomous driving industry is increasingly adopting end-to-end learning from sensory inputs to minimize human biases in system design. Traditional end-to-end driving models, however, suffer from long-tail events due to rare or unseen inputs within their training distributions. To address this, we propose TOKEN, a novel Multi-Modal Large Language Model (MM-LLM) that tokenizes the world into object-level knowledge, enabling better utilization of LLM's reasoning capabilities to enhance autonomous vehicle planning in long-tail scenarios. TOKEN effectively alleviates data scarcity and ineffici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00959","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/2407.00959/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":"2407.00959","created_at":"2026-07-05T08:38:26.873758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00959v1","created_at":"2026-07-05T08:38:26.873758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00959","created_at":"2026-07-05T08:38:26.873758+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PWWGJR2LIQG","created_at":"2026-07-05T08:38:26.873758+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PWWGJR2LIQGM7YD","created_at":"2026-07-05T08:38:26.873758+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PWWGJR2","created_at":"2026-07-05T08:38:26.873758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.26641","citing_title":"All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10564","citing_title":"DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04573","citing_title":"SAIL: Scene-aware Adaptive Iterative Learning for Long-Tail Trajectory Prediction in Autonomous Vehicles","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB","json":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB.json","graph_json":"https://pith.science/api/pith-number/3PWWGJR2LIQGM7YDU6IKKGGUCB/graph.json","events_json":"https://pith.science/api/pith-number/3PWWGJR2LIQGM7YDU6IKKGGUCB/events.json","paper":"https://pith.science/paper/3PWWGJR2"},"agent_actions":{"view_html":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB","download_json":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB.json","view_paper":"https://pith.science/paper/3PWWGJR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00959&json=true","fetch_graph":"https://pith.science/api/pith-number/3PWWGJR2LIQGM7YDU6IKKGGUCB/graph.json","fetch_events":"https://pith.science/api/pith-number/3PWWGJR2LIQGM7YDU6IKKGGUCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB/action/storage_attestation","attest_author":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB/action/author_attestation","sign_citation":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB/action/citation_signature","submit_replication":"https://pith.science/pith/3PWWGJR2LIQGM7YDU6IKKGGUCB/action/replication_record"}},"created_at":"2026-07-05T08:38:26.873758+00:00","updated_at":"2026-07-05T08:38:26.873758+00:00"}