{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CEN4AWJKP2MKFHQLXLECKWEERY","short_pith_number":"pith:CEN4AWJK","schema_version":"1.0","canonical_sha256":"111bc0592a7e98a29e0bbac82558848e208d8a95567bfc5838aa3e63c2945832","source":{"kind":"arxiv","id":"2309.04379","version":2},"attestation_state":"computed","paper":{"title":"Language Prompt for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-zhong Xu, Dongming Wu, Jianbing Shen, Tiancai Wang, Wencheng Han, Xiangyu Zhang, Yingfei Liu","submitted_at":"2023-09-08T15:21:07Z","abstract_excerpt":"A new trend in the computer vision community is to capture objects of interest following flexible human command represented by a natural language prompt. However, the progress of using language prompts in driving scenarios is stuck in a bottleneck due to the scarcity of paired prompt-instance data. To address this challenge, we propose the first object-centric language prompt set for driving scenes within 3D, multi-view, and multi-frame space, named NuPrompt. It expands nuScenes dataset by constructing a total of 40,147 language descriptions, each referring to an average of 7.4 object tracklet"},"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":"2309.04379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-08T15:21:07Z","cross_cats_sorted":[],"title_canon_sha256":"0361eeef0dadc6c17376d9b0b4d58c3a131ebb7990056854ce6f2cca15f8e559","abstract_canon_sha256":"75934e5ca783059589269c2747d59672c44fb7b878f9d7e196d846c35b71e1ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:10.329729Z","signature_b64":"vbXPRB9ZRp3GVxg2KgMo+oICcURaOVejjXA4rSHlZ8ZNRSdLWHUtrse/UxsyJrx7FvkSCfZNh8ISHI7UrSUHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111bc0592a7e98a29e0bbac82558848e208d8a95567bfc5838aa3e63c2945832","last_reissued_at":"2026-07-05T10:41:10.329207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:10.329207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Prompt for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-zhong Xu, Dongming Wu, Jianbing Shen, Tiancai Wang, Wencheng Han, Xiangyu Zhang, Yingfei Liu","submitted_at":"2023-09-08T15:21:07Z","abstract_excerpt":"A new trend in the computer vision community is to capture objects of interest following flexible human command represented by a natural language prompt. However, the progress of using language prompts in driving scenarios is stuck in a bottleneck due to the scarcity of paired prompt-instance data. To address this challenge, we propose the first object-centric language prompt set for driving scenes within 3D, multi-view, and multi-frame space, named NuPrompt. It expands nuScenes dataset by constructing a total of 40,147 language descriptions, each referring to an average of 7.4 object tracklet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04379","kind":"arxiv","version":2},"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/2309.04379/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":"2309.04379","created_at":"2026-07-05T10:41:10.329267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04379v2","created_at":"2026-07-05T10:41:10.329267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04379","created_at":"2026-07-05T10:41:10.329267+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEN4AWJKP2MK","created_at":"2026-07-05T10:41:10.329267+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEN4AWJKP2MKFHQL","created_at":"2026-07-05T10:41:10.329267+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEN4AWJK","created_at":"2026-07-05T10:41:10.329267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11507","citing_title":"SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05442","citing_title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07608","citing_title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2410.22313","citing_title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2402.12289","citing_title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY","json":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY.json","graph_json":"https://pith.science/api/pith-number/CEN4AWJKP2MKFHQLXLECKWEERY/graph.json","events_json":"https://pith.science/api/pith-number/CEN4AWJKP2MKFHQLXLECKWEERY/events.json","paper":"https://pith.science/paper/CEN4AWJK"},"agent_actions":{"view_html":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY","download_json":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY.json","view_paper":"https://pith.science/paper/CEN4AWJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04379&json=true","fetch_graph":"https://pith.science/api/pith-number/CEN4AWJKP2MKFHQLXLECKWEERY/graph.json","fetch_events":"https://pith.science/api/pith-number/CEN4AWJKP2MKFHQLXLECKWEERY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY/action/storage_attestation","attest_author":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY/action/author_attestation","sign_citation":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY/action/citation_signature","submit_replication":"https://pith.science/pith/CEN4AWJKP2MKFHQLXLECKWEERY/action/replication_record"}},"created_at":"2026-07-05T10:41:10.329267+00:00","updated_at":"2026-07-05T10:41:10.329267+00:00"}