{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWOWB2TDCKJ3I46XJ5BKTFSJ3W","short_pith_number":"pith:LWOWB2TD","schema_version":"1.0","canonical_sha256":"5d9d60ea631293b473d74f42a99649dda22e476b665ca4ef4c7c446f429d0793","source":{"kind":"arxiv","id":"2412.15208","version":2},"attestation_state":"computed","paper":{"title":"OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengyuan Qian, Hongyuan Hua, Kexin Tian, Shuo Xing, Yang Zhou, Yuping Wang, Zhengzhong Tu","submitted_at":"2024-12-19T18:59:40Z","abstract_excerpt":"Since the advent of Multimodal Large Language Models (MLLMs), they have made a significant impact across a wide range of real-world applications, particularly in Autonomous Driving (AD). Their ability to process complex visual data and reason about intricate driving scenarios has paved the way for a new paradigm in end-to-end AD systems. However, the progress of developing end-to-end models for AD has been slow, as existing fine-tuning methods demand substantial resources, including extensive computational power, large-scale datasets, and significant funding. Drawing inspiration from recent ad"},"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":"2412.15208","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:59:40Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"b21210a0c322ae5b0668199f7338a1c8e2aeacb312ae167d62208490f85adc8d","abstract_canon_sha256":"6cea2946fc3c6cf7edc117cd7ed417ef5a674db7ecb674e964496c1851981ae8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:49.376983Z","signature_b64":"qQsG1spqDEUvVnvb7RW9pMzrbDpLMwJdU7+YnsHi3b41STHU+2lUIypA8PWcUrMBZsE5p08OZg2go7Hn7vCkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d9d60ea631293b473d74f42a99649dda22e476b665ca4ef4c7c446f429d0793","last_reissued_at":"2026-07-05T10:14:49.376464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:49.376464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Chengyuan Qian, Hongyuan Hua, Kexin Tian, Shuo Xing, Yang Zhou, Yuping Wang, Zhengzhong Tu","submitted_at":"2024-12-19T18:59:40Z","abstract_excerpt":"Since the advent of Multimodal Large Language Models (MLLMs), they have made a significant impact across a wide range of real-world applications, particularly in Autonomous Driving (AD). Their ability to process complex visual data and reason about intricate driving scenarios has paved the way for a new paradigm in end-to-end AD systems. However, the progress of developing end-to-end models for AD has been slow, as existing fine-tuning methods demand substantial resources, including extensive computational power, large-scale datasets, and significant funding. Drawing inspiration from recent ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15208","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/2412.15208/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":"2412.15208","created_at":"2026-07-05T10:14:49.376529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15208v2","created_at":"2026-07-05T10:14:49.376529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15208","created_at":"2026-07-05T10:14:49.376529+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWOWB2TDCKJ3","created_at":"2026-07-05T10:14:49.376529+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWOWB2TDCKJ3I46X","created_at":"2026-07-05T10:14:49.376529+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWOWB2TD","created_at":"2026-07-05T10:14:49.376529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31116","citing_title":"NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15925","citing_title":"VERDI: VLM-Embedded Reasoning for Autonomous Driving","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17915","citing_title":"OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W","json":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W.json","graph_json":"https://pith.science/api/pith-number/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/graph.json","events_json":"https://pith.science/api/pith-number/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/events.json","paper":"https://pith.science/paper/LWOWB2TD"},"agent_actions":{"view_html":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W","download_json":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W.json","view_paper":"https://pith.science/paper/LWOWB2TD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15208&json=true","fetch_graph":"https://pith.science/api/pith-number/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/graph.json","fetch_events":"https://pith.science/api/pith-number/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/action/storage_attestation","attest_author":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/action/author_attestation","sign_citation":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/action/citation_signature","submit_replication":"https://pith.science/pith/LWOWB2TDCKJ3I46XJ5BKTFSJ3W/action/replication_record"}},"created_at":"2026-07-05T10:14:49.376529+00:00","updated_at":"2026-07-05T10:14:49.376529+00:00"}