{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GYE2EZG5AFV6LX6CFYI7SLSXBI","short_pith_number":"pith:GYE2EZG5","schema_version":"1.0","canonical_sha256":"3609a264dd016be5dfc22e11f92e570a099bd52c186fcf8213c1e92660b5aff2","source":{"kind":"arxiv","id":"2605.08830","version":2},"attestation_state":"computed","paper":{"title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"By routing tokens to separate vision-language and trajectory experts while sharing self-attention, VECTOR-DRIVE resolves the coupling trade-off in vision-language-action models for autonomous driving.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fei Gao, Jianlin Yu, Jiaqiao Liu, Rui Zhao, Zhenhai Gao","submitted_at":"2026-05-09T09:34:50Z","abstract_excerpt":"End-to-end autonomous driving requires models to understand traffic scenes, infer driving intent, and generate executable motion plans. Recent vision-language-action (VLA) models inherit semantic priors from large-scale vision-language pretraining, yet still face a coupling trade-off: fully shared backbones preserve multimodal interaction but may entangle language reasoning and trajectory prediction, whereas decou pled reasoning-action pipelines reduce task conflict but weaken semantic-motion coupling. We propose VECTOR-DRIVE, a tightly coupled VLA framework built on Qwen2.5-VL-3B. VECTOR-DRIV"},"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":"2605.08830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T09:34:50Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"fed3d9278d2e82a1d5fe4b16a3cbffb27d754832d4f16dcf86d9e434ca184089","abstract_canon_sha256":"25eda86a90ad4c9318dfca16e28520800778f162e04ab23c523ffabd0d748169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:16.132769Z","signature_b64":"h3bnJYdDjDt7sXNHolz8AcMr2Q2gVZAQ3R/i4WEYY8NCP7UMCH93PCGCV6lxDW1Mc3jpxx5hxHVtSnCIemHmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3609a264dd016be5dfc22e11f92e570a099bd52c186fcf8213c1e92660b5aff2","last_reissued_at":"2026-05-20T01:05:16.132006Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:16.132006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"By routing tokens to separate vision-language and trajectory experts while sharing self-attention, VECTOR-DRIVE resolves the coupling trade-off in vision-language-action models for autonomous driving.","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Fei Gao, Jianlin Yu, Jiaqiao Liu, Rui Zhao, Zhenhai Gao","submitted_at":"2026-05-09T09:34:50Z","abstract_excerpt":"End-to-end autonomous driving requires models to understand traffic scenes, infer driving intent, and generate executable motion plans. Recent vision-language-action (VLA) models inherit semantic priors from large-scale vision-language pretraining, yet still face a coupling trade-off: fully shared backbones preserve multimodal interaction but may entangle language reasoning and trajectory prediction, whereas decou pled reasoning-action pipelines reduce task conflict but weaken semantic-motion coupling. We propose VECTOR-DRIVE, a tightly coupled VLA framework built on Qwen2.5-VL-3B. VECTOR-DRIV"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On Bench2Drive, VECTOR-DRIVE achieves 88.91 Driving Score and outperforms representative end-to-end and VLA-based baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That routing tokens to separate experts according to semantics while keeping shared self-attention sufficiently preserves multimodal coupling without introducing new task conflicts or information loss.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VECTOR-DRIVE couples vision-language reasoning and trajectory planning in one Transformer via semantic expert routing and flow-matching, reaching 88.91 driving score on Bench2Drive.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"By routing tokens to separate vision-language and trajectory experts while sharing self-attention, VECTOR-DRIVE resolves the coupling trade-off in vision-language-action models for autonomous driving.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"485b5f85a72d212b78423e34c7d40ffb1cdef328b515c3e7abc17634331c72f9"},"source":{"id":"2605.08830","kind":"arxiv","version":2},"verdict":{"id":"fe341ff8-a9a3-41f2-98ba-01cd71cb830d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:44:57.024653Z","strongest_claim":"On Bench2Drive, VECTOR-DRIVE achieves 88.91 Driving Score and outperforms representative end-to-end and VLA-based baselines.","one_line_summary":"VECTOR-DRIVE couples vision-language reasoning and trajectory planning in one Transformer via semantic expert routing and flow-matching, reaching 88.91 driving score on Bench2Drive.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That routing tokens to separate experts according to semantics while keeping shared self-attention sufficiently preserves multimodal coupling without introducing new task conflicts or information loss.","pith_extraction_headline":"By routing tokens to separate vision-language and trajectory experts while sharing self-attention, VECTOR-DRIVE resolves the coupling trade-off in vision-language-action models for autonomous driving."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08830/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:34:02.009475Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:21.834211Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:47:58.717701Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8bedaf2e714cbc13af518ded835eb8ec1736b6191913fc6513f9bba188f129a4"},"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":"2605.08830","created_at":"2026-05-20T01:05:16.132087+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08830v2","created_at":"2026-05-20T01:05:16.132087+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08830","created_at":"2026-05-20T01:05:16.132087+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYE2EZG5AFV6","created_at":"2026-05-20T01:05:16.132087+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYE2EZG5AFV6LX6C","created_at":"2026-05-20T01:05:16.132087+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYE2EZG5","created_at":"2026-05-20T01:05:16.132087+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI","json":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI.json","graph_json":"https://pith.science/api/pith-number/GYE2EZG5AFV6LX6CFYI7SLSXBI/graph.json","events_json":"https://pith.science/api/pith-number/GYE2EZG5AFV6LX6CFYI7SLSXBI/events.json","paper":"https://pith.science/paper/GYE2EZG5"},"agent_actions":{"view_html":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI","download_json":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI.json","view_paper":"https://pith.science/paper/GYE2EZG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08830&json=true","fetch_graph":"https://pith.science/api/pith-number/GYE2EZG5AFV6LX6CFYI7SLSXBI/graph.json","fetch_events":"https://pith.science/api/pith-number/GYE2EZG5AFV6LX6CFYI7SLSXBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI/action/storage_attestation","attest_author":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI/action/author_attestation","sign_citation":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI/action/citation_signature","submit_replication":"https://pith.science/pith/GYE2EZG5AFV6LX6CFYI7SLSXBI/action/replication_record"}},"created_at":"2026-05-20T01:05:16.132087+00:00","updated_at":"2026-05-20T01:05:16.132087+00:00"}