{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GYE2EZG5AFV6LX6CFYI7SLSXBI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"25eda86a90ad4c9318dfca16e28520800778f162e04ab23c523ffabd0d748169","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T09:34:50Z","title_canon_sha256":"fed3d9278d2e82a1d5fe4b16a3cbffb27d754832d4f16dcf86d9e434ca184089"},"schema_version":"1.0","source":{"id":"2605.08830","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08830","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08830v2","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08830","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"GYE2EZG5AFV6","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"GYE2EZG5AFV6LX6C","created_at":"2026-05-20T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"GYE2EZG5","created_at":"2026-05-20T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:51593642fa023ad7c213faf53f4e60f6e94b7d0fa1c85cb0ffc15db8fa5e3ae2","target":"graph","created_at":"2026-05-20T01:05:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On Bench2Drive, VECTOR-DRIVE achieves 88.91 Driving Score and outperforms representative end-to-end and VLA-based baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"485b5f85a72d212b78423e34c7d40ffb1cdef328b515c3e7abc17634331c72f9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.08830/integrity.json","findings":[],"snapshot_sha256":"8bedaf2e714cbc13af518ded835eb8ec1736b6191913fc6513f9bba188f129a4","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fei Gao, Jianlin Yu, Jiaqiao Liu, Rui Zhao, Zhenhai Gao","cross_cats":["cs.AI","cs.RO"],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T09:34:50Z","title":"VECTOR-Drive: Tightly Coupled Vision-Language and Trajectory Expert Routing for End-to-End Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08830","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T01:44:57.024653Z","id":"fe341ff8-a9a3-41f2-98ba-01cd71cb830d","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"On Bench2Drive, VECTOR-DRIVE achieves 88.91 Driving Score and outperforms representative end-to-end and VLA-based baselines.","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."}},"verdict_id":"fe341ff8-a9a3-41f2-98ba-01cd71cb830d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ae4deda4f672e4224e972ccd558ceba0dfbb9c6bed93384b9e4009a373fbc6da","target":"record","created_at":"2026-05-20T01:05:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"25eda86a90ad4c9318dfca16e28520800778f162e04ab23c523ffabd0d748169","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T09:34:50Z","title_canon_sha256":"fed3d9278d2e82a1d5fe4b16a3cbffb27d754832d4f16dcf86d9e434ca184089"},"schema_version":"1.0","source":{"id":"2605.08830","kind":"arxiv","version":2}},"canonical_sha256":"3609a264dd016be5dfc22e11f92e570a099bd52c186fcf8213c1e92660b5aff2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3609a264dd016be5dfc22e11f92e570a099bd52c186fcf8213c1e92660b5aff2","first_computed_at":"2026-05-20T01:05:16.132006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:16.132006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h3bnJYdDjDt7sXNHolz8AcMr2Q2gVZAQ3R/i4WEYY8NCP7UMCH93PCGCV6lxDW1Mc3jpxx5hxHVtSnCIemHmCg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:16.132769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08830","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae4deda4f672e4224e972ccd558ceba0dfbb9c6bed93384b9e4009a373fbc6da","sha256:51593642fa023ad7c213faf53f4e60f6e94b7d0fa1c85cb0ffc15db8fa5e3ae2"],"state_sha256":"a569e2a5985136cf1ec171d0189950504ee63c31e463a65f62084312183a3b3e"}