{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:34NJIUMKWOQJ7M47CWQGJOOLVW","short_pith_number":"pith:34NJIUMK","schema_version":"1.0","canonical_sha256":"df1a94518ab3a09fb39f15a064b9cbad9252b81cd2f485f65b6f328f1290c735","source":{"kind":"arxiv","id":"2606.08684","version":1},"attestation_state":"computed","paper":{"title":"BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Ling, Hao Yang, Lijin Yang, Zhongzhan Huang","submitted_at":"2026-06-07T15:37:16Z","abstract_excerpt":"We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive analysis, we reveal that language matters on only a small fraction of routes, but on those routes it can greatly improve or degrade performance. Generating language at every frame is therefore inefficient, since most computation is spent on frames that do not benefit from language. We further show that pretrained VLA hidden states potentially already encode whether language will benefit a given frame, even though scene complexity and kinematic features"},"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":"2606.08684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-07T15:37:16Z","cross_cats_sorted":[],"title_canon_sha256":"1315075c29b9032eba1a4a7d8dbc6626556269ef895092fd82510a867655457c","abstract_canon_sha256":"9cf84e445b51ec5da29a2579e6b3d07d5bd282040c20fbd0309f4ecd7332e64f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:47.386536Z","signature_b64":"/S2gC19W/AnWZqGulGzNB2Y9MWa86PDGePA/7b0pqxLjOOHqDJYJGOY4tREJGOdu2BdqGO4cl7qVLvZzQIS8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df1a94518ab3a09fb39f15a064b9cbad9252b81cd2f485f65b6f328f1290c735","last_reissued_at":"2026-06-09T01:05:47.386121Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:47.386121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BLUE: Toward Better Language Use in Efficient Vision-Language-Action Models for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"George Ling, Hao Yang, Lijin Yang, Zhongzhan Huang","submitted_at":"2026-06-07T15:37:16Z","abstract_excerpt":"We present BLUE, a minimal method for better language use in vision-language-action (VLA) models for autonomous driving (AD). Through extensive analysis, we reveal that language matters on only a small fraction of routes, but on those routes it can greatly improve or degrade performance. Generating language at every frame is therefore inefficient, since most computation is spent on frames that do not benefit from language. We further show that pretrained VLA hidden states potentially already encode whether language will benefit a given frame, even though scene complexity and kinematic features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08684","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/2606.08684/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":"2606.08684","created_at":"2026-06-09T01:05:47.386177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08684v1","created_at":"2026-06-09T01:05:47.386177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08684","created_at":"2026-06-09T01:05:47.386177+00:00"},{"alias_kind":"pith_short_12","alias_value":"34NJIUMKWOQJ","created_at":"2026-06-09T01:05:47.386177+00:00"},{"alias_kind":"pith_short_16","alias_value":"34NJIUMKWOQJ7M47","created_at":"2026-06-09T01:05:47.386177+00:00"},{"alias_kind":"pith_short_8","alias_value":"34NJIUMK","created_at":"2026-06-09T01:05:47.386177+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/34NJIUMKWOQJ7M47CWQGJOOLVW","json":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW.json","graph_json":"https://pith.science/api/pith-number/34NJIUMKWOQJ7M47CWQGJOOLVW/graph.json","events_json":"https://pith.science/api/pith-number/34NJIUMKWOQJ7M47CWQGJOOLVW/events.json","paper":"https://pith.science/paper/34NJIUMK"},"agent_actions":{"view_html":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW","download_json":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW.json","view_paper":"https://pith.science/paper/34NJIUMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08684&json=true","fetch_graph":"https://pith.science/api/pith-number/34NJIUMKWOQJ7M47CWQGJOOLVW/graph.json","fetch_events":"https://pith.science/api/pith-number/34NJIUMKWOQJ7M47CWQGJOOLVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW/action/storage_attestation","attest_author":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW/action/author_attestation","sign_citation":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW/action/citation_signature","submit_replication":"https://pith.science/pith/34NJIUMKWOQJ7M47CWQGJOOLVW/action/replication_record"}},"created_at":"2026-06-09T01:05:47.386177+00:00","updated_at":"2026-06-09T01:05:47.386177+00:00"}