{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D3MLEUGMTFZJRNMILK7XT5RLWY","short_pith_number":"pith:D3MLEUGM","schema_version":"1.0","canonical_sha256":"1ed8b250cc997298b5885abf79f62bb61c0638e4b04f26c09072205bd5648821","source":{"kind":"arxiv","id":"2608.12932","version":1},"attestation_state":"computed","paper":{"title":"FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongfei Zhang, Jian Chen, Yesheng Liang, Yihao Liang, Zekai Li, Zhijian Liu","submitted_at":"2026-08-13T08:10:54Z","abstract_excerpt":"Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four. Visual encoding wastes compute on overlapping video frames; language-model prefill recomputes context that could be carried over from the previous timestep; reasoning tokens are generated serially despite low entropy; and flow-matching denoising applies uniform compute to a non-uniform velocity field. Addressing any one stage in i"},"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":"2608.12932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-13T08:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"9c857023a06f5085f9b23bb756536495823be011f53f4591568e548c2dbf0232","abstract_canon_sha256":"c001182c78cf8dba334e1b8b2bd5bad367bb242cb6df96823f4cb79874e2bade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:59:14.296017Z","signature_b64":"IKGZw633y2sJP4IlVo29wcvzwSrb4OKPDyKQufKU4aOMl62/ED7oiYo+oNz+836icvOZABSRN2/bO4P2ahhUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed8b250cc997298b5885abf79f62bb61c0638e4b04f26c09072205bd5648821","last_reissued_at":"2026-08-14T00:59:14.274988Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:59:14.274988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongfei Zhang, Jian Chen, Yesheng Liang, Yihao Liang, Zekai Li, Zhijian Liu","submitted_at":"2026-08-13T08:10:54Z","abstract_excerpt":"Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade of four. Visual encoding wastes compute on overlapping video frames; language-model prefill recomputes context that could be carried over from the previous timestep; reasoning tokens are generated serially despite low entropy; and flow-matching denoising applies uniform compute to a non-uniform velocity field. Addressing any one stage in i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12932","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/2608.12932/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":"2608.12932","created_at":"2026-08-14T00:59:14.294765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12932v1","created_at":"2026-08-14T00:59:14.294765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12932","created_at":"2026-08-14T00:59:14.294765+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3MLEUGMTFZJ","created_at":"2026-08-14T00:59:14.294765+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3MLEUGMTFZJRNMI","created_at":"2026-08-14T00:59:14.294765+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3MLEUGM","created_at":"2026-08-14T00:59:14.294765+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/D3MLEUGMTFZJRNMILK7XT5RLWY","json":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY.json","graph_json":"https://pith.science/api/pith-number/D3MLEUGMTFZJRNMILK7XT5RLWY/graph.json","events_json":"https://pith.science/api/pith-number/D3MLEUGMTFZJRNMILK7XT5RLWY/events.json","paper":"https://pith.science/paper/D3MLEUGM"},"agent_actions":{"view_html":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY","download_json":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY.json","view_paper":"https://pith.science/paper/D3MLEUGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12932&json=true","fetch_graph":"https://pith.science/api/pith-number/D3MLEUGMTFZJRNMILK7XT5RLWY/graph.json","fetch_events":"https://pith.science/api/pith-number/D3MLEUGMTFZJRNMILK7XT5RLWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY/action/storage_attestation","attest_author":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY/action/author_attestation","sign_citation":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY/action/citation_signature","submit_replication":"https://pith.science/pith/D3MLEUGMTFZJRNMILK7XT5RLWY/action/replication_record"}},"created_at":"2026-08-14T00:59:14.294765+00:00","updated_at":"2026-08-14T00:59:14.294765+00:00"}