{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HDF4NFW2MT4Z4YDMV2F6VFO6WW","short_pith_number":"pith:HDF4NFW2","schema_version":"1.0","canonical_sha256":"38cbc696da64f99e606cae8bea95deb5a8f5f40d2fc1d56b462e1d2fca052e23","source":{"kind":"arxiv","id":"2606.24051","version":1},"attestation_state":"computed","paper":{"title":"DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aixue Ye, Guanglin Xu, Hao Su, Jingke Wang, Kai Tang, Shuangming Lei, Yijia Xie, Yong Liu, Yuehao Huang, Yukai Ma, Zhenru Zhao","submitted_at":"2026-06-23T01:40:54Z","abstract_excerpt":"Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language guidances. However, existing VLA driving models still lack driving-oriented spatial intelligence: their policies are mainly grounded on perspective image tokens and language priors, while precise motion planning requires metric geometry, top-down scene structure, and attention to safety-critical perceptual cues. This limitation makes current models vulnerable to weak visual geometry modeling and perceptual coverage in expert demonstrat"},"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":"2606.24051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T01:40:54Z","cross_cats_sorted":[],"title_canon_sha256":"e00afe48209c6c8dd9bac3ca728624b5236e50395da56657085798f7730674c4","abstract_canon_sha256":"59ba22936863297443ef77ae276ec9583a4f9e45fec650a1cf1025f9808a5546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:39.090493Z","signature_b64":"t6/0GMmr0aFM6aWUt1k5t5KGR3APM61hk1mWPtxbZSaUh+ngXHiM0xYgHKvM1FcJzchD+Aag0vOpl4o2NPa6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38cbc696da64f99e606cae8bea95deb5a8f5f40d2fc1d56b462e1d2fca052e23","last_reissued_at":"2026-06-24T01:14:39.090123Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:39.090123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aixue Ye, Guanglin Xu, Hao Su, Jingke Wang, Kai Tang, Shuangming Lei, Yijia Xie, Yong Liu, Yuehao Huang, Yukai Ma, Zhenru Zhao","submitted_at":"2026-06-23T01:40:54Z","abstract_excerpt":"Vision-Language-Action driving models convert a pretrained Vision-Language Model into a driving policy, allowing them to use world knowledge and follow language guidances. However, existing VLA driving models still lack driving-oriented spatial intelligence: their policies are mainly grounded on perspective image tokens and language priors, while precise motion planning requires metric geometry, top-down scene structure, and attention to safety-critical perceptual cues. This limitation makes current models vulnerable to weak visual geometry modeling and perceptual coverage in expert demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24051","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/2606.24051/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":"2606.24051","created_at":"2026-06-24T01:14:39.090184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24051v1","created_at":"2026-06-24T01:14:39.090184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24051","created_at":"2026-06-24T01:14:39.090184+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDF4NFW2MT4Z","created_at":"2026-06-24T01:14:39.090184+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDF4NFW2MT4Z4YDM","created_at":"2026-06-24T01:14:39.090184+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDF4NFW2","created_at":"2026-06-24T01:14:39.090184+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/HDF4NFW2MT4Z4YDMV2F6VFO6WW","json":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW.json","graph_json":"https://pith.science/api/pith-number/HDF4NFW2MT4Z4YDMV2F6VFO6WW/graph.json","events_json":"https://pith.science/api/pith-number/HDF4NFW2MT4Z4YDMV2F6VFO6WW/events.json","paper":"https://pith.science/paper/HDF4NFW2"},"agent_actions":{"view_html":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW","download_json":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW.json","view_paper":"https://pith.science/paper/HDF4NFW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24051&json=true","fetch_graph":"https://pith.science/api/pith-number/HDF4NFW2MT4Z4YDMV2F6VFO6WW/graph.json","fetch_events":"https://pith.science/api/pith-number/HDF4NFW2MT4Z4YDMV2F6VFO6WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW/action/storage_attestation","attest_author":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW/action/author_attestation","sign_citation":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW/action/citation_signature","submit_replication":"https://pith.science/pith/HDF4NFW2MT4Z4YDMV2F6VFO6WW/action/replication_record"}},"created_at":"2026-06-24T01:14:39.090184+00:00","updated_at":"2026-06-24T01:14:39.090184+00:00"}