{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WL3J6PMRY44PG355LTYMMTX7WD","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":"044729682193aae3642ebca35f7dd7dbd39a5c31569ca7c3f81fad0a2f275192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T03:34:32Z","title_canon_sha256":"4cec3af5f169d3e670bb007d1110a426175dffff91848dfcc78b68536cd162cb"},"schema_version":"1.0","source":{"id":"2607.01658","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01658","created_at":"2026-07-03T01:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01658v1","created_at":"2026-07-03T01:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01658","created_at":"2026-07-03T01:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"WL3J6PMRY44P","created_at":"2026-07-03T01:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"WL3J6PMRY44PG355","created_at":"2026-07-03T01:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"WL3J6PMR","created_at":"2026-07-03T01:17:25Z"}],"graph_snapshots":[{"event_id":"sha256:22b8c8a8e3a57c42e7f43799a6a7455e5164a8be633cb9f1f28aa65fc133a38c","target":"graph","created_at":"2026-07-03T01:17:25Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.01658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects ","authors_text":"Baochang Zhang, Bo Zhang, Canyu Chen, Chunyang Liu, Juan Zhang, Kehua Sheng, Linlin Yang, Xianbin Cao, Yan Wang, Yizhi Wang, Yuguang Yang, Zhewen Tan, Zichao Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T03:34:32Z","title":"Teaching Vision-Language-Action Models What to See and Where to Look"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01658","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2bfca7ce57ddc41ff8edfa61ea8071b24be44671fc6289e2edd3256f5f02246c","target":"record","created_at":"2026-07-03T01:17:25Z","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":"044729682193aae3642ebca35f7dd7dbd39a5c31569ca7c3f81fad0a2f275192","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T03:34:32Z","title_canon_sha256":"4cec3af5f169d3e670bb007d1110a426175dffff91848dfcc78b68536cd162cb"},"schema_version":"1.0","source":{"id":"2607.01658","kind":"arxiv","version":1}},"canonical_sha256":"b2f69f3d91c738f36fbd5cf0c64effb0d5ec03fb7dc31311b032f8557d9ee293","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2f69f3d91c738f36fbd5cf0c64effb0d5ec03fb7dc31311b032f8557d9ee293","first_computed_at":"2026-07-03T01:17:25.855105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:25.855105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rAlfNs8ZdlWroXkDhvz5SitzfG1+lKi2al/bE3CrN23R6EXeybQTmQsL+NlYf/HgoAO15wiuN/Ahja6u18iYDw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:25.855626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01658","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bfca7ce57ddc41ff8edfa61ea8071b24be44671fc6289e2edd3256f5f02246c","sha256:22b8c8a8e3a57c42e7f43799a6a7455e5164a8be633cb9f1f28aa65fc133a38c"],"state_sha256":"458234b9b86a61aac5e615c0df8c7e293b68f8c6f8302e7879b1307e6b0e3ebc"}