{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TLPP35VFNGMLA7V7VES752ZUTJ","short_pith_number":"pith:TLPP35VF","schema_version":"1.0","canonical_sha256":"9adefdf6a56998b07ebfa925feeb349a548e2dc2273bafd8244215d4ffe80f66","source":{"kind":"arxiv","id":"2605.31041","version":1},"attestation_state":"computed","paper":{"title":"Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongliang Lu, Jingtao He, Xiaoyun Qiu, Xinhu Zheng, Yixuan Wang","submitted_at":"2026-05-29T09:18:32Z","abstract_excerpt":"Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning. However, how current VLA-based driving behavior is grounded in visual information remains poorly understood. Existing evaluation protocols mainly focus on aggregate performance metrics, lacking structured and practical diagnostics to quantify visual-behavior dependency. In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in"},"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":"2605.31041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T09:18:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c4c040c531fc7552b3a7a4ac3af67fc1e45b98199448ba710cd9c572e58833a","abstract_canon_sha256":"698cca79e38f4a908fbf5be6034efc9c0c678975371954086b39ec837f5910fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:32.327470Z","signature_b64":"wdcFg3p7UPT9KTPpob2zBa9WPkEkGnxHe1+TMWDs2REh7s9VunMM57viUvI8VPgkBHX8XPsrJyMqErk+i8YwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9adefdf6a56998b07ebfa925feeb349a548e2dc2273bafd8244215d4ffe80f66","last_reissued_at":"2026-06-01T01:03:32.326297Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:32.326297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongliang Lu, Jingtao He, Xiaoyun Qiu, Xinhu Zheng, Yixuan Wang","submitted_at":"2026-05-29T09:18:32Z","abstract_excerpt":"Vision-Language-Action (VLA) models have demonstrated promising capability in autonomous driving, highlighting the potential of unified multimodal architectures for jointly modeling perception and planning. However, how current VLA-based driving behavior is grounded in visual information remains poorly understood. Existing evaluation protocols mainly focus on aggregate performance metrics, lacking structured and practical diagnostics to quantify visual-behavior dependency. In this work, we introduce a structured multi-level visual perturbation framework to analyze visual-behavior dependency in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31041","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/2605.31041/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":"2605.31041","created_at":"2026-06-01T01:03:32.326450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31041v1","created_at":"2026-06-01T01:03:32.326450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31041","created_at":"2026-06-01T01:03:32.326450+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLPP35VFNGML","created_at":"2026-06-01T01:03:32.326450+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLPP35VFNGMLA7V7","created_at":"2026-06-01T01:03:32.326450+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLPP35VF","created_at":"2026-06-01T01:03:32.326450+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/TLPP35VFNGMLA7V7VES752ZUTJ","json":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ.json","graph_json":"https://pith.science/api/pith-number/TLPP35VFNGMLA7V7VES752ZUTJ/graph.json","events_json":"https://pith.science/api/pith-number/TLPP35VFNGMLA7V7VES752ZUTJ/events.json","paper":"https://pith.science/paper/TLPP35VF"},"agent_actions":{"view_html":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ","download_json":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ.json","view_paper":"https://pith.science/paper/TLPP35VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31041&json=true","fetch_graph":"https://pith.science/api/pith-number/TLPP35VFNGMLA7V7VES752ZUTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TLPP35VFNGMLA7V7VES752ZUTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ/action/storage_attestation","attest_author":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ/action/author_attestation","sign_citation":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ/action/citation_signature","submit_replication":"https://pith.science/pith/TLPP35VFNGMLA7V7VES752ZUTJ/action/replication_record"}},"created_at":"2026-06-01T01:03:32.326450+00:00","updated_at":"2026-06-01T01:03:32.326450+00:00"}