{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DDKKFTY6SNBDUDLJCSAAPUCUYY","short_pith_number":"pith:DDKKFTY6","schema_version":"1.0","canonical_sha256":"18d4a2cf1e93423a0d69148007d054c60da93b43672bc4ddad328dd90c83b7f8","source":{"kind":"arxiv","id":"2602.10719","version":2},"attestation_state":"computed","paper":{"title":"From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bingchuan Sun, Canyu Chen, Cheng Chi, Chenxu Dang, Haiyan Liu, Jason Bao, Sining Ang, Xuanyao Mao, Xuliang, Yan Wang, Yuguang Yang","submitted_at":"2026-02-11T10:25:05Z","abstract_excerpt":"Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vision-language models (VLMs) differ from standard vision-only encoders and whether these differences survive policy learning. We study this question under a unified VLM-hidden + diffusion-policy paradigm, comparing multiple VLM families/scales (e.g., InternVL3 and Qwen3VL) with vision-only encoders (e.g., ResNet, ViT, and EVA-CLIP). We ask three questions: how similar are their representations, do residual differences induce meaningful behavioral differenc"},"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":"2602.10719","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-11T10:25:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8b901d5159499fac365aef087efcddaefc1978a85b151c4248f6dbcc313aa6e0","abstract_canon_sha256":"3185036e276c23551ad5689348d7bf5d1af4045446e5c8d8791cf01c1c819ac3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:03.730286Z","signature_b64":"p2IKofSZq2Db6Ek4uUFIrXFq2cH0vYNd54ZOYb+Q4wKcSrtIbK+2pgRFqequRg+O3NDLR1QgvW1FOfQvh8pKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18d4a2cf1e93423a0d69148007d054c60da93b43672bc4ddad328dd90c83b7f8","last_reissued_at":"2026-08-04T00:36:03.728159Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:03.728159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bingchuan Sun, Canyu Chen, Cheng Chi, Chenxu Dang, Haiyan Liu, Jason Bao, Sining Ang, Xuanyao Mao, Xuliang, Yan Wang, Yuguang Yang","submitted_at":"2026-02-11T10:25:05Z","abstract_excerpt":"Vision-Language-Action (VLA) driving augments end-to-end (E2E) planning with language-enabled visual backbones, yet it remains unclear how vision-language models (VLMs) differ from standard vision-only encoders and whether these differences survive policy learning. We study this question under a unified VLM-hidden + diffusion-policy paradigm, comparing multiple VLM families/scales (e.g., InternVL3 and Qwen3VL) with vision-only encoders (e.g., ResNet, ViT, and EVA-CLIP). We ask three questions: how similar are their representations, do residual differences induce meaningful behavioral differenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10719","kind":"arxiv","version":2},"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/2602.10719/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":"2602.10719","created_at":"2026-08-04T00:36:03.729414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10719v2","created_at":"2026-08-04T00:36:03.729414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10719","created_at":"2026-08-04T00:36:03.729414+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDKKFTY6SNBD","created_at":"2026-08-04T00:36:03.729414+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDKKFTY6SNBDUDLJ","created_at":"2026-08-04T00:36:03.729414+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDKKFTY6","created_at":"2026-08-04T00:36:03.729414+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/DDKKFTY6SNBDUDLJCSAAPUCUYY","json":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY.json","graph_json":"https://pith.science/api/pith-number/DDKKFTY6SNBDUDLJCSAAPUCUYY/graph.json","events_json":"https://pith.science/api/pith-number/DDKKFTY6SNBDUDLJCSAAPUCUYY/events.json","paper":"https://pith.science/paper/DDKKFTY6"},"agent_actions":{"view_html":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY","download_json":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY.json","view_paper":"https://pith.science/paper/DDKKFTY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10719&json=true","fetch_graph":"https://pith.science/api/pith-number/DDKKFTY6SNBDUDLJCSAAPUCUYY/graph.json","fetch_events":"https://pith.science/api/pith-number/DDKKFTY6SNBDUDLJCSAAPUCUYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY/action/storage_attestation","attest_author":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY/action/author_attestation","sign_citation":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY/action/citation_signature","submit_replication":"https://pith.science/pith/DDKKFTY6SNBDUDLJCSAAPUCUYY/action/replication_record"}},"created_at":"2026-08-04T00:36:03.729414+00:00","updated_at":"2026-08-04T00:36:03.729414+00:00"}