{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UDW4A25Z4EZLYRTK6CAU3DTP2Q","short_pith_number":"pith:UDW4A25Z","schema_version":"1.0","canonical_sha256":"a0edc06bb9e132bc466af0814d8e6fd42a91b94b664aaca877f89260b25d48c8","source":{"kind":"arxiv","id":"2601.03309","version":2},"attestation_state":"computed","paper":{"title":"VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Zhang, Jianke Zhang, Jianyu Chen, Junyang Lin, Mingsheng Li, Qiuyue Wang, Shuai Bai, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","submitted_at":"2026-01-06T09:58:24Z","abstract_excerpt":"Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities. This paper revisits a fundamental yet seldom systematically studied question: how VLM choice and competence translate to downstream VLA policies performance? We introduce VLM4VLA, a minimal adaptation pipeline that converts general-purpose VLMs into VLA policies using only a small set of new learnable parameters for fair and efficient comparison. Despite its simplicity, VLM4VLA proves su"},"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":"2601.03309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-06T09:58:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"caa8a74983ef2ae11c317df055ac8ff5f11ca04219bfc3261d123713cacc1e90","abstract_canon_sha256":"7f47b7c10818700f4970ad428819cfb35810d8d702f98b55a0cc34a7320f6c55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:40.475539Z","signature_b64":"cGNMYpDdo3xtTPva2M2d8F1JnICK+skl9FyUSCb+6OBKQidBghqWvRvnRxBoRzRi4kX166Qv/Srev++huBVcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0edc06bb9e132bc466af0814d8e6fd42a91b94b664aaca877f89260b25d48c8","last_reissued_at":"2026-06-02T01:03:40.475031Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:40.475031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajun Zhang, Jianke Zhang, Jianyu Chen, Junyang Lin, Mingsheng Li, Qiuyue Wang, Shuai Bai, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","submitted_at":"2026-01-06T09:58:24Z","abstract_excerpt":"Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities. This paper revisits a fundamental yet seldom systematically studied question: how VLM choice and competence translate to downstream VLA policies performance? We introduce VLM4VLA, a minimal adaptation pipeline that converts general-purpose VLMs into VLA policies using only a small set of new learnable parameters for fair and efficient comparison. Despite its simplicity, VLM4VLA proves su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.03309","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/2601.03309/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":"2601.03309","created_at":"2026-06-02T01:03:40.475077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03309v2","created_at":"2026-06-02T01:03:40.475077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03309","created_at":"2026-06-02T01:03:40.475077+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDW4A25Z4EZL","created_at":"2026-06-02T01:03:40.475077+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDW4A25Z4EZLYRTK","created_at":"2026-06-02T01:03:40.475077+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDW4A25Z","created_at":"2026-06-02T01:03:40.475077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2605.22183","citing_title":"Action with Visual Primitives","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2602.19710","citing_title":"Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15735","citing_title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19282","citing_title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20323","citing_title":"PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06175","citing_title":"VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20012","citing_title":"EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06175","citing_title":"VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07381","citing_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13942","citing_title":"Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q","json":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q.json","graph_json":"https://pith.science/api/pith-number/UDW4A25Z4EZLYRTK6CAU3DTP2Q/graph.json","events_json":"https://pith.science/api/pith-number/UDW4A25Z4EZLYRTK6CAU3DTP2Q/events.json","paper":"https://pith.science/paper/UDW4A25Z"},"agent_actions":{"view_html":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q","download_json":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q.json","view_paper":"https://pith.science/paper/UDW4A25Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03309&json=true","fetch_graph":"https://pith.science/api/pith-number/UDW4A25Z4EZLYRTK6CAU3DTP2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/UDW4A25Z4EZLYRTK6CAU3DTP2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q/action/storage_attestation","attest_author":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q/action/author_attestation","sign_citation":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q/action/citation_signature","submit_replication":"https://pith.science/pith/UDW4A25Z4EZLYRTK6CAU3DTP2Q/action/replication_record"}},"created_at":"2026-06-02T01:03:40.475077+00:00","updated_at":"2026-06-02T01:03:40.475077+00:00"}