{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYN4ZZHEEJZKXCGDWL25CVBSBG","short_pith_number":"pith:GYN4ZZHE","schema_version":"1.0","canonical_sha256":"361bcce4e42272ab88c3b2f5d1543209973036e865b04faacbe22e1de6247f64","source":{"kind":"arxiv","id":"2409.15250","version":3},"attestation_state":"computed","paper":{"title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool, Nikolay Nikolov, Sombit Dey","submitted_at":"2024-09-23T17:47:59Z","abstract_excerpt":"Recent progress in large language models and access to large-scale robotic datasets has sparked a paradigm shift in robotics models transforming them into generalists able to adapt to various tasks, scenes, and robot modalities. A large step for the community are open Vision Language Action models which showcase strong performance in a wide variety of tasks. In this work, we study the visual generalization capabilities of three existing robotic foundation models, and propose a corresponding evaluation framework. Our study shows that the existing models do not exhibit robustness to visual out-o"},"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":"2409.15250","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-23T17:47:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3b210b11a53acb3dc8b667a9214462f9a100bbaa6028dec1ca7d112f1afc288f","abstract_canon_sha256":"bba5c57122d870a4182b2f2cdc8ce7864d9c05c293443ed18b0122ff7a9e4816"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:09.136404Z","signature_b64":"TeZ5hLPPXn0lCKwc0vzhJ4G3y7T0CwpLKv2zKMJSbMlXFTP7C9iMY9udBOTN0mPu7lQqPrK5SWLlcGykXol3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"361bcce4e42272ab88c3b2f5d1543209973036e865b04faacbe22e1de6247f64","last_reissued_at":"2026-07-05T11:06:09.135754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:09.135754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool, Nikolay Nikolov, Sombit Dey","submitted_at":"2024-09-23T17:47:59Z","abstract_excerpt":"Recent progress in large language models and access to large-scale robotic datasets has sparked a paradigm shift in robotics models transforming them into generalists able to adapt to various tasks, scenes, and robot modalities. A large step for the community are open Vision Language Action models which showcase strong performance in a wide variety of tasks. In this work, we study the visual generalization capabilities of three existing robotic foundation models, and propose a corresponding evaluation framework. Our study shows that the existing models do not exhibit robustness to visual out-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15250","kind":"arxiv","version":3},"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/2409.15250/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":"2409.15250","created_at":"2026-07-05T11:06:09.135818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15250v3","created_at":"2026-07-05T11:06:09.135818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15250","created_at":"2026-07-05T11:06:09.135818+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYN4ZZHEEJZK","created_at":"2026-07-05T11:06:09.135818+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYN4ZZHEEJZKXCGD","created_at":"2026-07-05T11:06:09.135818+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYN4ZZHE","created_at":"2026-07-05T11:06:09.135818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12403","citing_title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10126","citing_title":"AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06175","citing_title":"VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06175","citing_title":"VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG","json":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG.json","graph_json":"https://pith.science/api/pith-number/GYN4ZZHEEJZKXCGDWL25CVBSBG/graph.json","events_json":"https://pith.science/api/pith-number/GYN4ZZHEEJZKXCGDWL25CVBSBG/events.json","paper":"https://pith.science/paper/GYN4ZZHE"},"agent_actions":{"view_html":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG","download_json":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG.json","view_paper":"https://pith.science/paper/GYN4ZZHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15250&json=true","fetch_graph":"https://pith.science/api/pith-number/GYN4ZZHEEJZKXCGDWL25CVBSBG/graph.json","fetch_events":"https://pith.science/api/pith-number/GYN4ZZHEEJZKXCGDWL25CVBSBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG/action/storage_attestation","attest_author":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG/action/author_attestation","sign_citation":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG/action/citation_signature","submit_replication":"https://pith.science/pith/GYN4ZZHEEJZKXCGDWL25CVBSBG/action/replication_record"}},"created_at":"2026-07-05T11:06:09.135818+00:00","updated_at":"2026-07-05T11:06:09.135818+00:00"}