{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:57BKKR5LLLARYVXE44OU4D376A","short_pith_number":"pith:57BKKR5L","schema_version":"1.0","canonical_sha256":"efc2a547ab5ac11c56e4e71d4e0f7ff0306f60e690aca70f9f31455fe9e1e113","source":{"kind":"arxiv","id":"2506.09930","version":1},"attestation_state":"computed","paper":{"title":"From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Feng, Irving Fang, Juexiao Zhang, Shengbang Tong","submitted_at":"2025-06-11T16:52:18Z","abstract_excerpt":"One promise that Vision-Language-Action (VLA) models hold over traditional imitation learning for robotics is to leverage the broad generalization capabilities of large Vision-Language Models (VLMs) to produce versatile, \"generalist\" robot policies. However, current evaluations of VLAs remain insufficient. Traditional imitation learning benchmarks are unsuitable due to the lack of language instructions. Emerging benchmarks for VLAs that incorporate language often come with limited evaluation tasks and do not intend to investigate how much VLM pretraining truly contributes to the generalization"},"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":"2506.09930","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-11T16:52:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"36e3617ecb0059688f60d27a1bac7e619a03517a4dabff158b81cf68529cfaa6","abstract_canon_sha256":"8661817b700b511c79eb2bf36f29f3b34f055655ae523fb4eb85ecd7077e5d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:58.895337Z","signature_b64":"VDOZjj1b/ueEsHQ/hlZhrBVyPmtrqz2K+zwm79S19l2ZOHRHFVT9giObGwpytyfizXRGt8ewri0nHOOV/uzJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc2a547ab5ac11c56e4e71d4e0f7ff0306f60e690aca70f9f31455fe9e1e113","last_reissued_at":"2026-07-05T11:19:58.894872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:58.894872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chen Feng, Irving Fang, Juexiao Zhang, Shengbang Tong","submitted_at":"2025-06-11T16:52:18Z","abstract_excerpt":"One promise that Vision-Language-Action (VLA) models hold over traditional imitation learning for robotics is to leverage the broad generalization capabilities of large Vision-Language Models (VLMs) to produce versatile, \"generalist\" robot policies. However, current evaluations of VLAs remain insufficient. Traditional imitation learning benchmarks are unsuitable due to the lack of language instructions. Emerging benchmarks for VLAs that incorporate language often come with limited evaluation tasks and do not intend to investigate how much VLM pretraining truly contributes to the generalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09930","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/2506.09930/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":"2506.09930","created_at":"2026-07-05T11:19:58.894933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09930v1","created_at":"2026-07-05T11:19:58.894933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09930","created_at":"2026-07-05T11:19:58.894933+00:00"},{"alias_kind":"pith_short_12","alias_value":"57BKKR5LLLAR","created_at":"2026-07-05T11:19:58.894933+00:00"},{"alias_kind":"pith_short_16","alias_value":"57BKKR5LLLARYVXE","created_at":"2026-07-05T11:19:58.894933+00:00"},{"alias_kind":"pith_short_8","alias_value":"57BKKR5L","created_at":"2026-07-05T11:19:58.894933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24815","citing_title":"MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12366","citing_title":"APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00020","citing_title":"EmbodimentSemantic: A Spatial Scene-Graph Dataset and Benchmark for Vision-Language Models on Embodied Manipulation Trajectories","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06761","citing_title":"AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02277","citing_title":"RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03827","citing_title":"LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02078","citing_title":"Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02757","citing_title":"Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A","json":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A.json","graph_json":"https://pith.science/api/pith-number/57BKKR5LLLARYVXE44OU4D376A/graph.json","events_json":"https://pith.science/api/pith-number/57BKKR5LLLARYVXE44OU4D376A/events.json","paper":"https://pith.science/paper/57BKKR5L"},"agent_actions":{"view_html":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A","download_json":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A.json","view_paper":"https://pith.science/paper/57BKKR5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09930&json=true","fetch_graph":"https://pith.science/api/pith-number/57BKKR5LLLARYVXE44OU4D376A/graph.json","fetch_events":"https://pith.science/api/pith-number/57BKKR5LLLARYVXE44OU4D376A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A/action/storage_attestation","attest_author":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A/action/author_attestation","sign_citation":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A/action/citation_signature","submit_replication":"https://pith.science/pith/57BKKR5LLLARYVXE44OU4D376A/action/replication_record"}},"created_at":"2026-07-05T11:19:58.894933+00:00","updated_at":"2026-07-05T11:19:58.894933+00:00"}