{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZLIIDUTXYOYXL3EJJN5VVW2JTP","short_pith_number":"pith:ZLIIDUTX","schema_version":"1.0","canonical_sha256":"cad081d277c3b175ec894b7b5adb499bdedae01ab016cf42f5cc7d0bfd419dbc","source":{"kind":"arxiv","id":"2409.12894","version":2},"attestation_state":"computed","paper":{"title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.SE","authors_text":"Jiayang Song, Lei Ma, Yuheng Huang, Zhan Shu, Zhehua Zhou, Zhijie Wang","submitted_at":"2024-09-19T16:33:00Z","abstract_excerpt":"The rapid advancement of generative AI and multi-modal foundation models has shown significant potential in advancing robotic manipulation. Vision-language-action (VLA) models, in particular, have emerged as a promising approach for visuomotor control by leveraging large-scale vision-language data and robot demonstrations. However, current VLA models are typically evaluated using a limited set of hand-crafted scenes, leaving their general performance and robustness in diverse scenarios largely unexplored. To address this gap, we present VLATest, a fuzzing framework designed to generate robotic"},"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":"2409.12894","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-19T16:33:00Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"eb897bfd03db9d5203132652e82d4154b5de4a243a3b1dea104e33e9dcd44305","abstract_canon_sha256":"bdfab1aa090e28839b58f793a8b4bc0f34f14a8cb232ecb21d9bf597d782a569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:01.440268Z","signature_b64":"/hq7i8Bbb4FHPYtGEAGH3tBX/bnmoc2D3GA24QO/N3Yk7Nuy9FmGl2pjQlUc/Ek1j/FeYYTgpu88wv1sKDTmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad081d277c3b175ec894b7b5adb499bdedae01ab016cf42f5cc7d0bfd419dbc","last_reissued_at":"2026-07-05T11:01:01.439721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:01.439721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.SE","authors_text":"Jiayang Song, Lei Ma, Yuheng Huang, Zhan Shu, Zhehua Zhou, Zhijie Wang","submitted_at":"2024-09-19T16:33:00Z","abstract_excerpt":"The rapid advancement of generative AI and multi-modal foundation models has shown significant potential in advancing robotic manipulation. Vision-language-action (VLA) models, in particular, have emerged as a promising approach for visuomotor control by leveraging large-scale vision-language data and robot demonstrations. However, current VLA models are typically evaluated using a limited set of hand-crafted scenes, leaving their general performance and robustness in diverse scenarios largely unexplored. To address this gap, we present VLATest, a fuzzing framework designed to generate robotic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12894","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/2409.12894/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":"2409.12894","created_at":"2026-07-05T11:01:01.439784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12894v2","created_at":"2026-07-05T11:01:01.439784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12894","created_at":"2026-07-05T11:01:01.439784+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLIIDUTXYOYX","created_at":"2026-07-05T11:01:01.439784+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLIIDUTXYOYXL3EJ","created_at":"2026-07-05T11:01:01.439784+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLIIDUTX","created_at":"2026-07-05T11:01:01.439784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00351","citing_title":"Unleashing More Actions via Action Compositional Training for VLA Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30456","citing_title":"Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03480","citing_title":"SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP","json":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP.json","graph_json":"https://pith.science/api/pith-number/ZLIIDUTXYOYXL3EJJN5VVW2JTP/graph.json","events_json":"https://pith.science/api/pith-number/ZLIIDUTXYOYXL3EJJN5VVW2JTP/events.json","paper":"https://pith.science/paper/ZLIIDUTX"},"agent_actions":{"view_html":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP","download_json":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP.json","view_paper":"https://pith.science/paper/ZLIIDUTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12894&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLIIDUTXYOYXL3EJJN5VVW2JTP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLIIDUTXYOYXL3EJJN5VVW2JTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP/action/storage_attestation","attest_author":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP/action/author_attestation","sign_citation":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP/action/citation_signature","submit_replication":"https://pith.science/pith/ZLIIDUTXYOYXL3EJJN5VVW2JTP/action/replication_record"}},"created_at":"2026-07-05T11:01:01.439784+00:00","updated_at":"2026-07-05T11:01:01.439784+00:00"}