{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RUMOADU3NOCYZDXLQ2U7OJBGPR","short_pith_number":"pith:RUMOADU3","schema_version":"1.0","canonical_sha256":"8d18e00e9b6b858c8eeb86a9f724267c676e4386469de3e33b2f8f107e91cf70","source":{"kind":"arxiv","id":"2606.02307","version":1},"attestation_state":"computed","paper":{"title":"FATE-VLA:Failue-aware test generation for vision-language-action models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aitor Arrieta, Arusa Kanwal, Pablo Valle, Shaukat Ali","submitted_at":"2026-06-01T14:27:13Z","abstract_excerpt":"Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task scenes. In high-dimensional embodied spaces, failures are sparse and clustered, so static benchmarking can underestimate robustness risks. We reframe VLA evaluation as an active failure-discovery problem and propose a failure-aware test-generation approach that combines diversity-driven exploration with surrogate models learned from observed executions. The method steers testing toward high-risk yet diverse scene region"},"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":"2606.02307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"d7d0c6fe7c3c182100aa19e2bd5bd7884c90ae2ac01e9a421c0e5f67db90335a","abstract_canon_sha256":"936cb09e40e9e3fd1a2a6d4fdd8abaa4a11da7f98e20cdfa4acc154aa4447a17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:55.676333Z","signature_b64":"PCkyvgp3hL8VjsNbESQ++hL36j+0EnHJGbjkc112vYceDrCRLftzKrNSOqZwM1HxNcqN87uLHmzk7ilJUCLeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d18e00e9b6b858c8eeb86a9f724267c676e4386469de3e33b2f8f107e91cf70","last_reissued_at":"2026-06-02T03:04:55.675951Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:55.675951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FATE-VLA:Failue-aware test generation for vision-language-action models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aitor Arrieta, Arusa Kanwal, Pablo Valle, Shaukat Ali","submitted_at":"2026-06-01T14:27:13Z","abstract_excerpt":"Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task scenes. In high-dimensional embodied spaces, failures are sparse and clustered, so static benchmarking can underestimate robustness risks. We reframe VLA evaluation as an active failure-discovery problem and propose a failure-aware test-generation approach that combines diversity-driven exploration with surrogate models learned from observed executions. The method steers testing toward high-risk yet diverse scene region"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02307","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/2606.02307/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":"2606.02307","created_at":"2026-06-02T03:04:55.676009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02307v1","created_at":"2026-06-02T03:04:55.676009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02307","created_at":"2026-06-02T03:04:55.676009+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUMOADU3NOCY","created_at":"2026-06-02T03:04:55.676009+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUMOADU3NOCYZDXL","created_at":"2026-06-02T03:04:55.676009+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUMOADU3","created_at":"2026-06-02T03:04:55.676009+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/RUMOADU3NOCYZDXLQ2U7OJBGPR","json":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR.json","graph_json":"https://pith.science/api/pith-number/RUMOADU3NOCYZDXLQ2U7OJBGPR/graph.json","events_json":"https://pith.science/api/pith-number/RUMOADU3NOCYZDXLQ2U7OJBGPR/events.json","paper":"https://pith.science/paper/RUMOADU3"},"agent_actions":{"view_html":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR","download_json":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR.json","view_paper":"https://pith.science/paper/RUMOADU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02307&json=true","fetch_graph":"https://pith.science/api/pith-number/RUMOADU3NOCYZDXLQ2U7OJBGPR/graph.json","fetch_events":"https://pith.science/api/pith-number/RUMOADU3NOCYZDXLQ2U7OJBGPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR/action/storage_attestation","attest_author":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR/action/author_attestation","sign_citation":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR/action/citation_signature","submit_replication":"https://pith.science/pith/RUMOADU3NOCYZDXLQ2U7OJBGPR/action/replication_record"}},"created_at":"2026-06-02T03:04:55.676009+00:00","updated_at":"2026-06-02T03:04:55.676009+00:00"}