{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RUMOADU3NOCYZDXLQ2U7OJBGPR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"936cb09e40e9e3fd1a2a6d4fdd8abaa4a11da7f98e20cdfa4acc154aa4447a17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:27:13Z","title_canon_sha256":"d7d0c6fe7c3c182100aa19e2bd5bd7884c90ae2ac01e9a421c0e5f67db90335a"},"schema_version":"1.0","source":{"id":"2606.02307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02307","created_at":"2026-06-02T03:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02307v1","created_at":"2026-06-02T03:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02307","created_at":"2026-06-02T03:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"RUMOADU3NOCY","created_at":"2026-06-02T03:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"RUMOADU3NOCYZDXL","created_at":"2026-06-02T03:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"RUMOADU3","created_at":"2026-06-02T03:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:cc3dd15a170503ab396b87c5b0057908c3b706379ecbc8518eb837d83bf7743c","target":"graph","created_at":"2026-06-02T03:04:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.02307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aitor Arrieta, Arusa Kanwal, Pablo Valle, Shaukat Ali","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:27:13Z","title":"FATE-VLA:Failue-aware test generation for vision-language-action models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02307","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cff0dcbe41061fa8f6eb83c8ec7233d4af757b9c435daf40eac4f76a91f2c50d","target":"record","created_at":"2026-06-02T03:04:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"936cb09e40e9e3fd1a2a6d4fdd8abaa4a11da7f98e20cdfa4acc154aa4447a17","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-01T14:27:13Z","title_canon_sha256":"d7d0c6fe7c3c182100aa19e2bd5bd7884c90ae2ac01e9a421c0e5f67db90335a"},"schema_version":"1.0","source":{"id":"2606.02307","kind":"arxiv","version":1}},"canonical_sha256":"8d18e00e9b6b858c8eeb86a9f724267c676e4386469de3e33b2f8f107e91cf70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d18e00e9b6b858c8eeb86a9f724267c676e4386469de3e33b2f8f107e91cf70","first_computed_at":"2026-06-02T03:04:55.675951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:55.675951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PCkyvgp3hL8VjsNbESQ++hL36j+0EnHJGbjkc112vYceDrCRLftzKrNSOqZwM1HxNcqN87uLHmzk7ilJUCLeAw==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:55.676333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cff0dcbe41061fa8f6eb83c8ec7233d4af757b9c435daf40eac4f76a91f2c50d","sha256:cc3dd15a170503ab396b87c5b0057908c3b706379ecbc8518eb837d83bf7743c"],"state_sha256":"9f26cedf059e7dc5461a90950e2b57f5698c57de912268990a5a8282e5d89668"}