{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:43ERLFA52CXJD6Z5YWMVZBFXOD","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":"3db971312317339d98b73187099aeb6568ebe9b9252afa3c7d03bb2607b86847","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T10:10:19Z","title_canon_sha256":"2b1d0aa6998864d457b4afabf9fb35bc1c9fd05da4a78ed9237ba5c470bc0d02"},"schema_version":"1.0","source":{"id":"2605.29710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29710","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29710v1","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29710","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"43ERLFA52CXJ","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"43ERLFA52CXJD6Z5","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"43ERLFA5","created_at":"2026-05-29T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:37bb331675ec94219fa7d55bad5d0036756eb7d64c6aa68a48ff2e3b29abd1ec","target":"graph","created_at":"2026-05-29T01:05:56Z","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/2605.29710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with $N \\le 25$ rollouts per condition, almost always without confidence intervals or paired statistical comparison; these cohort sizes struggle to resolve close comparisons reliably. We introduce PhAIL (Physical AI Leaderboard, https://phail.ai), an open real-robot benchmark on a Franka FR3 (dataset, per-rollout artifacts, and end-to-end reference implementation) of a distributional evaluation methodology: the time-to-success cumulative distribution function (CDF) as the evalua","authors_text":"Sergey Arkhangelskiy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T10:10:19Z","title":"PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29710","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":"sha256:9cf9dfd180ad7837d496fbf9271c1ee7eba8c64fe9d04fe5e0c445deb2db9d9d","target":"record","created_at":"2026-05-29T01:05:56Z","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":"3db971312317339d98b73187099aeb6568ebe9b9252afa3c7d03bb2607b86847","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T10:10:19Z","title_canon_sha256":"2b1d0aa6998864d457b4afabf9fb35bc1c9fd05da4a78ed9237ba5c470bc0d02"},"schema_version":"1.0","source":{"id":"2605.29710","kind":"arxiv","version":1}},"canonical_sha256":"e6c915941dd0ae91fb3dc5995c84b770fc564aeb805f8cd7114fc180d76aa88d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6c915941dd0ae91fb3dc5995c84b770fc564aeb805f8cd7114fc180d76aa88d","first_computed_at":"2026-05-29T01:05:56.574158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:56.574158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDHZH/ytp1vYeM4WKSLB8BdVGzuVbt2I5adu+swEXq9+cGuKN/nF+BCMTUPG5Xm/YCaxNfVbTlpagVD5DuggBQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:56.574621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cf9dfd180ad7837d496fbf9271c1ee7eba8c64fe9d04fe5e0c445deb2db9d9d","sha256:37bb331675ec94219fa7d55bad5d0036756eb7d64c6aa68a48ff2e3b29abd1ec"],"state_sha256":"04ac11c43bf6a0fc6964b91a07880c1e0816e6ccd9f1077928d2e37be8067e91"}