{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43ERLFA52CXJD6Z5YWMVZBFXOD","short_pith_number":"pith:43ERLFA5","schema_version":"1.0","canonical_sha256":"e6c915941dd0ae91fb3dc5995c84b770fc564aeb805f8cd7114fc180d76aa88d","source":{"kind":"arxiv","id":"2605.29710","version":1},"attestation_state":"computed","paper":{"title":"PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Sergey Arkhangelskiy","submitted_at":"2026-05-28T10:10:19Z","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"},"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":"2605.29710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-28T10:10:19Z","cross_cats_sorted":[],"title_canon_sha256":"2b1d0aa6998864d457b4afabf9fb35bc1c9fd05da4a78ed9237ba5c470bc0d02","abstract_canon_sha256":"3db971312317339d98b73187099aeb6568ebe9b9252afa3c7d03bb2607b86847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:56.574621Z","signature_b64":"YDHZH/ytp1vYeM4WKSLB8BdVGzuVbt2I5adu+swEXq9+cGuKN/nF+BCMTUPG5Xm/YCaxNfVbTlpagVD5DuggBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c915941dd0ae91fb3dc5995c84b770fc564aeb805f8cd7114fc180d76aa88d","last_reissued_at":"2026-05-29T01:05:56.574158Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:56.574158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Sergey Arkhangelskiy","submitted_at":"2026-05-28T10:10:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29710","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/2605.29710/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":"2605.29710","created_at":"2026-05-29T01:05:56.574231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29710v1","created_at":"2026-05-29T01:05:56.574231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29710","created_at":"2026-05-29T01:05:56.574231+00:00"},{"alias_kind":"pith_short_12","alias_value":"43ERLFA52CXJ","created_at":"2026-05-29T01:05:56.574231+00:00"},{"alias_kind":"pith_short_16","alias_value":"43ERLFA52CXJD6Z5","created_at":"2026-05-29T01:05:56.574231+00:00"},{"alias_kind":"pith_short_8","alias_value":"43ERLFA5","created_at":"2026-05-29T01:05:56.574231+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/43ERLFA52CXJD6Z5YWMVZBFXOD","json":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD.json","graph_json":"https://pith.science/api/pith-number/43ERLFA52CXJD6Z5YWMVZBFXOD/graph.json","events_json":"https://pith.science/api/pith-number/43ERLFA52CXJD6Z5YWMVZBFXOD/events.json","paper":"https://pith.science/paper/43ERLFA5"},"agent_actions":{"view_html":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD","download_json":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD.json","view_paper":"https://pith.science/paper/43ERLFA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29710&json=true","fetch_graph":"https://pith.science/api/pith-number/43ERLFA52CXJD6Z5YWMVZBFXOD/graph.json","fetch_events":"https://pith.science/api/pith-number/43ERLFA52CXJD6Z5YWMVZBFXOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD/action/storage_attestation","attest_author":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD/action/author_attestation","sign_citation":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD/action/citation_signature","submit_replication":"https://pith.science/pith/43ERLFA52CXJD6Z5YWMVZBFXOD/action/replication_record"}},"created_at":"2026-05-29T01:05:56.574231+00:00","updated_at":"2026-05-29T01:05:56.574231+00:00"}