{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F6MMTLMGHDLT5RIVIAAPPUI2ZL","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":"28a4af69ca348c919f37420a45c80cfd3a1b60d9b818371c59b11341ef1aa12b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T00:21:54Z","title_canon_sha256":"6e00f25c4ecf98128af0ff35b89dc83236fe4c6abe59939773f206596fb5f651"},"schema_version":"1.0","source":{"id":"2607.14439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14439","created_at":"2026-07-17T00:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14439v1","created_at":"2026-07-17T00:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14439","created_at":"2026-07-17T00:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"F6MMTLMGHDLT","created_at":"2026-07-17T00:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"F6MMTLMGHDLT5RIV","created_at":"2026-07-17T00:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"F6MMTLMG","created_at":"2026-07-17T00:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:d2f6599eb9b9c30b78dcfc3a5b385d5e014eb2eed889c80f159fa348860b6c5d","target":"graph","created_at":"2026-07-17T00:21:12Z","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/2607.14439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalist robot manipulation policies trained on large, diverse datasets have shown remarkable promise across a wide range of tasks. However, rigorously evaluating these policies remains a fundamental challenge. Real-world performance depends on a large combinatorial space of task factors including object poses and camera viewpoints, making full, exhaustive evaluation intractable. Additionally, real hardware evaluation is slow and resource-intensive, so current practice is to use narrow test suites that can miss critical failure modes and misrepresent true deployment readiness. We propose an ","authors_text":"Andrew Liao, Aryan Deshwal, Hanchen Cui, Karthik Desingh","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T00:21:54Z","title":"Active Real-World Factor-Based Evaluation for Generalist Robot Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14439","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":"sha256:171584c41e599aac7ff49a1158ba6a707a60a17f1334b1534bc29ff833152fe3","target":"record","created_at":"2026-07-17T00:21:12Z","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":"28a4af69ca348c919f37420a45c80cfd3a1b60d9b818371c59b11341ef1aa12b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T00:21:54Z","title_canon_sha256":"6e00f25c4ecf98128af0ff35b89dc83236fe4c6abe59939773f206596fb5f651"},"schema_version":"1.0","source":{"id":"2607.14439","kind":"arxiv","version":1}},"canonical_sha256":"2f98c9ad8638d73ec5154000f7d11acafed3a4a92f32c18720d88eefdaf33d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f98c9ad8638d73ec5154000f7d11acafed3a4a92f32c18720d88eefdaf33d33","first_computed_at":"2026-07-17T00:21:12.493245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:21:12.493245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20zH6zvs2sSSJ3ZIJL0MbmchqngTuPNfSBA4yRcJXCJGAAgre2XpkHBat+J9X5JXM80B7cPEtkkTR2q2Ya30DA==","signature_status":"signed_v1","signed_at":"2026-07-17T00:21:12.494062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:171584c41e599aac7ff49a1158ba6a707a60a17f1334b1534bc29ff833152fe3","sha256:d2f6599eb9b9c30b78dcfc3a5b385d5e014eb2eed889c80f159fa348860b6c5d"],"state_sha256":"3882becb7da3ac7235d5c6e92cc75ea70d8c7feea8ca56c0cb6f5dddc2f7e4b5"}