{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F6MMTLMGHDLT5RIVIAAPPUI2ZL","short_pith_number":"pith:F6MMTLMG","schema_version":"1.0","canonical_sha256":"2f98c9ad8638d73ec5154000f7d11acafed3a4a92f32c18720d88eefdaf33d33","source":{"kind":"arxiv","id":"2607.14439","version":1},"attestation_state":"computed","paper":{"title":"Active Real-World Factor-Based Evaluation for Generalist Robot Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andrew Liao, Aryan Deshwal, Hanchen Cui, Karthik Desingh","submitted_at":"2026-07-16T00:21:54Z","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 "},"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":"2607.14439","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-16T00:21:54Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"6e00f25c4ecf98128af0ff35b89dc83236fe4c6abe59939773f206596fb5f651","abstract_canon_sha256":"28a4af69ca348c919f37420a45c80cfd3a1b60d9b818371c59b11341ef1aa12b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:12.494062Z","signature_b64":"20zH6zvs2sSSJ3ZIJL0MbmchqngTuPNfSBA4yRcJXCJGAAgre2XpkHBat+J9X5JXM80B7cPEtkkTR2q2Ya30DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f98c9ad8638d73ec5154000f7d11acafed3a4a92f32c18720d88eefdaf33d33","last_reissued_at":"2026-07-17T00:21:12.493245Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:12.493245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Real-World Factor-Based Evaluation for Generalist Robot Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Andrew Liao, Aryan Deshwal, Hanchen Cui, Karthik Desingh","submitted_at":"2026-07-16T00:21:54Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14439","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/2607.14439/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":"2607.14439","created_at":"2026-07-17T00:21:12.493669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14439v1","created_at":"2026-07-17T00:21:12.493669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14439","created_at":"2026-07-17T00:21:12.493669+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6MMTLMGHDLT","created_at":"2026-07-17T00:21:12.493669+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6MMTLMGHDLT5RIV","created_at":"2026-07-17T00:21:12.493669+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6MMTLMG","created_at":"2026-07-17T00:21:12.493669+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/F6MMTLMGHDLT5RIVIAAPPUI2ZL","json":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL.json","graph_json":"https://pith.science/api/pith-number/F6MMTLMGHDLT5RIVIAAPPUI2ZL/graph.json","events_json":"https://pith.science/api/pith-number/F6MMTLMGHDLT5RIVIAAPPUI2ZL/events.json","paper":"https://pith.science/paper/F6MMTLMG"},"agent_actions":{"view_html":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL","download_json":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL.json","view_paper":"https://pith.science/paper/F6MMTLMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14439&json=true","fetch_graph":"https://pith.science/api/pith-number/F6MMTLMGHDLT5RIVIAAPPUI2ZL/graph.json","fetch_events":"https://pith.science/api/pith-number/F6MMTLMGHDLT5RIVIAAPPUI2ZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL/action/storage_attestation","attest_author":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL/action/author_attestation","sign_citation":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL/action/citation_signature","submit_replication":"https://pith.science/pith/F6MMTLMGHDLT5RIVIAAPPUI2ZL/action/replication_record"}},"created_at":"2026-07-17T00:21:12.493669+00:00","updated_at":"2026-07-17T00:21:12.493669+00:00"}