{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PEZTGLNYARRJY6R7Z3RH6FBRT7","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":"bb21a3a9b39ef86ebafaa8c9a863585e5e5d465caeb28b701a1450e374116494","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:34:39Z","title_canon_sha256":"93fa1061b7bfa78a496357211e33fbeee46c06a86c3a56175acaac7c99bcb6a0"},"schema_version":"1.0","source":{"id":"2606.29898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29898","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29898v1","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29898","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"PEZTGLNYARRJ","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"PEZTGLNYARRJY6R7","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"PEZTGLNY","created_at":"2026-06-30T02:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:3bc5c59e2252871ea5e5066a212d1cbba28062c58df625ce7cd149f7409c7861","target":"graph","created_at":"2026-06-30T02:17:39Z","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/2606.29898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot policies: it is costly, difficult to reproduce, and often too sparse to reliably compare nearby model variants. A straightforward proxy for performance is validation loss on expert demonstrations, but this proxy is often poorly correlated with real-world performance. In this paper, we introduce Critical Interval MSE (CI-MSE), an intuitivel","authors_text":"Haoxu Huang, Jiacheng You, Tongsam Zheng, Yang Gao, Yifan Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:34:39Z","title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29898","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":"sha256:214659360ab17a99dc780ecef034ae025d38344120468db2c3bc6a8f76f894c1","target":"record","created_at":"2026-06-30T02:17:39Z","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":"bb21a3a9b39ef86ebafaa8c9a863585e5e5d465caeb28b701a1450e374116494","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:34:39Z","title_canon_sha256":"93fa1061b7bfa78a496357211e33fbeee46c06a86c3a56175acaac7c99bcb6a0"},"schema_version":"1.0","source":{"id":"2606.29898","kind":"arxiv","version":1}},"canonical_sha256":"7933332db804629c7a3fcee27f14319fe4e509b0c73434f7fc98a212dcfc353f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7933332db804629c7a3fcee27f14319fe4e509b0c73434f7fc98a212dcfc353f","first_computed_at":"2026-06-30T02:17:39.996063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:39.996063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lmavswGv4bluALIEcdBlUYF+8mF/aazh7E3evU1hoAOTdiY7TVACStikaolbvZyHQCWixrjl0f/gJ9MK4bT5Bw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:39.996590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:214659360ab17a99dc780ecef034ae025d38344120468db2c3bc6a8f76f894c1","sha256:3bc5c59e2252871ea5e5066a212d1cbba28062c58df625ce7cd149f7409c7861"],"state_sha256":"5ebc1d29b9f7f9e5ebf777e0d98fa0e3acfc8df72839edfb6bea4476b31dd6c6"}