{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KIV5QELSRRSYC4OSU534HYMU5R","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":"c896d4c19d9d27f8911b233206e995b6b216dc576e534d89947b7ff9a7405811","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T14:49:47Z","title_canon_sha256":"83b5c1db8e1ac74990b63b6c2bd04f1918c217646a55f3765d69ef165733a550"},"schema_version":"1.0","source":{"id":"2608.13326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13326","created_at":"2026-08-14T01:04:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13326v1","created_at":"2026-08-14T01:04:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13326","created_at":"2026-08-14T01:04:13Z"},{"alias_kind":"pith_short_12","alias_value":"KIV5QELSRRSY","created_at":"2026-08-14T01:04:13Z"},{"alias_kind":"pith_short_16","alias_value":"KIV5QELSRRSYC4OS","created_at":"2026-08-14T01:04:13Z"},{"alias_kind":"pith_short_8","alias_value":"KIV5QELS","created_at":"2026-08-14T01:04:13Z"}],"graph_snapshots":[{"event_id":"sha256:7f3e4bc5706b77b380adcf2fac513a07c794faf9fc216e2b4f642d57f7c40285","target":"graph","created_at":"2026-08-14T01:04:13Z","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/2608.13326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand $\\tau$, we test whether O separates every pair with different $\\tau$. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes ","authors_text":"Data Science, Economics), Junhao Luo, Ning Huang, Southwestern University of Finance, Wei Deng (School of Statistics, Wenxuan Tang, Ziqi Sha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T14:49:47Z","title":"Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13326","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":"sha256:848a30403746012a2c327761c2691503f6fdabc7806702d0b0b23aabd6b133dd","target":"record","created_at":"2026-08-14T01:04:13Z","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":"c896d4c19d9d27f8911b233206e995b6b216dc576e534d89947b7ff9a7405811","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T14:49:47Z","title_canon_sha256":"83b5c1db8e1ac74990b63b6c2bd04f1918c217646a55f3765d69ef165733a550"},"schema_version":"1.0","source":{"id":"2608.13326","kind":"arxiv","version":1}},"canonical_sha256":"522bd811728c658171d2a777c3e194ec7e25da6c2ba29227acf8e34c75e6d91a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522bd811728c658171d2a777c3e194ec7e25da6c2ba29227acf8e34c75e6d91a","first_computed_at":"2026-08-14T01:04:13.306528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:04:13.306528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JzphDF79czIJqZiMJb4MCtnl7aLmUtopoy4+XelOs3nnTX0EAm1gJLfJDr26YiGlgkTXBNfzn5eTb3m3XWXBQ==","signature_status":"signed_v1","signed_at":"2026-08-14T01:04:13.308199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:848a30403746012a2c327761c2691503f6fdabc7806702d0b0b23aabd6b133dd","sha256:7f3e4bc5706b77b380adcf2fac513a07c794faf9fc216e2b4f642d57f7c40285"],"state_sha256":"4c98503ed922ea13d1b9328beee6f31f7519a3dd0e8969bd33ed88a5bd616420"}