{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZGF43COKPR5TWX4VWWFVPVQPIM","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":"45a2cbc03f7e39fb1926797c00ef67fe93d51e3f9db97b648af80b8c804756b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T13:24:40Z","title_canon_sha256":"a6e2d0396548ba46df2fab06478853afa230813cb0be6076e253a82ff7acca9a"},"schema_version":"1.0","source":{"id":"2606.26185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26185","created_at":"2026-06-26T00:15:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26185v1","created_at":"2026-06-26T00:15:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26185","created_at":"2026-06-26T00:15:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZGF43COKPR5T","created_at":"2026-06-26T00:15:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZGF43COKPR5TWX4V","created_at":"2026-06-26T00:15:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZGF43COK","created_at":"2026-06-26T00:15:28Z"}],"graph_snapshots":[{"event_id":"sha256:a13464ef2d63854153936a2a3f152475a8e99d8cff9858f5f9cda3073311296d","target":"graph","created_at":"2026-06-26T00:15:28Z","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/2606.26185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-judge (\"grader\") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions. A widespread assumption is that setting the grader's sampling temperature to 0 makes grading deterministic. We test this assumption against a real safety-evaluation codebase (Japan AISI's open-source aisev) and show it fails on two levels. First, the harness invokes its grader without setting temperature or seed; the underlying provider silently applies its default of 1.0, so items near the decision boundary flip pass/fail","authors_text":"Hiroki Tamba","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T13:24:40Z","title":"Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26185","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":"sha256:076a2ca93cd307fec4e73d6cf98999c974b4823ba0a1e9f9dce42c2a02df92ac","target":"record","created_at":"2026-06-26T00:15:28Z","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":"45a2cbc03f7e39fb1926797c00ef67fe93d51e3f9db97b648af80b8c804756b2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T13:24:40Z","title_canon_sha256":"a6e2d0396548ba46df2fab06478853afa230813cb0be6076e253a82ff7acca9a"},"schema_version":"1.0","source":{"id":"2606.26185","kind":"arxiv","version":1}},"canonical_sha256":"c98bcd89ca7c7b3b5f95b58b57d60f4304d9e1ee7513cb417e973b0b060c365f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c98bcd89ca7c7b3b5f95b58b57d60f4304d9e1ee7513cb417e973b0b060c365f","first_computed_at":"2026-06-26T00:15:28.803819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:28.803819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ydwBTenCAx84ILIxBJHQVDV22f617caw2OhrOGfYgufsB5enbyBZR8bvM/SU00YRD7W/jr/sQS1PcD1E7LCkAA==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:28.804230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:076a2ca93cd307fec4e73d6cf98999c974b4823ba0a1e9f9dce42c2a02df92ac","sha256:a13464ef2d63854153936a2a3f152475a8e99d8cff9858f5f9cda3073311296d"],"state_sha256":"563842e0fd945acbb2348049e271b20f6e7731b30aa9ece13cbfc5ef663c57d9"}