{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BMPDWOKNAMIDFMTZP6OJ3NEFPA","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":"bc6657294e88ccf86d279a3b27d194bd07d349065861e53e29c373fcdad3b2b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:26:03Z","title_canon_sha256":"de6b245007d6834115a754390a5b4290398e286230a9ea9bf41197ddd70f9cbe"},"schema_version":"1.0","source":{"id":"2605.27901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27901","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27901v1","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27901","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"BMPDWOKNAMID","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"BMPDWOKNAMIDFMTZ","created_at":"2026-05-28T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"BMPDWOKN","created_at":"2026-05-28T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:ef19d33fcac3aa0b6b1bfc4ec060595fd695df54d872bd2a7e623ec571ecb5f0","target":"graph","created_at":"2026-05-28T01:04:51Z","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/2605.27901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT monitorability across 13 diverse languages and seven frontier model families, comprising 16 models. Using adversarial-hint evaluations that require explicit intermediate computation, together with analysis of internal answer-token probabilities, we consistently find CoT unfaithfulness across languages ","authors_text":"Bhavya Kailkhura, Chirag Agarwal, Eric Onyame, Kowshik Thopalli, Runtao Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:26:03Z","title":"The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27901","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":"sha256:0968a397f9d52cd3ec64d3278a08e3c1383961b1bc0db3a3f808dbc78566969c","target":"record","created_at":"2026-05-28T01:04:51Z","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":"bc6657294e88ccf86d279a3b27d194bd07d349065861e53e29c373fcdad3b2b4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T03:26:03Z","title_canon_sha256":"de6b245007d6834115a754390a5b4290398e286230a9ea9bf41197ddd70f9cbe"},"schema_version":"1.0","source":{"id":"2605.27901","kind":"arxiv","version":1}},"canonical_sha256":"0b1e3b394d031032b2797f9c9db485780ef40816fd29a92b9371edad17ead598","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b1e3b394d031032b2797f9c9db485780ef40816fd29a92b9371edad17ead598","first_computed_at":"2026-05-28T01:04:51.893152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:51.893152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YYEr5E42Ibt/N9Ig1LSrKf/N1ylWQHX3Pfvcd1S+8RCpDt6a+8FLyT+O6wy3gVGXlqHdvtlRsCUSfJAtZ3K3BA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:51.893599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0968a397f9d52cd3ec64d3278a08e3c1383961b1bc0db3a3f808dbc78566969c","sha256:ef19d33fcac3aa0b6b1bfc4ec060595fd695df54d872bd2a7e623ec571ecb5f0"],"state_sha256":"8e60d2e0c865b0b39e00a270b66d3f17b5434dc55889de3829f4f443e9e7af69"}