{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RT5K7LJUD4E55U7EWYBVZZG7LX","short_pith_number":"pith:RT5K7LJU","canonical_record":{"source":{"id":"2507.05246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T17:54:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b6806490fe0c35aa37417f80ed35b11733dd28015f9490215a3f471a7bebc160","abstract_canon_sha256":"987c5c557f13320f74a952395e93058ce770df698f9c2d4fc2cad68cab7df09d"},"schema_version":"1.0"},"canonical_sha256":"8cfaafad341f09ded3e4b6035ce4df5dff26cf112a98520a805b320005f67594","source":{"kind":"arxiv","id":"2507.05246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05246","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05246v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05246","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"RT5K7LJUD4E5","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"RT5K7LJUD4E55U7E","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"RT5K7LJU","created_at":"2026-07-05T11:33:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RT5K7LJUD4E55U7EWYBVZZG7LX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T17:54:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b6806490fe0c35aa37417f80ed35b11733dd28015f9490215a3f471a7bebc160","abstract_canon_sha256":"987c5c557f13320f74a952395e93058ce770df698f9c2d4fc2cad68cab7df09d"},"schema_version":"1.0"},"canonical_sha256":"8cfaafad341f09ded3e4b6035ce4df5dff26cf112a98520a805b320005f67594","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:11.160386Z","signature_b64":"cq2zP6VsPKMcBx4fuM5uQUBDn2blBQ/PQksOiPkOuZGclBROILhIhRmdzs9F4EFHazXc7rxi37C9Jr94CwuZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cfaafad341f09ded3e4b6035ce4df5dff26cf112a98520a805b320005f67594","last_reissued_at":"2026-07-05T11:33:11.159942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:11.159942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05246","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uC2qlXycqlnaxv9WI7N4hM65aJxVdKOqimm+D/92YrIZ7vvncDmDI9LDFk3r7CKKJE+tROw8bATx6BZiH3dhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:14:11.549424Z"},"content_sha256":"40793e0396b8a41e4ee4c8ebb0d960c8c673136faee2217d36c06f28e404ecfd","schema_version":"1.0","event_id":"sha256:40793e0396b8a41e4ee4c8ebb0d960c8c673136faee2217d36c06f28e404ecfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RT5K7LJUD4E55U7EWYBVZZG7LX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"David K. Elson, Erik Jenner, Heng Chen, Irhum Shafkat, Rif A. Saurous, Rohin Shah, Scott Emmons, Senthooran Rajamanoharan","submitted_at":"2025-07-07T17:54:52Z","abstract_excerpt":"While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on \"unfaithfulness\" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc rationalization in applications like auditing for bias. However, for the distinct problem of runtime monitoring to prevent severe harm, we argue the key property is not faithfulness but monitorability. To this end, we introduce a conceptual framework distinguishing CoT-as-rationalization from CoT-as-computation. We expect that certain classes of severe harm will "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05246","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/2507.05246/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ugTB87KSRNVDrHLQagKVrJKc/S+WznYtV9FZjjlm6YcVk+MctJnSjAqvIAB7CwieasXSDQ9o0YZ0LGA00n2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:14:11.550293Z"},"content_sha256":"e31d63f4d261e55bdb2afc698e5ae50b7dbba1fe83efe7e5a821f43d7333184d","schema_version":"1.0","event_id":"sha256:e31d63f4d261e55bdb2afc698e5ae50b7dbba1fe83efe7e5a821f43d7333184d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/bundle.json","state_url":"https://pith.science/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T16:14:11Z","links":{"resolver":"https://pith.science/pith/RT5K7LJUD4E55U7EWYBVZZG7LX","bundle":"https://pith.science/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/bundle.json","state":"https://pith.science/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RT5K7LJUD4E55U7EWYBVZZG7LX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RT5K7LJUD4E55U7EWYBVZZG7LX","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":"987c5c557f13320f74a952395e93058ce770df698f9c2d4fc2cad68cab7df09d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T17:54:52Z","title_canon_sha256":"b6806490fe0c35aa37417f80ed35b11733dd28015f9490215a3f471a7bebc160"},"schema_version":"1.0","source":{"id":"2507.05246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05246","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05246v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05246","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"RT5K7LJUD4E5","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"RT5K7LJUD4E55U7E","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"RT5K7LJU","created_at":"2026-07-05T11:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:e31d63f4d261e55bdb2afc698e5ae50b7dbba1fe83efe7e5a821f43d7333184d","target":"graph","created_at":"2026-07-05T11:33:11Z","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/2507.05246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on \"unfaithfulness\" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc rationalization in applications like auditing for bias. However, for the distinct problem of runtime monitoring to prevent severe harm, we argue the key property is not faithfulness but monitorability. To this end, we introduce a conceptual framework distinguishing CoT-as-rationalization from CoT-as-computation. We expect that certain classes of severe harm will ","authors_text":"David K. Elson, Erik Jenner, Heng Chen, Irhum Shafkat, Rif A. Saurous, Rohin Shah, Scott Emmons, Senthooran Rajamanoharan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T17:54:52Z","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05246","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":"sha256:40793e0396b8a41e4ee4c8ebb0d960c8c673136faee2217d36c06f28e404ecfd","target":"record","created_at":"2026-07-05T11:33:11Z","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":"987c5c557f13320f74a952395e93058ce770df698f9c2d4fc2cad68cab7df09d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-07T17:54:52Z","title_canon_sha256":"b6806490fe0c35aa37417f80ed35b11733dd28015f9490215a3f471a7bebc160"},"schema_version":"1.0","source":{"id":"2507.05246","kind":"arxiv","version":1}},"canonical_sha256":"8cfaafad341f09ded3e4b6035ce4df5dff26cf112a98520a805b320005f67594","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cfaafad341f09ded3e4b6035ce4df5dff26cf112a98520a805b320005f67594","first_computed_at":"2026-07-05T11:33:11.159942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:11.159942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cq2zP6VsPKMcBx4fuM5uQUBDn2blBQ/PQksOiPkOuZGclBROILhIhRmdzs9F4EFHazXc7rxi37C9Jr94CwuZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:11.160386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40793e0396b8a41e4ee4c8ebb0d960c8c673136faee2217d36c06f28e404ecfd","sha256:e31d63f4d261e55bdb2afc698e5ae50b7dbba1fe83efe7e5a821f43d7333184d"],"state_sha256":"4eadb9e88a87872d200eb86949ad346a74cb6460b1a163609b9532a244a0b208"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKWtO7fCCOQPgJ74ol2EBxGH4hnJBcc/JjHQDK+miQ+T24AGykaXE/aJUgtPGi+KrTtpozX2GiFV+51nX0RmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:14:11.564415Z","bundle_sha256":"226caedaec2d82921964170c37bf8c21a61891f0732d62669ab77eda3b3ac7f0"}}