{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:37CEBBFBTXI5GNLJ3Y5CMF3TUW","short_pith_number":"pith:37CEBBFB","canonical_record":{"source":{"id":"2504.13972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-04-17T19:10:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70d78a9958fcc70442b5bc6bd6bbf984367a9c656b594605582e294d6725deb1","abstract_canon_sha256":"1cd12aed904f4dde5905b8c3b27b043f69635b051ff99625267393d5ca3a8217"},"schema_version":"1.0"},"canonical_sha256":"dfc44084a19dd1d33569de3a261773a5aa3059be9a44e9d02c999b31e93abd48","source":{"kind":"arxiv","id":"2504.13972","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13972","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13972v1","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13972","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"37CEBBFBTXI5","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"37CEBBFBTXI5GNLJ","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"37CEBBFB","created_at":"2026-07-05T10:51:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:37CEBBFBTXI5GNLJ3Y5CMF3TUW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-04-17T19:10:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70d78a9958fcc70442b5bc6bd6bbf984367a9c656b594605582e294d6725deb1","abstract_canon_sha256":"1cd12aed904f4dde5905b8c3b27b043f69635b051ff99625267393d5ca3a8217"},"schema_version":"1.0"},"canonical_sha256":"dfc44084a19dd1d33569de3a261773a5aa3059be9a44e9d02c999b31e93abd48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:08.990308Z","signature_b64":"rXQ/RrMVAagEQusdSZfYmE9hQ7wDYqw0r2zvrrE2xjgxS4V0HNdGYetpgTMPUEHPBNcYok95M9qYniBn35hpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfc44084a19dd1d33569de3a261773a5aa3059be9a44e9d02c999b31e93abd48","last_reissued_at":"2026-07-05T10:51:08.989909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:08.989909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13972","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":"2026-07-05T10:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o6MStpx/+sej0CQNJGbx3t9K7DiwduoROKFixEuZ9mX+am9cCuVtchCFJktfQny6Q32wY2v5p4wzFzCy7zlGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:18:33.075348Z"},"content_sha256":"d1ba4e29098ad2c9b19e620d2c9aebbff09f7f556e7f2480d7bc862d5b7642ae","schema_version":"1.0","event_id":"sha256:d1ba4e29098ad2c9b19e620d2c9aebbff09f7f556e7f2480d7bc862d5b7642ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:37CEBBFBTXI5GNLJ3Y5CMF3TUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Governance Challenges in Reinforcement Learning from Human Feedback: Evaluator Rationality and Reinforcement Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Abdulrahman Kamal, Dana Alsagheer, Mohammad Kamal, Weidong Shi","submitted_at":"2025-04-17T19:10:00Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is central in aligning large language models (LLMs) with human values and expectations. However, the process remains susceptible to governance challenges, including evaluator bias, inconsistency, and the unreliability of feedback. This study examines how the cognitive capacity of evaluators, specifically their level of rationality, affects the stability of reinforcement signals. A controlled experiment comparing high-rationality and low-rationality participants reveals that evaluators with higher rationality scores produce significantly more co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13972","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/2504.13972/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":"2026-07-05T10:51:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2MzBF5yXwras4XDbkWLb204/4ptoAvJnNOCkgSUzwQe0QMEf3N4xdQ93FMCZqB0RMaN5sOowqC7QZnbQlNXTBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T20:18:33.075728Z"},"content_sha256":"9c263d05ba0137b884ed653cd2f09aa9bf7b405ddba430996aba873e28555dae","schema_version":"1.0","event_id":"sha256:9c263d05ba0137b884ed653cd2f09aa9bf7b405ddba430996aba873e28555dae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/bundle.json","state_url":"https://pith.science/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/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":"2026-08-21T20:18:33Z","links":{"resolver":"https://pith.science/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW","bundle":"https://pith.science/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/bundle.json","state":"https://pith.science/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37CEBBFBTXI5GNLJ3Y5CMF3TUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:37CEBBFBTXI5GNLJ3Y5CMF3TUW","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":"1cd12aed904f4dde5905b8c3b27b043f69635b051ff99625267393d5ca3a8217","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-04-17T19:10:00Z","title_canon_sha256":"70d78a9958fcc70442b5bc6bd6bbf984367a9c656b594605582e294d6725deb1"},"schema_version":"1.0","source":{"id":"2504.13972","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13972","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13972v1","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13972","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_12","alias_value":"37CEBBFBTXI5","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_16","alias_value":"37CEBBFBTXI5GNLJ","created_at":"2026-07-05T10:51:08Z"},{"alias_kind":"pith_short_8","alias_value":"37CEBBFB","created_at":"2026-07-05T10:51:08Z"}],"graph_snapshots":[{"event_id":"sha256:9c263d05ba0137b884ed653cd2f09aa9bf7b405ddba430996aba873e28555dae","target":"graph","created_at":"2026-07-05T10:51:08Z","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/2504.13972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is central in aligning large language models (LLMs) with human values and expectations. However, the process remains susceptible to governance challenges, including evaluator bias, inconsistency, and the unreliability of feedback. This study examines how the cognitive capacity of evaluators, specifically their level of rationality, affects the stability of reinforcement signals. A controlled experiment comparing high-rationality and low-rationality participants reveals that evaluators with higher rationality scores produce significantly more co","authors_text":"Abdulrahman Kamal, Dana Alsagheer, Mohammad Kamal, Weidong Shi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-04-17T19:10:00Z","title":"Governance Challenges in Reinforcement Learning from Human Feedback: Evaluator Rationality and Reinforcement Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13972","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:d1ba4e29098ad2c9b19e620d2c9aebbff09f7f556e7f2480d7bc862d5b7642ae","target":"record","created_at":"2026-07-05T10:51:08Z","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":"1cd12aed904f4dde5905b8c3b27b043f69635b051ff99625267393d5ca3a8217","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-04-17T19:10:00Z","title_canon_sha256":"70d78a9958fcc70442b5bc6bd6bbf984367a9c656b594605582e294d6725deb1"},"schema_version":"1.0","source":{"id":"2504.13972","kind":"arxiv","version":1}},"canonical_sha256":"dfc44084a19dd1d33569de3a261773a5aa3059be9a44e9d02c999b31e93abd48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfc44084a19dd1d33569de3a261773a5aa3059be9a44e9d02c999b31e93abd48","first_computed_at":"2026-07-05T10:51:08.989909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:08.989909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rXQ/RrMVAagEQusdSZfYmE9hQ7wDYqw0r2zvrrE2xjgxS4V0HNdGYetpgTMPUEHPBNcYok95M9qYniBn35hpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:08.990308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13972","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1ba4e29098ad2c9b19e620d2c9aebbff09f7f556e7f2480d7bc862d5b7642ae","sha256:9c263d05ba0137b884ed653cd2f09aa9bf7b405ddba430996aba873e28555dae"],"state_sha256":"272a96a71d2dd5a270435ac9c0dc654e6f5729cb9f23e08daef991e5c4422c1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uc00yz22Wc9qFLXveYHZ4RQU+lGUy649nbfccmxWPGFdby4QXjHedd5fIxDgkr642ezW5qwm08xht8e8VNtPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T20:18:33.078486Z","bundle_sha256":"989497ae07511f50dde2727752021fea6fae551e5c54b4832909a45b0fe1b952"}}