{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SJ4L3HVG7FJB72H6H7KPD3FM2B","short_pith_number":"pith:SJ4L3HVG","canonical_record":{"source":{"id":"2407.00215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T19:53:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e48f952d676c13f40b0776947d8a735d7c08d415f0c29f5dc664987c86f35e2c","abstract_canon_sha256":"a60463404cec2694df7b456c1d6ffcb76a64efdef74d786786bba83e6fbe8fa3"},"schema_version":"1.0"},"canonical_sha256":"9278bd9ea6f9521fe8fe3fd4f1ecacd0498df5bd52022cc02c2acfd46055819d","source":{"kind":"arxiv","id":"2407.00215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00215","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00215v1","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00215","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"SJ4L3HVG7FJB","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_16","alias_value":"SJ4L3HVG7FJB72H6","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_8","alias_value":"SJ4L3HVG","created_at":"2026-07-05T08:38:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SJ4L3HVG7FJB72H6H7KPD3FM2B","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T19:53:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e48f952d676c13f40b0776947d8a735d7c08d415f0c29f5dc664987c86f35e2c","abstract_canon_sha256":"a60463404cec2694df7b456c1d6ffcb76a64efdef74d786786bba83e6fbe8fa3"},"schema_version":"1.0"},"canonical_sha256":"9278bd9ea6f9521fe8fe3fd4f1ecacd0498df5bd52022cc02c2acfd46055819d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:15.895233Z","signature_b64":"ZwJZrRvbZtpFSfzRChcygPB1lFHrssyjAMkOiC+MdReE6j7yzwb6VQRrBue2/enPT6d4KelKNwlEBCqNOh1GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9278bd9ea6f9521fe8fe3fd4f1ecacd0498df5bd52022cc02c2acfd46055819d","last_reissued_at":"2026-07-05T08:38:15.894812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:15.894812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00215","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":"2026-07-05T08:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gezANl/wMVE9rQgy/ZAtbG4+oXYUrivP6rClb7toY1v8QU+EtDBR7PDn72taVt1tLFs1lNPOHtG4Hpp1++zBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:51:44.264946Z"},"content_sha256":"6ee1629447d538df46525b9571b96973224c9f0ea07aca63fe13ae5358fb0a80","schema_version":"1.0","event_id":"sha256:6ee1629447d538df46525b9571b96973224c9f0ea07aca63fe13ae5358fb0a80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SJ4L3HVG7FJB72H6H7KPD3FM2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Critics Help Catch LLM Bugs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Evgenia Nitishinskaya, Jan Leike, Juan Felipe Ceron Uribe, Maja Trebacz, Nat McAleese, Rai Michael Pokorny","submitted_at":"2024-06-28T19:53:17Z","abstract_excerpt":"Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains \"critic\" models that help humans to more accurately evaluate model-written code. These critics are themselves LLMs trained with RLHF to write natural language feedback highlighting problems in code from real-world assistant tasks. On code containing naturally occurring LLM errors model-written critiques are preferred over human critiques in 63% of cases, and human evaluation fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00215","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/2407.00215/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":"2026-07-05T08:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q7Q4us1goCd6K/HKtRu0zjPVUZSqOeqOTTOBTB3RIAJv89LtVdaKSlFOCul8bBwVBcELEDsPzCPN4mhvtreKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:51:44.265441Z"},"content_sha256":"a42ac6565ffb7471991f38f45bcfda13444fbabecac58673c1324faa664ed703","schema_version":"1.0","event_id":"sha256:a42ac6565ffb7471991f38f45bcfda13444fbabecac58673c1324faa664ed703"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/bundle.json","state_url":"https://pith.science/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/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":"2026-08-04T16:51:44Z","links":{"resolver":"https://pith.science/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B","bundle":"https://pith.science/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/bundle.json","state":"https://pith.science/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJ4L3HVG7FJB72H6H7KPD3FM2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SJ4L3HVG7FJB72H6H7KPD3FM2B","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":"a60463404cec2694df7b456c1d6ffcb76a64efdef74d786786bba83e6fbe8fa3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T19:53:17Z","title_canon_sha256":"e48f952d676c13f40b0776947d8a735d7c08d415f0c29f5dc664987c86f35e2c"},"schema_version":"1.0","source":{"id":"2407.00215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00215","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00215v1","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00215","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"SJ4L3HVG7FJB","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_16","alias_value":"SJ4L3HVG7FJB72H6","created_at":"2026-07-05T08:38:15Z"},{"alias_kind":"pith_short_8","alias_value":"SJ4L3HVG","created_at":"2026-07-05T08:38:15Z"}],"graph_snapshots":[{"event_id":"sha256:a42ac6565ffb7471991f38f45bcfda13444fbabecac58673c1324faa664ed703","target":"graph","created_at":"2026-07-05T08:38:15Z","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/2407.00215/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 fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains \"critic\" models that help humans to more accurately evaluate model-written code. These critics are themselves LLMs trained with RLHF to write natural language feedback highlighting problems in code from real-world assistant tasks. On code containing naturally occurring LLM errors model-written critiques are preferred over human critiques in 63% of cases, and human evaluation fin","authors_text":"Evgenia Nitishinskaya, Jan Leike, Juan Felipe Ceron Uribe, Maja Trebacz, Nat McAleese, Rai Michael Pokorny","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T19:53:17Z","title":"LLM Critics Help Catch LLM Bugs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00215","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":"sha256:6ee1629447d538df46525b9571b96973224c9f0ea07aca63fe13ae5358fb0a80","target":"record","created_at":"2026-07-05T08:38:15Z","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":"a60463404cec2694df7b456c1d6ffcb76a64efdef74d786786bba83e6fbe8fa3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-28T19:53:17Z","title_canon_sha256":"e48f952d676c13f40b0776947d8a735d7c08d415f0c29f5dc664987c86f35e2c"},"schema_version":"1.0","source":{"id":"2407.00215","kind":"arxiv","version":1}},"canonical_sha256":"9278bd9ea6f9521fe8fe3fd4f1ecacd0498df5bd52022cc02c2acfd46055819d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9278bd9ea6f9521fe8fe3fd4f1ecacd0498df5bd52022cc02c2acfd46055819d","first_computed_at":"2026-07-05T08:38:15.894812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:15.894812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZwJZrRvbZtpFSfzRChcygPB1lFHrssyjAMkOiC+MdReE6j7yzwb6VQRrBue2/enPT6d4KelKNwlEBCqNOh1GAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:15.895233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ee1629447d538df46525b9571b96973224c9f0ea07aca63fe13ae5358fb0a80","sha256:a42ac6565ffb7471991f38f45bcfda13444fbabecac58673c1324faa664ed703"],"state_sha256":"746db239fe90300f177c1cc91d343f66f2929e4d64edd833c2f213d2e728ae1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g77XOUt8nqK8v38CLu8rjVciO56Yce0Cp5voQEqWX0g0Fv9gG6kur/WjWbxfFk3yhCW8cjc1LiCrJFW49tXUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:51:44.270097Z","bundle_sha256":"dbe05c569f4e30a61ec6132c12a778cb7a612b1985280c7dcda93595f554649c"}}