{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NL6BJQNDF5BHIAJASQ7IKJTYBP","short_pith_number":"pith:NL6BJQND","canonical_record":{"source":{"id":"2305.06176","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:06:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8d21c5fd40bd65dd0aa632e2056da864cbb397ec18b36407c9e3a147f7f5dd00","abstract_canon_sha256":"09c11cd8cf548fd9cabed144f0ea0048f8828c9be8cab56ecfb99eac76376323"},"schema_version":"1.0"},"canonical_sha256":"6afc14c1a32f42740120943e8526780bdb04cf5657735b64c260e808e4abf002","source":{"kind":"arxiv","id":"2305.06176","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06176","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06176v3","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06176","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"NL6BJQNDF5BH","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"NL6BJQNDF5BHIAJA","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"NL6BJQND","created_at":"2026-07-05T07:52:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NL6BJQNDF5BHIAJASQ7IKJTYBP","target":"record","payload":{"canonical_record":{"source":{"id":"2305.06176","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:06:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8d21c5fd40bd65dd0aa632e2056da864cbb397ec18b36407c9e3a147f7f5dd00","abstract_canon_sha256":"09c11cd8cf548fd9cabed144f0ea0048f8828c9be8cab56ecfb99eac76376323"},"schema_version":"1.0"},"canonical_sha256":"6afc14c1a32f42740120943e8526780bdb04cf5657735b64c260e808e4abf002","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:09.676834Z","signature_b64":"2sswQgRcLf7DHklB9jx0tWkazFYoVhaAyPgUGnlMbM3ciVUHdF0JDDfbsyQcCTqhtAs04OvuTT6f+2fQeBAEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6afc14c1a32f42740120943e8526780bdb04cf5657735b64c260e808e4abf002","last_reissued_at":"2026-07-05T07:52:09.676388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:09.676388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.06176","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/2iwb15yQ+SEYy+ZYEeEs5I9Q3vbHAyrjIEzhGgG2DtcqGdR8jN3qzZ8/YMIHGokItAwstPSPBVMS7y65YBWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:01:21.333598Z"},"content_sha256":"46e93b65aa52681b4013d5a765b03610ec81abd6e1c4d6f21fa34f3651101b20","schema_version":"1.0","event_id":"sha256:46e93b65aa52681b4013d5a765b03610ec81abd6e1c4d6f21fa34f3651101b20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NL6BJQNDF5BHIAJASQ7IKJTYBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bryan Kian Hsiang Low, Lau Jia Jaw, Zhang Hui, Zhang Ze Yu","submitted_at":"2023-05-09T17:06:06Z","abstract_excerpt":"Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF is constrained by the expertise and productivity limitations of human evaluators. A response to this downside is to fall back to supervised fine-tuning (SFT) with additional carefully selected expert demonstrations. However, while this method has been proven to be effective, it invariably also leads to increased human-in-the-loop overhead. In this study, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06176","kind":"arxiv","version":3},"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/2305.06176/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":"2026-07-05T07:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gR3Ls8HopfO5pG3o3/bI7tGlWSozREe+SStqOyJPhqlwmRg3cfQLXHBJmXaKgvZ8NV4kITRAt1x4G6CwLNFMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:01:21.334295Z"},"content_sha256":"0d250330a1963ae39d5451f4c5c90c9d4324023c4417df8aef9be8257a152cc2","schema_version":"1.0","event_id":"sha256:0d250330a1963ae39d5451f4c5c90c9d4324023c4417df8aef9be8257a152cc2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/bundle.json","state_url":"https://pith.science/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/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":"2026-08-20T10:01:21Z","links":{"resolver":"https://pith.science/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP","bundle":"https://pith.science/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/bundle.json","state":"https://pith.science/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NL6BJQNDF5BHIAJASQ7IKJTYBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NL6BJQNDF5BHIAJASQ7IKJTYBP","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":"09c11cd8cf548fd9cabed144f0ea0048f8828c9be8cab56ecfb99eac76376323","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:06:06Z","title_canon_sha256":"8d21c5fd40bd65dd0aa632e2056da864cbb397ec18b36407c9e3a147f7f5dd00"},"schema_version":"1.0","source":{"id":"2305.06176","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06176","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06176v3","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06176","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"NL6BJQNDF5BH","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"NL6BJQNDF5BHIAJA","created_at":"2026-07-05T07:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"NL6BJQND","created_at":"2026-07-05T07:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:0d250330a1963ae39d5451f4c5c90c9d4324023c4417df8aef9be8257a152cc2","target":"graph","created_at":"2026-07-05T07:52:09Z","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/2305.06176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Human Feedback (RLHF) has been demonstrated to significantly enhance the performance of large language models (LLMs) by aligning their outputs with desired human values through instruction tuning. However, RLHF is constrained by the expertise and productivity limitations of human evaluators. A response to this downside is to fall back to supervised fine-tuning (SFT) with additional carefully selected expert demonstrations. However, while this method has been proven to be effective, it invariably also leads to increased human-in-the-loop overhead. In this study, we p","authors_text":"Bryan Kian Hsiang Low, Lau Jia Jaw, Zhang Hui, Zhang Ze Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:06:06Z","title":"Fine-tuning Language Models with Generative Adversarial Reward Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06176","kind":"arxiv","version":3},"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":"sha256:46e93b65aa52681b4013d5a765b03610ec81abd6e1c4d6f21fa34f3651101b20","target":"record","created_at":"2026-07-05T07:52:09Z","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":"09c11cd8cf548fd9cabed144f0ea0048f8828c9be8cab56ecfb99eac76376323","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-09T17:06:06Z","title_canon_sha256":"8d21c5fd40bd65dd0aa632e2056da864cbb397ec18b36407c9e3a147f7f5dd00"},"schema_version":"1.0","source":{"id":"2305.06176","kind":"arxiv","version":3}},"canonical_sha256":"6afc14c1a32f42740120943e8526780bdb04cf5657735b64c260e808e4abf002","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6afc14c1a32f42740120943e8526780bdb04cf5657735b64c260e808e4abf002","first_computed_at":"2026-07-05T07:52:09.676388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:09.676388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sswQgRcLf7DHklB9jx0tWkazFYoVhaAyPgUGnlMbM3ciVUHdF0JDDfbsyQcCTqhtAs04OvuTT6f+2fQeBAEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:09.676834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06176","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46e93b65aa52681b4013d5a765b03610ec81abd6e1c4d6f21fa34f3651101b20","sha256:0d250330a1963ae39d5451f4c5c90c9d4324023c4417df8aef9be8257a152cc2"],"state_sha256":"59d3ece62faf3f8680ea1976fb55d57b0aa694e7e88ea7c7113b63c15cab4bee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RVQC5DmWZYhY+t0fEdJORyniUa2mVnIzqmr9ajzUf6geB+PB/ZDDlbDapG+E55Xn95hcXZ24AFQSR+yoWL4nCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:01:21.340782Z","bundle_sha256":"a71b7b0e3d571c3cdfcc3bb34ceb3ec22b22c0e8918d5701d4a1f066483cf30c"}}