{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVASIGWSULKX4P74LQF2M3QW5I","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":"5b1df4b5d67869fb2c6a68858dc6c12af14d3b86cfac48e49924a1069e78178c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-08T17:19:48Z","title_canon_sha256":"df18f33d165ba006f38fbea7bdf922a681da6e76af341c00dd7550cbc74b490f"},"schema_version":"1.0","source":{"id":"2412.06000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06000","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06000v1","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06000","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"IVASIGWSULKX","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"IVASIGWSULKX4P74","created_at":"2026-07-05T09:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"IVASIGWS","created_at":"2026-07-05T09:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:9ea58f322a64cb1a106100ded8cc473e618f5c5b7f25d833802d710bad6700e4","target":"graph","created_at":"2026-07-05T09:46:12Z","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/2412.06000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study explores the scaling properties of Reinforcement Learning from Human Feedback (RLHF) in Large Language Models (LLMs). Although RLHF is considered an important step in post-training of LLMs, its scaling potential is still largely unknown. We systematically analyze key components in the RLHF framework--model size, data composition, and inference budget--and their impacts on performance. Our findings show that increasing data diversity and volume improves reward model performance, helping process-supervision models scale better. For policy training, more response samples per prompt boo","authors_text":"Aohan Zeng, Hongning Wang, Jie Tang, Minlie Huang, Pengfan Du, Xiao Liu, Yilin Niu, Yuxiao Dong, Zhengxiao Du, Zhenyu Hou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-08T17:19:48Z","title":"Does RLHF Scale? Exploring the Impacts From Data, Model, and Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06000","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:feaf719a14f391c7437cdc75c20153ec71a6f0adc0189927ebd0fd95d40fe0a8","target":"record","created_at":"2026-07-05T09:46:12Z","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":"5b1df4b5d67869fb2c6a68858dc6c12af14d3b86cfac48e49924a1069e78178c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-08T17:19:48Z","title_canon_sha256":"df18f33d165ba006f38fbea7bdf922a681da6e76af341c00dd7550cbc74b490f"},"schema_version":"1.0","source":{"id":"2412.06000","kind":"arxiv","version":1}},"canonical_sha256":"4541241ad2a2d57e3ffc5c0ba66e16ea20f0edbb6f8d67f38dc61e9c595d93b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4541241ad2a2d57e3ffc5c0ba66e16ea20f0edbb6f8d67f38dc61e9c595d93b4","first_computed_at":"2026-07-05T09:46:12.839372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:12.839372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fobb+Gu6IExApKGN/OkpcF6zE8TuEjYBjUrS9ieupWtWXx5RBUlaHW4EyErDCVc9wbePe6vlnuE0RujM/up5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:12.839838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feaf719a14f391c7437cdc75c20153ec71a6f0adc0189927ebd0fd95d40fe0a8","sha256:9ea58f322a64cb1a106100ded8cc473e618f5c5b7f25d833802d710bad6700e4"],"state_sha256":"7283378b1887568604d2f231cbd103ab520a46164ee2259c48f1f68950bd153d"}