{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SCNZYHFOJRAD4SE2E6TQMEA4FR","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":"7c3ea2b3525d90aecd71bdfbc96ee28cb4dbd4cd5bcb5d80f9bcc5e1733e62e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T09:57:21Z","title_canon_sha256":"2f21921d98408a14bf9ce1832b9add0ee3514e45626257853f98ab0b5c3073fa"},"schema_version":"1.0","source":{"id":"2404.19409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19409","created_at":"2026-07-05T08:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19409v1","created_at":"2026-07-05T08:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19409","created_at":"2026-07-05T08:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"SCNZYHFOJRAD","created_at":"2026-07-05T08:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"SCNZYHFOJRAD4SE2","created_at":"2026-07-05T08:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"SCNZYHFO","created_at":"2026-07-05T08:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:ad8636d1312b91652d4fe7adb16a28a0b77648ad0f3b6821913fa7609ef78687","target":"graph","created_at":"2026-07-05T08:13:43Z","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/2404.19409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Reinforcement Learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO). Existing approaches address ROO by adding KL regularization, requiring computationally expensive hyperparameter tuning. Additionally, KL regularization focuses solely on regularizing the language policy, neglecting a potential source of regularization: the reward function itself. Inspired by demonstration-guided RL, we here introduce the Reward Calibration from Demonstration (RCfD), which leverages human demonstrations and a reward model to recalib","authors_text":"Emmanuel Dupoux, Florian Strub, Mathieu Rita, Olivier Pietquin, Paul Michel, Rahma Chaabouni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T09:57:21Z","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19409","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":"sha256:3432a364b2333c59710cdd24c3f44f6b56034665095105ad0c87d40c3d45d723","target":"record","created_at":"2026-07-05T08:13:43Z","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":"7c3ea2b3525d90aecd71bdfbc96ee28cb4dbd4cd5bcb5d80f9bcc5e1733e62e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T09:57:21Z","title_canon_sha256":"2f21921d98408a14bf9ce1832b9add0ee3514e45626257853f98ab0b5c3073fa"},"schema_version":"1.0","source":{"id":"2404.19409","kind":"arxiv","version":1}},"canonical_sha256":"909b9c1cae4c403e489a27a706101c2c786d014294959545f1ef933b9c2b1ab5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"909b9c1cae4c403e489a27a706101c2c786d014294959545f1ef933b9c2b1ab5","first_computed_at":"2026-07-05T08:13:43.279387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:43.279387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kWGQpe13tLASLZIDfCjrOCWZYVsO/8QBkgLRcWnNO+8oXOKjD6nEeaFaeRbrcDwzrgG2o813NswcP5p0JRwaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:43.279857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3432a364b2333c59710cdd24c3f44f6b56034665095105ad0c87d40c3d45d723","sha256:ad8636d1312b91652d4fe7adb16a28a0b77648ad0f3b6821913fa7609ef78687"],"state_sha256":"3651d1a1e8394ce02239bbc66f9c61700ad11965b2e686169e6c0c9e56059c02"}