{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7PUGVZHRCEOFKORV7UG4MBJWJJ","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":"77c0212571a394958567677d484ecb7472df65acee01847a9e3c4deca159cca5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T18:53:54Z","title_canon_sha256":"5959be27353bbcbb07471eb3d7520ace46b62d6db8bb7c5794d1a5b4cf869522"},"schema_version":"1.0","source":{"id":"2402.12366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12366","created_at":"2026-07-05T07:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12366v1","created_at":"2026-07-05T07:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12366","created_at":"2026-07-05T07:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"7PUGVZHRCEOF","created_at":"2026-07-05T07:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"7PUGVZHRCEOFKORV","created_at":"2026-07-05T07:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"7PUGVZHR","created_at":"2026-07-05T07:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:8d83faecf122da56fc4b315e0366e5d040b7b25bfb8413c5199f1c619f3fab4d","target":"graph","created_at":"2026-07-05T07:46:52Z","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/2402.12366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with AI feedback (RLAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. RLAIF first performs supervised fine-tuning (SFT) using demonstrations from a teacher model and then further fine-tunes the model with reinforcement learning (RL), using feedback from a critic model. While recent popular open-source models have demonstrated substantial improvements in performance from the RL step, in this paper we question whether the complexity of this RL step is truly warranted for AI feedback. We show that the impro","authors_text":"Archit Sharma, Chelsea Finn, Eric Mitchell, Kushal Arora, Sedrick Keh, Thomas Kollar","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T18:53:54Z","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12366","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":"sha256:36dd20966368b048f1ceb388f4ef9ff13dcee883ddc54033a299de381d2bb283","target":"record","created_at":"2026-07-05T07:46:52Z","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":"77c0212571a394958567677d484ecb7472df65acee01847a9e3c4deca159cca5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T18:53:54Z","title_canon_sha256":"5959be27353bbcbb07471eb3d7520ace46b62d6db8bb7c5794d1a5b4cf869522"},"schema_version":"1.0","source":{"id":"2402.12366","kind":"arxiv","version":1}},"canonical_sha256":"fbe86ae4f1111c553a35fd0dc605364a4037d850d1f6fa79080ee33862a00679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbe86ae4f1111c553a35fd0dc605364a4037d850d1f6fa79080ee33862a00679","first_computed_at":"2026-07-05T07:46:52.470072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:52.470072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xA5wBXBP/pOLK4BhKBIkcV+c8JrnOgprmAjs7WNLbPWszv1je4K2TH3u51np9oN1LjGMxPCKaL0gINHFA47ZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:52.470474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36dd20966368b048f1ceb388f4ef9ff13dcee883ddc54033a299de381d2bb283","sha256:8d83faecf122da56fc4b315e0366e5d040b7b25bfb8413c5199f1c619f3fab4d"],"state_sha256":"bbe5fdcb91de27f50ab22a1993ec07dd6a44bbcb7412188c766b8e13788b7ac2"}