{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:23J24TAOT5VNFLV5DBVY3QBCCJ","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":"445bb2579f19116d78b088a82beae5a14f08edf7223582690c1a647d1c710d8d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-14T20:13:21Z","title_canon_sha256":"d016db4a7c1ad00ad106413a5f4e6159d3892d952343578c9c1cae1fd0332eb5"},"schema_version":"1.0","source":{"id":"2203.07472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.07472","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.07472v1","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07472","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"23J24TAOT5VN","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"23J24TAOT5VNFLV5","created_at":"2026-07-05T04:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"23J24TAO","created_at":"2026-07-05T04:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:51e5e2eaa8ddcef07635d0b23244213c26763d622780f75fd2baddc19593d658","target":"graph","created_at":"2026-07-05T04:05:18Z","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/2203.07472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. However, collecting a large preference comparison dataset is still expensive -- and the learned reward models are unreliable out-of-distribution. We seek to addre","authors_text":"Adam Gleave, Geoffrey Irving","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-14T20:13:21Z","title":"Uncertainty Estimation for Language Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07472","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:f3a0b6c275c69265f24c80152481732e45321dc1d3e42316c08ce9238e0739a0","target":"record","created_at":"2026-07-05T04:05:18Z","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":"445bb2579f19116d78b088a82beae5a14f08edf7223582690c1a647d1c710d8d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-14T20:13:21Z","title_canon_sha256":"d016db4a7c1ad00ad106413a5f4e6159d3892d952343578c9c1cae1fd0332eb5"},"schema_version":"1.0","source":{"id":"2203.07472","kind":"arxiv","version":1}},"canonical_sha256":"d6d3ae4c0e9f6ad2aebd186b8dc0221279251d55586f874893ee0ee302c624e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6d3ae4c0e9f6ad2aebd186b8dc0221279251d55586f874893ee0ee302c624e4","first_computed_at":"2026-07-05T04:05:18.840669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:18.840669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ao3WhfDHuI8DTxa8aZUqCHTpBwF7N6U6pJkTXCVfwoWj6wlQcIVNS9VaK4bb5Iu5Tygw8HVAat1UHgerhwe9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:18.841097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.07472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3a0b6c275c69265f24c80152481732e45321dc1d3e42316c08ce9238e0739a0","sha256:51e5e2eaa8ddcef07635d0b23244213c26763d622780f75fd2baddc19593d658"],"state_sha256":"c7f0367758d30175c9781591d5aa7a7a2dbed3ef7d909b771bd2c478ec4bed19"}