{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5HKMIHUSFDMFIJ67MBVQJFNPSQ","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":"eb75b926407cb9e1eb3032ba6bd5488748401700c0d2f472b8a6106a5e2ffbc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T12:51:29Z","title_canon_sha256":"6f9cae5b8982a82d0d8c18d75b37cfb1bb20275c1ffef9277c69cd2ab6e8939d"},"schema_version":"1.0","source":{"id":"2507.15906","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15906","created_at":"2026-07-05T11:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15906v1","created_at":"2026-07-05T11:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15906","created_at":"2026-07-05T11:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"5HKMIHUSFDMF","created_at":"2026-07-05T11:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"5HKMIHUSFDMFIJ67","created_at":"2026-07-05T11:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"5HKMIHUS","created_at":"2026-07-05T11:40:59Z"}],"graph_snapshots":[{"event_id":"sha256:c81476a5075a3a7b2c3f930168c901ed4078c9a1c252b5ff6a79affd7bb5ff1f","target":"graph","created_at":"2026-07-05T11:40:59Z","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/2507.15906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model estimate can render it vulnerable to inaccuracies in the reward model. We empirically study the variability of reward model training on open-source benchmarks. We observe that independently trained reward models on the same preference dataset can exhibit substantial disagreement, highlighting the instability of current alignment strategies. Employing a theoret","authors_text":"Aditya Gopalan, Debangshu Banerjee, Kintan Saha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T12:51:29Z","title":"Towards Reliable, Uncertainty-Aware Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15906","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":"sha256:1f309dcac82c453698f0e2a6ed22e01da0d2d9e887ebc3412c433afee4a3412b","target":"record","created_at":"2026-07-05T11:40:59Z","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":"eb75b926407cb9e1eb3032ba6bd5488748401700c0d2f472b8a6106a5e2ffbc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T12:51:29Z","title_canon_sha256":"6f9cae5b8982a82d0d8c18d75b37cfb1bb20275c1ffef9277c69cd2ab6e8939d"},"schema_version":"1.0","source":{"id":"2507.15906","kind":"arxiv","version":1}},"canonical_sha256":"e9d4c41e9228d85427df606b0495af942d76a3bfaac365c654ae481899420a15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d4c41e9228d85427df606b0495af942d76a3bfaac365c654ae481899420a15","first_computed_at":"2026-07-05T11:40:59.047094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:59.047094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6iQvxCY+y5kcy7sRMunKIRSRbe3C5yq2L0PT75QKdrZlHRV1RihWFcSsqbLophkXMbirZtiQ6KbcbC2kXS1ZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:59.047709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15906","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f309dcac82c453698f0e2a6ed22e01da0d2d9e887ebc3412c433afee4a3412b","sha256:c81476a5075a3a7b2c3f930168c901ed4078c9a1c252b5ff6a79affd7bb5ff1f"],"state_sha256":"b7d374361ec540c94bae7491a710dd87a8480a8d74aac6efe4b7b2446cf3da8c"}