{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UDVBFP75RR6HELUNCKOTVXNLYJ","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":"e2e963c9b1908d910fae6e3196a2ca5a0e3d3e972151f11fd9d48a9d6463cc78","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T15:55:56Z","title_canon_sha256":"2cc4cf1a6728151fb968eb5520c0eccd4be1f8caf36bdab9af4e3381003bc2b1"},"schema_version":"1.0","source":{"id":"2602.08819","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08819","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08819v2","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08819","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"UDVBFP75RR6H","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"UDVBFP75RR6HELUN","created_at":"2026-05-21T01:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"UDVBFP75","created_at":"2026-05-21T01:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:e3bc3e86b7ab88c4c0cd9f63ff95d61b2261d192fbff29a5ea6a4069af3ba863","target":"graph","created_at":"2026-05-21T01:04:22Z","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/2602.08819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to settings such as verifiable rewards and multi-objective alignment, RMs are expected to encode more complex and multifaceted preference distributions. However, classifier RMs remain static once trained, limiting their adaptability at test time. We propose Variational In-Context Reward Modeling (ICRM), a novel Bayesian reward modeling objective that enables test-time steerability via in-context preference demonstrations. ICRM casts reward modeling as amor","authors_text":"Jiwoo Hong, Shao Tang, Zhipeng Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T15:55:56Z","title":"Bayesian Preference Learning for Test-Time Steerable Reward Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08819","kind":"arxiv","version":2},"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":"sha256:55e792e4b7e91f1ca2af14ce27a8c25d18bd92adc8965c95c1ddd8890301b12c","target":"record","created_at":"2026-05-21T01:04:22Z","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":"e2e963c9b1908d910fae6e3196a2ca5a0e3d3e972151f11fd9d48a9d6463cc78","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T15:55:56Z","title_canon_sha256":"2cc4cf1a6728151fb968eb5520c0eccd4be1f8caf36bdab9af4e3381003bc2b1"},"schema_version":"1.0","source":{"id":"2602.08819","kind":"arxiv","version":2}},"canonical_sha256":"a0ea12bffd8c7c722e8d129d3addabc2784ad3580de8a3d31642a580f0f4bc1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0ea12bffd8c7c722e8d129d3addabc2784ad3580de8a3d31642a580f0f4bc1c","first_computed_at":"2026-05-21T01:04:22.649496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:22.649496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hc2SgI07dzRvD4rGWUMwygao4OtCsv+0aqf6KR11K+X+7cnEExxzprktbzd2BwlILaSy8YCEwKXph2JLm4taCA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:22.653933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08819","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55e792e4b7e91f1ca2af14ce27a8c25d18bd92adc8965c95c1ddd8890301b12c","sha256:e3bc3e86b7ab88c4c0cd9f63ff95d61b2261d192fbff29a5ea6a4069af3ba863"],"state_sha256":"da840da15ba958d66f05c706d12ce777b4be6cb859b5f6dca06e50c4e6c0ad37"}