{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AY2RG55GJRHOJCHYOZZIRXQAMM","short_pith_number":"pith:AY2RG55G","schema_version":"1.0","canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","source":{"kind":"arxiv","id":"2605.30323","version":1},"attestation_state":"computed","paper":{"title":"In-Context Reward Adaptation for Robust Preference Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ermin Wei, Zheng Xu, Zhenyu Sun","submitted_at":"2026-05-28T17:56:54Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model often lacks the robustness required to generalize to unseen preference domains. While existing multi-reward frameworks attempt to address this, they are often restricted to a fixed set of known domains and fail to adapt to unseen human distributions without costly retraining. In this work, we propose In-Context Reward Adaptation, a transformer-based framework de"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.30323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:56:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8cad2e33d54b35f1edb181688ad8b5123f66b3afee31f30d2325282d9faaed2b","abstract_canon_sha256":"0f226b8ca21e9191aa2c6b237a5e35607b34e7aa7b99df22949ce1ecee67a635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:16.500436Z","signature_b64":"V3Cavz8WCAX8JaO3xnLn8s3v1q+3/2K7sa2X+CBeT/3+WibsWOotPnBaavKNSDPPXTjTcpXcx89zbeh5PPRwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","last_reissued_at":"2026-05-29T02:06:16.500030Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:16.500030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Reward Adaptation for Robust Preference Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ermin Wei, Zheng Xu, Zhenyu Sun","submitted_at":"2026-05-28T17:56:54Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model often lacks the robustness required to generalize to unseen preference domains. While existing multi-reward frameworks attempt to address this, they are often restricted to a fixed set of known domains and fail to adapt to unseen human distributions without costly retraining. In this work, we propose In-Context Reward Adaptation, a transformer-based framework de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30323","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.30323/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.30323","created_at":"2026-05-29T02:06:16.500094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30323v1","created_at":"2026-05-29T02:06:16.500094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30323","created_at":"2026-05-29T02:06:16.500094+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY2RG55GJRHO","created_at":"2026-05-29T02:06:16.500094+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY2RG55GJRHOJCHY","created_at":"2026-05-29T02:06:16.500094+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY2RG55G","created_at":"2026-05-29T02:06:16.500094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM","json":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM.json","graph_json":"https://pith.science/api/pith-number/AY2RG55GJRHOJCHYOZZIRXQAMM/graph.json","events_json":"https://pith.science/api/pith-number/AY2RG55GJRHOJCHYOZZIRXQAMM/events.json","paper":"https://pith.science/paper/AY2RG55G"},"agent_actions":{"view_html":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM","download_json":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM.json","view_paper":"https://pith.science/paper/AY2RG55G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30323&json=true","fetch_graph":"https://pith.science/api/pith-number/AY2RG55GJRHOJCHYOZZIRXQAMM/graph.json","fetch_events":"https://pith.science/api/pith-number/AY2RG55GJRHOJCHYOZZIRXQAMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/action/storage_attestation","attest_author":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/action/author_attestation","sign_citation":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/action/citation_signature","submit_replication":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/action/replication_record"}},"created_at":"2026-05-29T02:06:16.500094+00:00","updated_at":"2026-05-29T02:06:16.500094+00:00"}