{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AY2RG55GJRHOJCHYOZZIRXQAMM","short_pith_number":"pith:AY2RG55G","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"},"canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","source":{"kind":"arxiv","id":"2605.30323","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30323","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30323v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30323","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"AY2RG55GJRHO","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"AY2RG55GJRHOJCHY","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"AY2RG55G","created_at":"2026-05-29T02:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AY2RG55GJRHOJCHYOZZIRXQAMM","target":"record","payload":{"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"},"canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","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"},"source_kind":"arxiv","source_id":"2605.30323","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZjDvqOdCyEGXax5lOQ4hOUCuvW9SnVExV2m8XiG/HNSyzFFs14VNP7w27A4ad/KtccpTWPNv7tF665wZbbTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:09:30.856661Z"},"content_sha256":"5cc38e924a244e43f80e3a98341a9980125b04868da4c02323aa26351dfad7f4","schema_version":"1.0","event_id":"sha256:5cc38e924a244e43f80e3a98341a9980125b04868da4c02323aa26351dfad7f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AY2RG55GJRHOJCHYOZZIRXQAMM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnRiIEZwHSm+UiTicXudrvNzLooupoeGY2sqwODLmEvT0AhMdsary7hYqZdGFTu1f+TXrlJc67C8yaE8U8ZXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T17:09:30.857034Z"},"content_sha256":"29aefe84eabed754f6ce440d91bc37ecd0f41e14bd3454a733f7f334c3cbc5a3","schema_version":"1.0","event_id":"sha256:29aefe84eabed754f6ce440d91bc37ecd0f41e14bd3454a733f7f334c3cbc5a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/bundle.json","state_url":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T17:09:30Z","links":{"resolver":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM","bundle":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/bundle.json","state":"https://pith.science/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AY2RG55GJRHOJCHYOZZIRXQAMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AY2RG55GJRHOJCHYOZZIRXQAMM","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":"0f226b8ca21e9191aa2c6b237a5e35607b34e7aa7b99df22949ce1ecee67a635","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:56:54Z","title_canon_sha256":"8cad2e33d54b35f1edb181688ad8b5123f66b3afee31f30d2325282d9faaed2b"},"schema_version":"1.0","source":{"id":"2605.30323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30323","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30323v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30323","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"AY2RG55GJRHO","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"AY2RG55GJRHOJCHY","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"AY2RG55G","created_at":"2026-05-29T02:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:29aefe84eabed754f6ce440d91bc37ecd0f41e14bd3454a733f7f334c3cbc5a3","target":"graph","created_at":"2026-05-29T02:06:16Z","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/2605.30323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ermin Wei, Zheng Xu, Zhenyu Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:56:54Z","title":"In-Context Reward Adaptation for Robust Preference Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30323","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":"sha256:5cc38e924a244e43f80e3a98341a9980125b04868da4c02323aa26351dfad7f4","target":"record","created_at":"2026-05-29T02:06:16Z","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":"0f226b8ca21e9191aa2c6b237a5e35607b34e7aa7b99df22949ce1ecee67a635","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:56:54Z","title_canon_sha256":"8cad2e33d54b35f1edb181688ad8b5123f66b3afee31f30d2325282d9faaed2b"},"schema_version":"1.0","source":{"id":"2605.30323","kind":"arxiv","version":1}},"canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06351377a64c4ee488f8767288de00631042043ea4c4ad0749e898af7739728d","first_computed_at":"2026-05-29T02:06:16.500030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:16.500030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V3Cavz8WCAX8JaO3xnLn8s3v1q+3/2K7sa2X+CBeT/3+WibsWOotPnBaavKNSDPPXTjTcpXcx89zbeh5PPRwCQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:16.500436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc38e924a244e43f80e3a98341a9980125b04868da4c02323aa26351dfad7f4","sha256:29aefe84eabed754f6ce440d91bc37ecd0f41e14bd3454a733f7f334c3cbc5a3"],"state_sha256":"32e780f040e6f6a27f347091ded7eeb9cc4d4f2c70a1d07d845158a0fc0766f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kS54uXMdST1m8wZWZj4hT0ofWHUHbBLqzNG4JdFx+6vss5Xg2PtHAGEbmqsBn8fAGuWoLjBWu2Jfod6+eHC2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T17:09:30.859060Z","bundle_sha256":"141981ab1927cab043f70a352fe66b3d06687aded500caf33bd2b3d205e44ecf"}}