{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C4HMXMNBWGUWHUVSXLSVM4R74S","short_pith_number":"pith:C4HMXMNB","canonical_record":{"source":{"id":"2410.14001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:06:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"efd60f9ef190cb781ff4269cb7a1e155fd02e1747d3cb787801dcd7ce2430150","abstract_canon_sha256":"cbce5d599ca9be912be506045ac4efcf70f862ac29f2ca79f4b3f4a54c7d5fd5"},"schema_version":"1.0"},"canonical_sha256":"170ecbb1a1b1a963d2b2bae556723fe49c2c0d845bc753207d956d3b9304b91f","source":{"kind":"arxiv","id":"2410.14001","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14001","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14001v1","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14001","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"C4HMXMNBWGUW","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"C4HMXMNBWGUWHUVS","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"C4HMXMNB","created_at":"2026-07-05T09:22:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C4HMXMNBWGUWHUVSXLSVM4R74S","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:06:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"efd60f9ef190cb781ff4269cb7a1e155fd02e1747d3cb787801dcd7ce2430150","abstract_canon_sha256":"cbce5d599ca9be912be506045ac4efcf70f862ac29f2ca79f4b3f4a54c7d5fd5"},"schema_version":"1.0"},"canonical_sha256":"170ecbb1a1b1a963d2b2bae556723fe49c2c0d845bc753207d956d3b9304b91f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:25.633200Z","signature_b64":"SLNUORlnJo+3nNTYc+SYGsCU7a4Uo75Z7GXeR5ogzRIa4h63XIn3a9Xf2+7iRzRPORlXPT4mzmQiYvUuVk0MCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"170ecbb1a1b1a963d2b2bae556723fe49c2c0d845bc753207d956d3b9304b91f","last_reissued_at":"2026-07-05T09:22:25.632696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:25.632696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14001","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":"2026-07-05T09:22:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bY66hMJiiSiYWEQ3tpz4hsn2BtVZyLbMSCoI9wV4++IhEn+UL7INnxKdDskTVgjA47e6FUgQdIKJk3taM5jCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:24:09.442064Z"},"content_sha256":"3dc48757a83ea02ecb9e3d6fe665f2ad9854685f8e01a28de34185521e1bd798","schema_version":"1.0","event_id":"sha256:3dc48757a83ea02ecb9e3d6fe665f2ad9854685f8e01a28de34185521e1bd798"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C4HMXMNBWGUWHUVSXLSVM4R74S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalized Adaptation via In-Context Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Allison Lau, Keertana Chidambaram, Rahul G. Krishnan, Vahid Balazadeh, Vasilis Syrgkanis, Younwoo Choi","submitted_at":"2024-10-17T20:06:02Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences. However, existing approaches often neglect individual user preferences, leading to suboptimal personalization. We present the Preference Pretrained Transformer (PPT), a novel approach for adaptive personalization using online user feedback. PPT leverages the in-context learning capabilities of transformers to dynamically adapt to individual preferences. Our approach consists of two phases: (1) an offline phase where we train a single policy model using a history-dependent los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14001","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/2410.14001/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":"2026-07-05T09:22:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jy+FEGvZimP9ZbXfBWAPmNIB+bapj+15aMJhFdtQEZR+2MrUBTramtGl659xZhvfBXQvwBlF027uzfqZeCKICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:24:09.442561Z"},"content_sha256":"b517c7f663dcfdda547ed5f344d403ea8a9aadb70e68b21ea0121ff30dae9f19","schema_version":"1.0","event_id":"sha256:b517c7f663dcfdda547ed5f344d403ea8a9aadb70e68b21ea0121ff30dae9f19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/bundle.json","state_url":"https://pith.science/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/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":"2026-08-22T08:24:09Z","links":{"resolver":"https://pith.science/pith/C4HMXMNBWGUWHUVSXLSVM4R74S","bundle":"https://pith.science/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/bundle.json","state":"https://pith.science/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4HMXMNBWGUWHUVSXLSVM4R74S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C4HMXMNBWGUWHUVSXLSVM4R74S","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":"cbce5d599ca9be912be506045ac4efcf70f862ac29f2ca79f4b3f4a54c7d5fd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:06:02Z","title_canon_sha256":"efd60f9ef190cb781ff4269cb7a1e155fd02e1747d3cb787801dcd7ce2430150"},"schema_version":"1.0","source":{"id":"2410.14001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14001","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14001v1","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14001","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_12","alias_value":"C4HMXMNBWGUW","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_16","alias_value":"C4HMXMNBWGUWHUVS","created_at":"2026-07-05T09:22:25Z"},{"alias_kind":"pith_short_8","alias_value":"C4HMXMNB","created_at":"2026-07-05T09:22:25Z"}],"graph_snapshots":[{"event_id":"sha256:b517c7f663dcfdda547ed5f344d403ea8a9aadb70e68b21ea0121ff30dae9f19","target":"graph","created_at":"2026-07-05T09:22:25Z","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/2410.14001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is widely used to align Language Models (LMs) with human preferences. However, existing approaches often neglect individual user preferences, leading to suboptimal personalization. We present the Preference Pretrained Transformer (PPT), a novel approach for adaptive personalization using online user feedback. PPT leverages the in-context learning capabilities of transformers to dynamically adapt to individual preferences. Our approach consists of two phases: (1) an offline phase where we train a single policy model using a history-dependent los","authors_text":"Allison Lau, Keertana Chidambaram, Rahul G. Krishnan, Vahid Balazadeh, Vasilis Syrgkanis, Younwoo Choi","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:06:02Z","title":"Personalized Adaptation via In-Context Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14001","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":"sha256:3dc48757a83ea02ecb9e3d6fe665f2ad9854685f8e01a28de34185521e1bd798","target":"record","created_at":"2026-07-05T09:22:25Z","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":"cbce5d599ca9be912be506045ac4efcf70f862ac29f2ca79f4b3f4a54c7d5fd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:06:02Z","title_canon_sha256":"efd60f9ef190cb781ff4269cb7a1e155fd02e1747d3cb787801dcd7ce2430150"},"schema_version":"1.0","source":{"id":"2410.14001","kind":"arxiv","version":1}},"canonical_sha256":"170ecbb1a1b1a963d2b2bae556723fe49c2c0d845bc753207d956d3b9304b91f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"170ecbb1a1b1a963d2b2bae556723fe49c2c0d845bc753207d956d3b9304b91f","first_computed_at":"2026-07-05T09:22:25.632696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:25.632696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SLNUORlnJo+3nNTYc+SYGsCU7a4Uo75Z7GXeR5ogzRIa4h63XIn3a9Xf2+7iRzRPORlXPT4mzmQiYvUuVk0MCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:25.633200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc48757a83ea02ecb9e3d6fe665f2ad9854685f8e01a28de34185521e1bd798","sha256:b517c7f663dcfdda547ed5f344d403ea8a9aadb70e68b21ea0121ff30dae9f19"],"state_sha256":"ccf985b66d192cd851437c8c0382976f8671019bb43bcece1d029247c8e6aade"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nK8Alxmucp/4kvtRKZogCgQX6AMWStx+Thm262QM9ADB3pEptGhajYnsaI5SBmr/rZU5TIH9XW5iyx7yUX2dCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:24:09.447233Z","bundle_sha256":"e8be39ab8eebbf1e09e5dfddd2814b0508a4aacef6d896f25d37ae4814f42bbe"}}