{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SJUGLHZ2JSRJ23F2FHN3XRIH6G","short_pith_number":"pith:SJUGLHZ2","canonical_record":{"source":{"id":"2506.05598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T21:23:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75ad9755eb0f718a5841eef490d7c13717f865a35c5d39866dfdeee1eb5a0f7c","abstract_canon_sha256":"5c78b75ecc38500f7fc2497a2aa8cbfaa137e0874a85ece2f7242425a8e59fd6"},"schema_version":"1.0"},"canonical_sha256":"9268659f3a4ca29d6cba29dbbbc507f19819418f7391a8c977bccbdac2e448dc","source":{"kind":"arxiv","id":"2506.05598","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05598","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05598v1","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05598","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_12","alias_value":"SJUGLHZ2JSRJ","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_16","alias_value":"SJUGLHZ2JSRJ23F2","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_8","alias_value":"SJUGLHZ2","created_at":"2026-07-05T11:17:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SJUGLHZ2JSRJ23F2FHN3XRIH6G","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T21:23:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75ad9755eb0f718a5841eef490d7c13717f865a35c5d39866dfdeee1eb5a0f7c","abstract_canon_sha256":"5c78b75ecc38500f7fc2497a2aa8cbfaa137e0874a85ece2f7242425a8e59fd6"},"schema_version":"1.0"},"canonical_sha256":"9268659f3a4ca29d6cba29dbbbc507f19819418f7391a8c977bccbdac2e448dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:06.577814Z","signature_b64":"PjwHfx3oo9HizkOxQ1DJfg0nLnlVtPznZVR/Nvn+tTGt2sIQlFihTXQlLhSyR/Xcu/l2475/cu6EtNxIHYagBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9268659f3a4ca29d6cba29dbbbc507f19819418f7391a8c977bccbdac2e448dc","last_reissued_at":"2026-07-05T11:17:06.577224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:06.577224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05598","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":"2026-07-05T11:17:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOrrnN/P7k269vlytKReR2LI33VD783xtq4tvNANoFLrmOLkxbo42orDGZsvx6SpKsaKs11EUOyP5/qLxnIEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:59.355324Z"},"content_sha256":"0b62e6283a849e1f2f74bd9cb767207868527305dff96d399798286629718ee6","schema_version":"1.0","event_id":"sha256:0b62e6283a849e1f2f74bd9cb767207868527305dff96d399798286629718ee6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SJUGLHZ2JSRJ23F2FHN3XRIH6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditri Bhagirath, Daniel Frees, Diyi Yang, Michael J Ryan, Omar Shaikh, William Held","submitted_at":"2025-06-05T21:23:16Z","abstract_excerpt":"Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as demographic details or a predefined set of preference categories. To this end, we introduce SynthesizeMe, an approach to inducing synthetic user personas from user interactions for personalized reward modeling. SynthesizeMe first generates and verifies reasoning to explain user preferences, then induces synthetic user personas from that reasoning, and finally "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05598","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/2506.05598/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":"2026-07-05T11:17:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Z4EOkPl5HDjn5+s7RznRbOQh9pKxOViINdL0Ub28ifOfrphIROt/CfY/ZTm8K6yu2TmsH8bmGkWtjmQ1ogFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:59.356310Z"},"content_sha256":"68ec5f353d670b77391bb508adc6294b38080eb4024b777b496370de874db3c9","schema_version":"1.0","event_id":"sha256:68ec5f353d670b77391bb508adc6294b38080eb4024b777b496370de874db3c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/bundle.json","state_url":"https://pith.science/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/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":"2026-08-08T02:34:59Z","links":{"resolver":"https://pith.science/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G","bundle":"https://pith.science/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/bundle.json","state":"https://pith.science/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJUGLHZ2JSRJ23F2FHN3XRIH6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJUGLHZ2JSRJ23F2FHN3XRIH6G","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":"5c78b75ecc38500f7fc2497a2aa8cbfaa137e0874a85ece2f7242425a8e59fd6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T21:23:16Z","title_canon_sha256":"75ad9755eb0f718a5841eef490d7c13717f865a35c5d39866dfdeee1eb5a0f7c"},"schema_version":"1.0","source":{"id":"2506.05598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05598","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05598v1","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05598","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_12","alias_value":"SJUGLHZ2JSRJ","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_16","alias_value":"SJUGLHZ2JSRJ23F2","created_at":"2026-07-05T11:17:06Z"},{"alias_kind":"pith_short_8","alias_value":"SJUGLHZ2","created_at":"2026-07-05T11:17:06Z"}],"graph_snapshots":[{"event_id":"sha256:68ec5f353d670b77391bb508adc6294b38080eb4024b777b496370de874db3c9","target":"graph","created_at":"2026-07-05T11:17:06Z","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/2506.05598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent calls for pluralistic alignment of Large Language Models (LLMs) encourage adapting models to diverse user preferences. However, most prior work on personalized reward models heavily rely on additional identity information, such as demographic details or a predefined set of preference categories. To this end, we introduce SynthesizeMe, an approach to inducing synthetic user personas from user interactions for personalized reward modeling. SynthesizeMe first generates and verifies reasoning to explain user preferences, then induces synthetic user personas from that reasoning, and finally ","authors_text":"Aditri Bhagirath, Daniel Frees, Diyi Yang, Michael J Ryan, Omar Shaikh, William Held","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T21:23:16Z","title":"SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05598","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":"sha256:0b62e6283a849e1f2f74bd9cb767207868527305dff96d399798286629718ee6","target":"record","created_at":"2026-07-05T11:17:06Z","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":"5c78b75ecc38500f7fc2497a2aa8cbfaa137e0874a85ece2f7242425a8e59fd6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T21:23:16Z","title_canon_sha256":"75ad9755eb0f718a5841eef490d7c13717f865a35c5d39866dfdeee1eb5a0f7c"},"schema_version":"1.0","source":{"id":"2506.05598","kind":"arxiv","version":1}},"canonical_sha256":"9268659f3a4ca29d6cba29dbbbc507f19819418f7391a8c977bccbdac2e448dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9268659f3a4ca29d6cba29dbbbc507f19819418f7391a8c977bccbdac2e448dc","first_computed_at":"2026-07-05T11:17:06.577224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:06.577224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PjwHfx3oo9HizkOxQ1DJfg0nLnlVtPznZVR/Nvn+tTGt2sIQlFihTXQlLhSyR/Xcu/l2475/cu6EtNxIHYagBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:06.577814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b62e6283a849e1f2f74bd9cb767207868527305dff96d399798286629718ee6","sha256:68ec5f353d670b77391bb508adc6294b38080eb4024b777b496370de874db3c9"],"state_sha256":"6fb55959313f85335f97e915df03b5b4fbcc863decf459387cae4fd3de4a58ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQJ9FK9lSk5GeqsXqtMSR7AM5mAqLtCHC+yFRP+n5xzf5UqrR7GGwG7BScyCVr891dpdvxDgkH/OkkqVA9/iBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:34:59.364960Z","bundle_sha256":"684d9e56fae86dba9146acdf7b7958fe428c3d44ed9855667b7ce5f703622fee"}}