{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO","short_pith_number":"pith:MDYTKY3S","canonical_record":{"source":{"id":"2601.02986","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T12:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"bd0023e53efd2552cf40e487c74e538b2722c03b24b3f89cf1951773a470f51d","abstract_canon_sha256":"9f59bc62fb7dbd6ac008a8e66d5745247b45e948d929d06fd0e052ad5077dc96"},"schema_version":"1.0"},"canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","source":{"kind":"arxiv","id":"2601.02986","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.02986","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"arxiv_version","alias_value":"2601.02986v3","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02986","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDYTKY3SIV22","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDYTKY3SIV22NHKI","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDYTKY3S","created_at":"2026-06-23T03:13:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO","target":"record","payload":{"canonical_record":{"source":{"id":"2601.02986","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T12:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"bd0023e53efd2552cf40e487c74e538b2722c03b24b3f89cf1951773a470f51d","abstract_canon_sha256":"9f59bc62fb7dbd6ac008a8e66d5745247b45e948d929d06fd0e052ad5077dc96"},"schema_version":"1.0"},"canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:53.112307Z","signature_b64":"Pm2tdpUnxzlbGTFJ/YQc5l/SVoCoYfjMpHlgDRGKw3VQONpd/c82V4yewUi7IjdVf+GFd+7q4KbGlv63ZMMWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","last_reissued_at":"2026-06-23T03:13:53.111918Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:53.111918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.02986","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TamCMKlmvU7BAN/uinZA7LzWMG3RTXHXC40WIkzKcJ0AxbeG6UX3vLkG2OBH0j5bAi6SkzXnH4v0NbFafkq4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:23:07.305468Z"},"content_sha256":"866b5154d275b7b2c8a1cc030743e50e2357a176f54d6d007d37a7c520507734","schema_version":"1.0","event_id":"sha256:866b5154d275b7b2c8a1cc030743e50e2357a176f54d6d007d37a7c520507734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongha Lee, Kwangwook Seo","submitted_at":"2026-01-06T12:53:53Z","abstract_excerpt":"Recent approaches in personalized reward modeling have primarily focused on leveraging user interaction history to align model judgments with individual preferences. However, existing approaches largely treat user context as a static or implicit conditioning signal, failing to capture the dynamic and multi-faceted nature of human judgment. In this paper, we propose P-Check, a novel personalized reward modeling framework, designed to train a plug-and-play checklist generator that synthesizes dynamic evaluation criteria for guiding the reward prediction. To better align these checklists with per"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"P-Check not only improves reward accuracy but also enhances downstream personalized generation, and remains robust in OOD scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a learned checklist generator can reliably synthesize dynamic, multi-faceted criteria that capture nuanced personal judgment without introducing artifacts or requiring user-specific data beyond what static baselines already use.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"P-Check advances personalized reward modeling by training a dynamic checklist generator and preference-contrastive weighting to improve reward accuracy, downstream generation, and OOD robustness.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8bf392728ad17cb37e2e8d35d2905c41f95fd0657f2644385cc74fd86fdf67d1"},"source":{"id":"2601.02986","kind":"arxiv","version":3},"verdict":{"id":"1c8055a6-b917-4fc4-8e6f-1f7d2c38d102","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T17:34:46.181441Z","strongest_claim":"P-Check not only improves reward accuracy but also enhances downstream personalized generation, and remains robust in OOD scenarios.","one_line_summary":"P-Check advances personalized reward modeling by training a dynamic checklist generator and preference-contrastive weighting to improve reward accuracy, downstream generation, and OOD robustness.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a learned checklist generator can reliably synthesize dynamic, multi-faceted criteria that capture nuanced personal judgment without introducing artifacts or requiring user-specific data beyond what static baselines already use.","pith_extraction_headline":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.02986/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":2,"snapshot_sha256":"bfadb63e5113f8f1aa3bd98227b457c7e82326e48cc315aa2a9f8e5ff2445126"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1c8055a6-b917-4fc4-8e6f-1f7d2c38d102"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pycGK2c0NRXmuuAjh0ccPIvNaUQTfVvgStOpj9DiJsbrKQP2d2CtNepNZftLDimpn2FyKgxPodKYLT8nPHoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:23:07.305892Z"},"content_sha256":"bdabe04363ab7296cff7cbcc3871cc1a797d68d44a5c2c5da9c4a09d0de49667","schema_version":"1.0","event_id":"sha256:bdabe04363ab7296cff7cbcc3871cc1a797d68d44a5c2c5da9c4a09d0de49667"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/bundle.json","state_url":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/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":"2026-08-05T13:23:07Z","links":{"resolver":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO","bundle":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/bundle.json","state":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO","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":"9f59bc62fb7dbd6ac008a8e66d5745247b45e948d929d06fd0e052ad5077dc96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T12:53:53Z","title_canon_sha256":"bd0023e53efd2552cf40e487c74e538b2722c03b24b3f89cf1951773a470f51d"},"schema_version":"1.0","source":{"id":"2601.02986","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.02986","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"arxiv_version","alias_value":"2601.02986v3","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02986","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_12","alias_value":"MDYTKY3SIV22","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_16","alias_value":"MDYTKY3SIV22NHKI","created_at":"2026-06-23T03:13:53Z"},{"alias_kind":"pith_short_8","alias_value":"MDYTKY3S","created_at":"2026-06-23T03:13:53Z"}],"graph_snapshots":[{"event_id":"sha256:bdabe04363ab7296cff7cbcc3871cc1a797d68d44a5c2c5da9c4a09d0de49667","target":"graph","created_at":"2026-06-23T03:13:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"P-Check not only improves reward accuracy but also enhances downstream personalized generation, and remains robust in OOD scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a learned checklist generator can reliably synthesize dynamic, multi-faceted criteria that capture nuanced personal judgment without introducing artifacts or requiring user-specific data beyond what static baselines already use."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"P-Check advances personalized reward modeling by training a dynamic checklist generator and preference-contrastive weighting to improve reward accuracy, downstream generation, and OOD robustness."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences."}],"snapshot_sha256":"8bf392728ad17cb37e2e8d35d2905c41f95fd0657f2644385cc74fd86fdf67d1"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bfadb63e5113f8f1aa3bd98227b457c7e82326e48cc315aa2a9f8e5ff2445126"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.02986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent approaches in personalized reward modeling have primarily focused on leveraging user interaction history to align model judgments with individual preferences. However, existing approaches largely treat user context as a static or implicit conditioning signal, failing to capture the dynamic and multi-faceted nature of human judgment. In this paper, we propose P-Check, a novel personalized reward modeling framework, designed to train a plug-and-play checklist generator that synthesizes dynamic evaluation criteria for guiding the reward prediction. To better align these checklists with per","authors_text":"Dongha Lee, Kwangwook Seo","cross_cats":[],"headline":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T12:53:53Z","title":"P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.02986","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T17:34:46.181441Z","id":"1c8055a6-b917-4fc4-8e6f-1f7d2c38d102","model_set":{"reader":"grok-4.3"},"one_line_summary":"P-Check advances personalized reward modeling by training a dynamic checklist generator and preference-contrastive weighting to improve reward accuracy, downstream generation, and OOD robustness.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"P-Check trains a checklist generator to produce dynamic criteria that align reward models more closely with individual preferences.","strongest_claim":"P-Check not only improves reward accuracy but also enhances downstream personalized generation, and remains robust in OOD scenarios.","weakest_assumption":"That a learned checklist generator can reliably synthesize dynamic, multi-faceted criteria that capture nuanced personal judgment without introducing artifacts or requiring user-specific data beyond what static baselines already use."}},"verdict_id":"1c8055a6-b917-4fc4-8e6f-1f7d2c38d102"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:866b5154d275b7b2c8a1cc030743e50e2357a176f54d6d007d37a7c520507734","target":"record","created_at":"2026-06-23T03:13:53Z","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":"9f59bc62fb7dbd6ac008a8e66d5745247b45e948d929d06fd0e052ad5077dc96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-06T12:53:53Z","title_canon_sha256":"bd0023e53efd2552cf40e487c74e538b2722c03b24b3f89cf1951773a470f51d"},"schema_version":"1.0","source":{"id":"2601.02986","kind":"arxiv","version":3}},"canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","first_computed_at":"2026-06-23T03:13:53.111918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:53.111918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pm2tdpUnxzlbGTFJ/YQc5l/SVoCoYfjMpHlgDRGKw3VQONpd/c82V4yewUi7IjdVf+GFd+7q4KbGlv63ZMMWDw==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:53.112307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.02986","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:866b5154d275b7b2c8a1cc030743e50e2357a176f54d6d007d37a7c520507734","sha256:bdabe04363ab7296cff7cbcc3871cc1a797d68d44a5c2c5da9c4a09d0de49667"],"state_sha256":"b5fe9667013d2df9b3ed85e6870f3540ea3df83bc00d1df112660c2f65793825"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQCmr7VyvyRwsrEzXcPk54HsSZY19vV33moeORazsGM7acNXEq9AH+6iV3QH/rSiRjmM9DF8nkOQ2XWC1YMjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:23:07.310247Z","bundle_sha256":"92b583ac5e18018953fb4e3634566dcd2107db2a7e1683e3ce5a23c61bd36f7f"}}