{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MDYTKY3SIV22NHKIUJSOQ7LWJO","short_pith_number":"pith:MDYTKY3S","schema_version":"1.0","canonical_sha256":"60f13563724575a69d48a264e87d764b9af931c7642c290d48a671d43568b4a4","source":{"kind":"arxiv","id":"2601.02986","version":3},"attestation_state":"computed","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"},"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":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.02986","created_at":"2026-06-23T03:13:53.111974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.02986v3","created_at":"2026-06-23T03:13:53.111974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.02986","created_at":"2026-06-23T03:13:53.111974+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDYTKY3SIV22","created_at":"2026-06-23T03:13:53.111974+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDYTKY3SIV22NHKI","created_at":"2026-06-23T03:13:53.111974+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDYTKY3S","created_at":"2026-06-23T03:13:53.111974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.13602","citing_title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","ref_index":150,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO","json":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO.json","graph_json":"https://pith.science/api/pith-number/MDYTKY3SIV22NHKIUJSOQ7LWJO/graph.json","events_json":"https://pith.science/api/pith-number/MDYTKY3SIV22NHKIUJSOQ7LWJO/events.json","paper":"https://pith.science/paper/MDYTKY3S"},"agent_actions":{"view_html":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO","download_json":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO.json","view_paper":"https://pith.science/paper/MDYTKY3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.02986&json=true","fetch_graph":"https://pith.science/api/pith-number/MDYTKY3SIV22NHKIUJSOQ7LWJO/graph.json","fetch_events":"https://pith.science/api/pith-number/MDYTKY3SIV22NHKIUJSOQ7LWJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/action/storage_attestation","attest_author":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/action/author_attestation","sign_citation":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/action/citation_signature","submit_replication":"https://pith.science/pith/MDYTKY3SIV22NHKIUJSOQ7LWJO/action/replication_record"}},"created_at":"2026-06-23T03:13:53.111974+00:00","updated_at":"2026-06-23T03:13:53.111974+00:00"}