{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A7SPZLVFZHCUL2XRXRLXFJGSOC","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":"ef4b0a2dda253769d71b209b7422b1f2d98069f13053649fa25b48c90ad2a791","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T14:53:32Z","title_canon_sha256":"305f12860bdb6742272b1064d822b83b6696ae6e17959f8511936b2699a9e9ea"},"schema_version":"1.0","source":{"id":"2601.14032","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.14032","created_at":"2026-07-28T01:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2601.14032v2","created_at":"2026-07-28T01:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14032","created_at":"2026-07-28T01:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"A7SPZLVFZHCU","created_at":"2026-07-28T01:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"A7SPZLVFZHCUL2XR","created_at":"2026-07-28T01:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"A7SPZLVF","created_at":"2026-07-28T01:22:28Z"}],"graph_snapshots":[{"event_id":"sha256:95d941d611bd4bf92cb0c83934fe0b2a737518303d98dc01a0b5050131eb45c4","target":"graph","created_at":"2026-07-28T01:22:28Z","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/2601.14032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-quality human preference annotations, distilling preferences from generative LLMs has emerged as a standard practice. However, existing approaches predominantly treat teacher models as simple binary annotators, failing to fully exploit the rich knowledge and capabilities for RM distillation. To address this, we propose RM-Distiller, a framework designed to systematically exploit the multifaceted capabilities of teacher LLMs: (1) Refinement capability,","authors_text":"Chenglong Wang, Fuhai Song, Hailong Cao, Hongli Zhou, Hui Huang, Lvyuan Han, Muyun Yang, Tiejun Zhao, Wei Liu, Wenhao Jiang, Xingyuan Bu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T14:53:32Z","title":"RM-Distiller: Exploiting Generative LLM for Reward Model Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14032","kind":"arxiv","version":2},"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:b1e4a87f58583959ff2628b59960ea03aaf28851439b4b579ee3385e98edcd86","target":"record","created_at":"2026-07-28T01:22:28Z","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":"ef4b0a2dda253769d71b209b7422b1f2d98069f13053649fa25b48c90ad2a791","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-20T14:53:32Z","title_canon_sha256":"305f12860bdb6742272b1064d822b83b6696ae6e17959f8511936b2699a9e9ea"},"schema_version":"1.0","source":{"id":"2601.14032","kind":"arxiv","version":2}},"canonical_sha256":"07e4fcaea5c9c545eaf1bc5772a4d270a45b9329851be4dc0e157948e16311af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07e4fcaea5c9c545eaf1bc5772a4d270a45b9329851be4dc0e157948e16311af","first_computed_at":"2026-07-28T01:22:28.312143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:28.312143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fpO0fg3FdGNXB0qrC9drDrL0gQIu3B0nAusJ1jTyztWIAFBoG9rKmEdilmp5csH/1HPwI4CNATaXyl/EEbEMCA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:28.313252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.14032","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1e4a87f58583959ff2628b59960ea03aaf28851439b4b579ee3385e98edcd86","sha256:95d941d611bd4bf92cb0c83934fe0b2a737518303d98dc01a0b5050131eb45c4"],"state_sha256":"2f7b9e8d7b9562f3df775e467c057a0f371e68476a803b654d046e495647792d"}