{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G7RBLVKPEHLWITQNDHOVOSJTGW","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":"54639d5e1d5b97e652512d761f4cfbe8a9a6b7466e660b324a2820c9ef7eb221","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T17:56:57Z","title_canon_sha256":"ec8bce7ee9ab4fad9b44b0cbe6afa39ce78feb4e2eb2e199f3ecf8652b237dba"},"schema_version":"1.0","source":{"id":"2606.03980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03980","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03980v1","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03980","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"G7RBLVKPEHLW","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"G7RBLVKPEHLWITQN","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"G7RBLVKP","created_at":"2026-06-03T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:47e249653d0c3e63a1642ed07a4dfd3db63a7873781b8f8f43191d68b67a9265","target":"graph","created_at":"2026-06-03T02:06:08Z","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/2606.03980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored. To this end, we propose Skill Reward Model (Skill-RM), a unified framework that reformulates reward modeling as the execution of a reusable Reward-Evaluation Skill. By treating reward computat","authors_text":"Gangwei Jiang, Guanjun Jiang, Jiaqi Guo, Jingwei Ni, Junling Liu, Kai Tang, Mengyu Zhou, Pengyu Cheng, Qinliang su, Siyuan Huang, Tao Chen, Xiaoxi Jiang, Yihao Liu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T17:56:57Z","title":"Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03980","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:f3cefd57cd7582d35d1f40bcf4e91fbf07f9bdefd5e1c6a7e1882e1ef12350a2","target":"record","created_at":"2026-06-03T02:06:08Z","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":"54639d5e1d5b97e652512d761f4cfbe8a9a6b7466e660b324a2820c9ef7eb221","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T17:56:57Z","title_canon_sha256":"ec8bce7ee9ab4fad9b44b0cbe6afa39ce78feb4e2eb2e199f3ecf8652b237dba"},"schema_version":"1.0","source":{"id":"2606.03980","kind":"arxiv","version":1}},"canonical_sha256":"37e215d54f21d7644e0d19dd57493335a79935066800659f8fddadfcad82c5ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37e215d54f21d7644e0d19dd57493335a79935066800659f8fddadfcad82c5ad","first_computed_at":"2026-06-03T02:06:08.570786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:08.570786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KUSwIpZiQxIOCk7ETrfSo+uCUPHj6nZPF9aAnO1aU7g46rjxX2+lnqo9FC338JNLxYl6OqdUTKMGrgAnoKhHAg==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:08.571189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3cefd57cd7582d35d1f40bcf4e91fbf07f9bdefd5e1c6a7e1882e1ef12350a2","sha256:47e249653d0c3e63a1642ed07a4dfd3db63a7873781b8f8f43191d68b67a9265"],"state_sha256":"58fbd39f5fd9d466fc61edece4679120912bbf0d1b465bd7b19f863c6d3101a8"}