{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y6UBJ5LU4E7FSOFYWOFVWVYBHP","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":"1cbbe84baf5c8179c848904dafbb272802683d704f77d44cf9bbd35074658776","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T21:19:08Z","title_canon_sha256":"75804ed9cfc54f7b9c3b618466025a7e4d05773ded6f5c618fe06a44c3404c1b"},"schema_version":"1.0","source":{"id":"2603.17145","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.17145","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.17145v2","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17145","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_12","alias_value":"Y6UBJ5LU4E7F","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_16","alias_value":"Y6UBJ5LU4E7FSOFY","created_at":"2026-06-01T01:02:37Z"},{"alias_kind":"pith_short_8","alias_value":"Y6UBJ5LU","created_at":"2026-06-01T01:02:37Z"}],"graph_snapshots":[{"event_id":"sha256:71f89c864ac9321474fe9f0d22b79b7689f174d7e77e6fb143a13397c9c2c745","target":"graph","created_at":"2026-06-01T01:02:37Z","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/2603.17145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the ground truth is 5. Conversely, existing regression-aware approaches are often confined to Supervised Fine-Tuning (SFT), limiting their ability to explore op","authors_text":"Michal Lukasik, Mingyuan Zhou, Oscar Leong, Tianyu Chen, Yasi Zhang, Ying Nian Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T21:19:08Z","title":"REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17145","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":"sha256:486bb6a1227ee17dac2bd66a50cb3d1ccce2a078c5bb6cce205dd486c920525f","target":"record","created_at":"2026-06-01T01:02:37Z","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":"1cbbe84baf5c8179c848904dafbb272802683d704f77d44cf9bbd35074658776","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T21:19:08Z","title_canon_sha256":"75804ed9cfc54f7b9c3b618466025a7e4d05773ded6f5c618fe06a44c3404c1b"},"schema_version":"1.0","source":{"id":"2603.17145","kind":"arxiv","version":2}},"canonical_sha256":"c7a814f574e13e5938b8b38b5b57013bebfb9c5981366580a728ff72c04a3a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7a814f574e13e5938b8b38b5b57013bebfb9c5981366580a728ff72c04a3a56","first_computed_at":"2026-06-01T01:02:37.330940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:37.330940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JT+lrrNAP7GsDUZnKsqDzfs1UZ4KXTJY1/5IvMvpbCHs18MsM7glwC/bUXNVy5RGe8kx1sRAsJLEvpIVOB2FDw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:37.332101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.17145","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486bb6a1227ee17dac2bd66a50cb3d1ccce2a078c5bb6cce205dd486c920525f","sha256:71f89c864ac9321474fe9f0d22b79b7689f174d7e77e6fb143a13397c9c2c745"],"state_sha256":"d75dc8ace2f28972351c1160d33ddcced530c7191cf8fdc90c945ddf6ce6e42d"}