{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:66R6IVCCSKXHQD3DCPQPRJOGZB","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":"02e9031e7176471ccfea5f3edb489c5f4d8c379e7cb60ba66fa28bc445ddd23e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T02:21:59Z","title_canon_sha256":"19d2ab198c68c19253ce68f2e4781be1f8a7b92a927f5de9d5da6bf503773c75"},"schema_version":"1.0","source":{"id":"2501.18099","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18099","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18099v2","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18099","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_12","alias_value":"66R6IVCCSKXH","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_16","alias_value":"66R6IVCCSKXHQD3D","created_at":"2026-07-05T11:33:19Z"},{"alias_kind":"pith_short_8","alias_value":"66R6IVCC","created_at":"2026-07-05T11:33:19Z"}],"graph_snapshots":[{"event_id":"sha256:b0b645a192c1bc39714af8cd0ef51205950bc9b9c1065f0e97acb2b9d464d83a","target":"graph","created_at":"2026-07-05T11:33:19Z","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/2501.18099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-a-Judge models generate chain-of-thought (CoT) sequences intended to capture the step-bystep reasoning process that underlies the final evaluation of a response. However, due to the lack of human annotated CoTs for evaluation, the required components and structure of effective reasoning traces remain understudied. Consequently, previous approaches often (1) constrain reasoning traces to hand-designed components, such as a list of criteria, reference answers, or verification questions and (2) structure them such that planning is intertwined with the reasoning for evaluation. In this work","authors_text":"Jason Weston, Marjan Ghazvininejad, Swarnadeep Saha, Tianlu Wang, Xian Li","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T02:21:59Z","title":"Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18099","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:c52094eb07763aa524991847e5b0bc2ee94ee3d9c6f1daba5e2890cf2039de77","target":"record","created_at":"2026-07-05T11:33:19Z","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":"02e9031e7176471ccfea5f3edb489c5f4d8c379e7cb60ba66fa28bc445ddd23e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-30T02:21:59Z","title_canon_sha256":"19d2ab198c68c19253ce68f2e4781be1f8a7b92a927f5de9d5da6bf503773c75"},"schema_version":"1.0","source":{"id":"2501.18099","kind":"arxiv","version":2}},"canonical_sha256":"f7a3e4544292ae780f6313e0f8a5c6c86aea49dd4af56c1d2fefd53c1de51983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7a3e4544292ae780f6313e0f8a5c6c86aea49dd4af56c1d2fefd53c1de51983","first_computed_at":"2026-07-05T11:33:19.574722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:19.574722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lNyFmKNu3Ax/BVTv4ikxJfI1JcVWIh+FOXd02sDbvT74PmT/i5x4Zb20LBs425lBjmxi/fZeqDfn+Qvf9zEFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:19.575147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18099","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c52094eb07763aa524991847e5b0bc2ee94ee3d9c6f1daba5e2890cf2039de77","sha256:b0b645a192c1bc39714af8cd0ef51205950bc9b9c1065f0e97acb2b9d464d83a"],"state_sha256":"a93ca3ec73e26ad32d923d6128b91c1a6dfc8e7651c2a2a4d27d51ae072daa5a"}