{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J6GC7RSIE6HE2TZBMS2P2P4SFS","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":"e88ff67d8915ac6945e5d611e3ec98688deaa065597fc3895e9067984934399b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-08T11:11:22Z","title_canon_sha256":"fa8e86fb7a9b40363b97d731313f2830fba428d521d8a31584e067e971e38f03"},"schema_version":"1.0","source":{"id":"2508.06225","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06225","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06225v3","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06225","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_12","alias_value":"J6GC7RSIE6HE","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_16","alias_value":"J6GC7RSIE6HE2TZB","created_at":"2026-07-05T11:55:21Z"},{"alias_kind":"pith_short_8","alias_value":"J6GC7RSI","created_at":"2026-07-05T11:55:21Z"}],"graph_snapshots":[{"event_id":"sha256:80b610f8441e4323d65c27c4c8de43360ab552a2a17fc6b7dd4275cbb2003242","target":"graph","created_at":"2026-07-05T11:55:21Z","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/2508.06225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accuracy, overlooking the necessity of well-calibrated confidence, which is vital for adaptive and reliable evaluation pipelines. In this work, we advocate a shift from accuracy-centric evaluation to confidence-driven, risk-aware LLM-as-a-Judge systems, emphasizing the necessity of well-calibrated confidence for trustworthy and adaptive evaluation. We systematically identify the Overconfidence Phenomen","authors_text":"Haozhe Xu, Houfeng Wang, Lizi Liao, Richeng Xuan, Xi Yang, Yanzhe Chen, Zailong Tian, Zhuoheng Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-08T11:11:22Z","title":"Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06225","kind":"arxiv","version":3},"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":"sha256:80a35f937c7ef7c5509a21e10f7512752d2a0c4f1bb566f8472799436b201be5","target":"record","created_at":"2026-07-05T11:55:21Z","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":"e88ff67d8915ac6945e5d611e3ec98688deaa065597fc3895e9067984934399b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-08T11:11:22Z","title_canon_sha256":"fa8e86fb7a9b40363b97d731313f2830fba428d521d8a31584e067e971e38f03"},"schema_version":"1.0","source":{"id":"2508.06225","kind":"arxiv","version":3}},"canonical_sha256":"4f8c2fc648278e4d4f2164b4fd3f922c9abb2d39e0f9d5d2dd5aa431f09027fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f8c2fc648278e4d4f2164b4fd3f922c9abb2d39e0f9d5d2dd5aa431f09027fc","first_computed_at":"2026-07-05T11:55:21.147638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:21.147638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7pvks0WXRidg7FpqVcDYnNlfGcgd8UqTlkGEwZTrMlKNLk31dB7HwbV3nhjj3h0kws1H3/KhGgWc3CTrxay6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:21.148123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06225","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a35f937c7ef7c5509a21e10f7512752d2a0c4f1bb566f8472799436b201be5","sha256:80b610f8441e4323d65c27c4c8de43360ab552a2a17fc6b7dd4275cbb2003242"],"state_sha256":"7b17d395dc838cf01b8ecc87c1d5222b7966c5acafb3ea9a64de63af86b14598"}