{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4VZI4W62EECBYMC7VTQ76XJJ5S","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":"73b64d0e578cf2c3be1c28493476f1b511f18065ae31b44d4c3cdf61323793ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T01:42:25Z","title_canon_sha256":"7b34d3e5a3acb4f551535ba257f02aa2ea3a0f97417db6875282900021efaa8f"},"schema_version":"1.0","source":{"id":"2508.02994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02994","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02994v1","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02994","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"4VZI4W62EECB","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"4VZI4W62EECBYMC7","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"4VZI4W62","created_at":"2026-07-05T11:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:202262d5f250de34d012507c0224ea565f094cefd37e538d0e09c4c1ec99bcc3","target":"graph","created_at":"2026-07-05T11:48:34Z","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/2508.02994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models (LLMs) grow in capability and autonomy, evaluating their outputs-especially in open-ended and complex tasks-has become a critical bottleneck. A new paradigm is emerging: using AI agents as the evaluators themselves. This \"agent-as-a-judge\" approach leverages the reasoning and perspective-taking abilities of LLMs to assess the quality and safety of other models, promising calable and nuanced alternatives to human evaluation. In this review, we define the agent-as-a-judge concept, trace its evolution from single-model judges to dynamic multi-agent debate frameworks, and ","authors_text":"Fangyi Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T01:42:25Z","title":"When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02994","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:b194b171f77ed995cc42b981cfbf27f9b13e261363ce118f1ff29a9601074dd6","target":"record","created_at":"2026-07-05T11:48:34Z","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":"73b64d0e578cf2c3be1c28493476f1b511f18065ae31b44d4c3cdf61323793ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-05T01:42:25Z","title_canon_sha256":"7b34d3e5a3acb4f551535ba257f02aa2ea3a0f97417db6875282900021efaa8f"},"schema_version":"1.0","source":{"id":"2508.02994","kind":"arxiv","version":1}},"canonical_sha256":"e5728e5bda21041c305face1ff5d29eca7cc3d89a46cfd2886ddea772ec8ee2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5728e5bda21041c305face1ff5d29eca7cc3d89a46cfd2886ddea772ec8ee2f","first_computed_at":"2026-07-05T11:48:34.438053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:34.438053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2+DcBfRPW5We2L6RD6klLKri5aWrZ+yxvCpgDDSmt+ZisqfaSnVOKP4N2Yv8y+cTYAzR/5XfnkgKLIUnVNS1AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:34.438548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b194b171f77ed995cc42b981cfbf27f9b13e261363ce118f1ff29a9601074dd6","sha256:202262d5f250de34d012507c0224ea565f094cefd37e538d0e09c4c1ec99bcc3"],"state_sha256":"0bdf1db925e3f5f0c18523117d98e3662bf40c6077c3d8da4b149c1889e363e7"}