{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O6UXE24BNJDXBSB5Y4BRRT5CKR","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":"520597991c36704db0d57674d2c308195516721671833edb38b32e51a726d6fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T17:57:02Z","title_canon_sha256":"a8e8751641f103e15e27ac2210a50eb37624d02e2216c3ee6d047288023a2b22"},"schema_version":"1.0","source":{"id":"2410.10934","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10934","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10934v2","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10934","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"O6UXE24BNJDX","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"O6UXE24BNJDXBSB5","created_at":"2026-07-05T09:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"O6UXE24B","created_at":"2026-07-05T09:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:b3fd8a551f8bfce568d2c4e58aa39df5d1c15c9b353a1cc52e1beabc887ff3de","target":"graph","created_at":"2026-07-05T09:21:50Z","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/2410.10934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes -- ignoring the step-by-step nature of agentic systems, or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We apply the Agent-as-a-Judge to the task of code generation. To overcome issues with exi","authors_text":"Changsheng Zhao, Dmitrii Khizbullin, Dylan Ashley, Ernie Chang, J\\\"urgen Schmidhuber, Mingchen Zhuge, Raghuraman Krishnamoorthi, Vikas Chandra, Wenyi Wang, Yangyang Shi, Yuandong Tian, Yunyang Xiong, Zechun Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T17:57:02Z","title":"Agent-as-a-Judge: Evaluate Agents with Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10934","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":"sha256:930583bf6f90da9abec2e780389b3b841993e4ec193285fe882a0e9d09683c90","target":"record","created_at":"2026-07-05T09:21:50Z","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":"520597991c36704db0d57674d2c308195516721671833edb38b32e51a726d6fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-14T17:57:02Z","title_canon_sha256":"a8e8751641f103e15e27ac2210a50eb37624d02e2216c3ee6d047288023a2b22"},"schema_version":"1.0","source":{"id":"2410.10934","kind":"arxiv","version":2}},"canonical_sha256":"77a9726b816a4770c83dc70318cfa2544b577c947dbb540df91294ab499bd3ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77a9726b816a4770c83dc70318cfa2544b577c947dbb540df91294ab499bd3ec","first_computed_at":"2026-07-05T09:21:50.070955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:50.070955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5VbnIvhVfmQmML37KMSQbZZx4XPYaTHpzYoJh4pDyvJxgMqLV0P+bPp5g0HUuyngKhHr7A04+6HVPovKtNq7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:50.071437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10934","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:930583bf6f90da9abec2e780389b3b841993e4ec193285fe882a0e9d09683c90","sha256:b3fd8a551f8bfce568d2c4e58aa39df5d1c15c9b353a1cc52e1beabc887ff3de"],"state_sha256":"7aaf4b63eb31a0264316cdcd20b4dfcaf9d3faa19708a14b6f073daf9f87d343"}