{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6PA2R6Y632REB7ZITOJDTQFA2Q","short_pith_number":"pith:6PA2R6Y6","schema_version":"1.0","canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","source":{"kind":"arxiv","id":"2504.02867","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eoin Thomas, Hongliu Cao, Ilias Driouich, Robin Singh","submitted_at":"2025-04-01T09:36:56Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive performance across diverse domains, yet they still encounter challenges such as insufficient domain-specific knowledge, biases, and hallucinations. This underscores the need for robust evaluation methodologies to accurately assess LLM-based applications. Traditional evaluation methods, which rely on word overlap or text embeddings, are inadequate for capturing the nuanced semantic information necessary to evaluate dynamic, open-ended text generation. Recent research has explored leveraging LLMs to mimic human reasoning and decision-maki"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.02867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T09:36:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"daf64f4db6651bf689428b194bc2012e772fd350dbcde8cf9d5f2a70d0faaaef","abstract_canon_sha256":"14bb61ffed067dfa7e517d1d16fffeb38ca8038f89bf044b01ee368f4c427ca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:04.162595Z","signature_b64":"zrpaYEX8Uc88udt3Zm+JFb359QDWEJoz1FjsXTETD3cOTPs3lWSftbSI9FN/7OBqjqf++X022rL957AL2r2jBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","last_reissued_at":"2026-07-05T10:44:04.162074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:04.162074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eoin Thomas, Hongliu Cao, Ilias Driouich, Robin Singh","submitted_at":"2025-04-01T09:36:56Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive performance across diverse domains, yet they still encounter challenges such as insufficient domain-specific knowledge, biases, and hallucinations. This underscores the need for robust evaluation methodologies to accurately assess LLM-based applications. Traditional evaluation methods, which rely on word overlap or text embeddings, are inadequate for capturing the nuanced semantic information necessary to evaluate dynamic, open-ended text generation. Recent research has explored leveraging LLMs to mimic human reasoning and decision-maki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02867","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.02867/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.02867","created_at":"2026-07-05T10:44:04.162137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02867v1","created_at":"2026-07-05T10:44:04.162137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02867","created_at":"2026-07-05T10:44:04.162137+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PA2R6Y632RE","created_at":"2026-07-05T10:44:04.162137+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PA2R6Y632REB7ZI","created_at":"2026-07-05T10:44:04.162137+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PA2R6Y6","created_at":"2026-07-05T10:44:04.162137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18929","citing_title":"Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent framework","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q","json":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q.json","graph_json":"https://pith.science/api/pith-number/6PA2R6Y632REB7ZITOJDTQFA2Q/graph.json","events_json":"https://pith.science/api/pith-number/6PA2R6Y632REB7ZITOJDTQFA2Q/events.json","paper":"https://pith.science/paper/6PA2R6Y6"},"agent_actions":{"view_html":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q","download_json":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q.json","view_paper":"https://pith.science/paper/6PA2R6Y6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02867&json=true","fetch_graph":"https://pith.science/api/pith-number/6PA2R6Y632REB7ZITOJDTQFA2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/6PA2R6Y632REB7ZITOJDTQFA2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/action/storage_attestation","attest_author":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/action/author_attestation","sign_citation":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/action/citation_signature","submit_replication":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/action/replication_record"}},"created_at":"2026-07-05T10:44:04.162137+00:00","updated_at":"2026-07-05T10:44:04.162137+00:00"}