{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PA2R6Y632REB7ZITOJDTQFA2Q","short_pith_number":"pith:6PA2R6Y6","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"},"canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","source":{"kind":"arxiv","id":"2504.02867","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02867","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02867v1","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02867","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"6PA2R6Y632RE","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"6PA2R6Y632REB7ZI","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"6PA2R6Y6","created_at":"2026-07-05T10:44:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PA2R6Y632REB7ZITOJDTQFA2Q","target":"record","payload":{"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"},"canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","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"},"source_kind":"arxiv","source_id":"2504.02867","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Sy7Pffv6lX7pGtub1GqyKHV1/sRGn3DT3x8AcDs2EgNabsY3HsqVdkwms2TCtaiAe7dD0H7WL0tB6HN5uKxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:54:14.305297Z"},"content_sha256":"dd909afd03210feec816c7c8dc2aa5feee0cbaacf06b7f9e529cdea535e246dc","schema_version":"1.0","event_id":"sha256:dd909afd03210feec816c7c8dc2aa5feee0cbaacf06b7f9e529cdea535e246dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PA2R6Y632REB7ZITOJDTQFA2Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svy1lHiPKpMPBW7GPmAQ5Y6yCofThsUYlzzYNeytEqrMdOq1PlzQ+68l4ES8Ylwwaic1ppcr+B2P+pVoF9FKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:54:14.306192Z"},"content_sha256":"86bd93bb5a683da2d767945d07901768cb6c809eeaa51773298840524ce53994","schema_version":"1.0","event_id":"sha256:86bd93bb5a683da2d767945d07901768cb6c809eeaa51773298840524ce53994"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/bundle.json","state_url":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:54:14Z","links":{"resolver":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q","bundle":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/bundle.json","state":"https://pith.science/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PA2R6Y632REB7ZITOJDTQFA2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PA2R6Y632REB7ZITOJDTQFA2Q","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":"14bb61ffed067dfa7e517d1d16fffeb38ca8038f89bf044b01ee368f4c427ca8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T09:36:56Z","title_canon_sha256":"daf64f4db6651bf689428b194bc2012e772fd350dbcde8cf9d5f2a70d0faaaef"},"schema_version":"1.0","source":{"id":"2504.02867","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02867","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02867v1","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02867","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"6PA2R6Y632RE","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"6PA2R6Y632REB7ZI","created_at":"2026-07-05T10:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"6PA2R6Y6","created_at":"2026-07-05T10:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:86bd93bb5a683da2d767945d07901768cb6c809eeaa51773298840524ce53994","target":"graph","created_at":"2026-07-05T10:44:04Z","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/2504.02867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Eoin Thomas, Hongliu Cao, Ilias Driouich, Robin Singh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T09:36:56Z","title":"Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02867","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:dd909afd03210feec816c7c8dc2aa5feee0cbaacf06b7f9e529cdea535e246dc","target":"record","created_at":"2026-07-05T10:44:04Z","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":"14bb61ffed067dfa7e517d1d16fffeb38ca8038f89bf044b01ee368f4c427ca8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-01T09:36:56Z","title_canon_sha256":"daf64f4db6651bf689428b194bc2012e772fd350dbcde8cf9d5f2a70d0faaaef"},"schema_version":"1.0","source":{"id":"2504.02867","kind":"arxiv","version":1}},"canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3c1a8fb1edea240ff289b9239c0a0d40f7ca7a584491bff47c378adeec83575","first_computed_at":"2026-07-05T10:44:04.162074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:04.162074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zrpaYEX8Uc88udt3Zm+JFb359QDWEJoz1FjsXTETD3cOTPs3lWSftbSI9FN/7OBqjqf++X022rL957AL2r2jBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:04.162595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02867","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd909afd03210feec816c7c8dc2aa5feee0cbaacf06b7f9e529cdea535e246dc","sha256:86bd93bb5a683da2d767945d07901768cb6c809eeaa51773298840524ce53994"],"state_sha256":"9bbd5236271852542e94e30600c9b7ff1c6665a75b0b705d6079bee53ee023e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+pTY3SJ5J/zyGKtKsu6LkzdoQFIkd+iXhLAJZR9H1fvvt46YuIlMLVLM/LnfGumtjxx0+FxZHyXVSH4H7+LAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:54:14.312097Z","bundle_sha256":"95432f4b02ab98b67c2984f5cfb6464dfb1c454eb6e12efe140211fb2df4b290"}}