{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VXRAOCJ6H3Q7TUJTCT2H3WEJXH","short_pith_number":"pith:VXRAOCJ6","canonical_record":{"source":{"id":"2504.17087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T20:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"8830b7f5f5a64cf73696bffd04ab0d6d66000cfafdb344b7e1c3e07c4ace38ed","abstract_canon_sha256":"54b9676a0756595d71995e43fdb8bb7f9658178cec6563e7f67afd34a108faff"},"schema_version":"1.0"},"canonical_sha256":"ade207093e3ee1f9d13314f47dd889b9e5721aac0b0a288184dd5d137e6cfc30","source":{"kind":"arxiv","id":"2504.17087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17087","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17087v1","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17087","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"VXRAOCJ6H3Q7","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"VXRAOCJ6H3Q7TUJT","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"VXRAOCJ6","created_at":"2026-07-05T10:53:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VXRAOCJ6H3Q7TUJTCT2H3WEJXH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T20:32:12Z","cross_cats_sorted":[],"title_canon_sha256":"8830b7f5f5a64cf73696bffd04ab0d6d66000cfafdb344b7e1c3e07c4ace38ed","abstract_canon_sha256":"54b9676a0756595d71995e43fdb8bb7f9658178cec6563e7f67afd34a108faff"},"schema_version":"1.0"},"canonical_sha256":"ade207093e3ee1f9d13314f47dd889b9e5721aac0b0a288184dd5d137e6cfc30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:22.057205Z","signature_b64":"ND9wiNsibiUYQVWnr8TOyjHHjT+7rZJR5mAd5J3TWq8nDrwRaQDKEOTrw7Ac21ph7R+2Bklf0uwrugE0s1lFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ade207093e3ee1f9d13314f47dd889b9e5721aac0b0a288184dd5d137e6cfc30","last_reissued_at":"2026-07-05T10:53:22.056697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:22.056697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17087","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":"2026-07-05T10:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OHUQbupkFsUk8H0Cep9rUPz7Ec5ZSi35iCThORl3h9BL38NvDkb3z8DKeqAVSaJwo7VEljWCN9Je3/hxW2Q9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:28.765059Z"},"content_sha256":"f26a1e03036f4f7e431f9513a4de88efb4ed910ef023b913a6f97f3df5ead615","schema_version":"1.0","event_id":"sha256:f26a1e03036f4f7e431f9513a4de88efb4ed910ef023b913a6f97f3df5ead615"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VXRAOCJ6H3Q7TUJTCT2H3WEJXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benoit Boulet, Chongren Sun, Di Wu, Jama Hussein Mohamud, Yuran Li","submitted_at":"2025-04-23T20:32:12Z","abstract_excerpt":"Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance evaluation offers a more efficient alternative. However, most studies focus mainly on aligning LLMs' judgments with human preferences, overlooking the existence of biases and mistakes in human judgment. Furthermore, how to select suitable LLM judgments given multiple potential LLM responses remains underexplored. To address these two aforementioned issues, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17087","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/2504.17087/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":"2026-07-05T10:53:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+qjC8eC+4EXLg3e2U7MdwyOWeHFZNiCCwUOe4E0pS59g/sU5dAitF5EaQR73ahYYshD+xXoyH40a6TaiXxACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:00:28.765596Z"},"content_sha256":"5922f8ca69dea0d532dd41b50a866c5412021c1e8a5f0f279f8181db33da81a5","schema_version":"1.0","event_id":"sha256:5922f8ca69dea0d532dd41b50a866c5412021c1e8a5f0f279f8181db33da81a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/bundle.json","state_url":"https://pith.science/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/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":"2026-08-06T06:00:28Z","links":{"resolver":"https://pith.science/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH","bundle":"https://pith.science/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/bundle.json","state":"https://pith.science/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXRAOCJ6H3Q7TUJTCT2H3WEJXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VXRAOCJ6H3Q7TUJTCT2H3WEJXH","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":"54b9676a0756595d71995e43fdb8bb7f9658178cec6563e7f67afd34a108faff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T20:32:12Z","title_canon_sha256":"8830b7f5f5a64cf73696bffd04ab0d6d66000cfafdb344b7e1c3e07c4ace38ed"},"schema_version":"1.0","source":{"id":"2504.17087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17087","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17087v1","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17087","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_12","alias_value":"VXRAOCJ6H3Q7","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_16","alias_value":"VXRAOCJ6H3Q7TUJT","created_at":"2026-07-05T10:53:22Z"},{"alias_kind":"pith_short_8","alias_value":"VXRAOCJ6","created_at":"2026-07-05T10:53:22Z"}],"graph_snapshots":[{"event_id":"sha256:5922f8ca69dea0d532dd41b50a866c5412021c1e8a5f0f279f8181db33da81a5","target":"graph","created_at":"2026-07-05T10:53:22Z","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/2504.17087/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are being widely applied across various fields, but as tasks become more complex, evaluating their responses is increasingly challenging. Compared to human evaluators, the use of LLMs to support performance evaluation offers a more efficient alternative. However, most studies focus mainly on aligning LLMs' judgments with human preferences, overlooking the existence of biases and mistakes in human judgment. Furthermore, how to select suitable LLM judgments given multiple potential LLM responses remains underexplored. To address these two aforementioned issues, we pr","authors_text":"Benoit Boulet, Chongren Sun, Di Wu, Jama Hussein Mohamud, Yuran Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T20:32:12Z","title":"Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17087","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:f26a1e03036f4f7e431f9513a4de88efb4ed910ef023b913a6f97f3df5ead615","target":"record","created_at":"2026-07-05T10:53:22Z","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":"54b9676a0756595d71995e43fdb8bb7f9658178cec6563e7f67afd34a108faff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T20:32:12Z","title_canon_sha256":"8830b7f5f5a64cf73696bffd04ab0d6d66000cfafdb344b7e1c3e07c4ace38ed"},"schema_version":"1.0","source":{"id":"2504.17087","kind":"arxiv","version":1}},"canonical_sha256":"ade207093e3ee1f9d13314f47dd889b9e5721aac0b0a288184dd5d137e6cfc30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ade207093e3ee1f9d13314f47dd889b9e5721aac0b0a288184dd5d137e6cfc30","first_computed_at":"2026-07-05T10:53:22.056697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:22.056697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ND9wiNsibiUYQVWnr8TOyjHHjT+7rZJR5mAd5J3TWq8nDrwRaQDKEOTrw7Ac21ph7R+2Bklf0uwrugE0s1lFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:22.057205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f26a1e03036f4f7e431f9513a4de88efb4ed910ef023b913a6f97f3df5ead615","sha256:5922f8ca69dea0d532dd41b50a866c5412021c1e8a5f0f279f8181db33da81a5"],"state_sha256":"dcb7e23f62da51c54907a51e315e515261ccb59a2a1a5cb682569d2635ebcc4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTrE6kEAgF6YE/vlWAxln4MKoz0X1Rh8N6tWQ0TdbU8pVMiGoJdhRmyOkoAH6JrlMRjNWb3sVlYaM9GvdcClBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:00:28.770683Z","bundle_sha256":"dba5366ec19f96fdf76b504ac8d9d20c0209417a7b17b6c76fab6f45f5c44743"}}