{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C7CFWE2BWWNSU43L5NQAS3ZCWO","short_pith_number":"pith:C7CFWE2B","canonical_record":{"source":{"id":"2412.00543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"202f60efdc0c4b9bb1e7be5e74712a18be99a10c01b3c77005392b8bd8cef2f6","abstract_canon_sha256":"3e632266776fedee082d5213c7c392f0152f26e201de90c22ac64a7453088ed8"},"schema_version":"1.0"},"canonical_sha256":"17c45b1341b59b2a736beb60096f22b3a6f9b1df38fb6e6b30d2a6cf1390bc03","source":{"kind":"arxiv","id":"2412.00543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00543","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00543v1","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00543","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"C7CFWE2BWWNS","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"C7CFWE2BWWNSU43L","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"C7CFWE2B","created_at":"2026-07-05T09:42:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C7CFWE2BWWNSU43L5NQAS3ZCWO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"202f60efdc0c4b9bb1e7be5e74712a18be99a10c01b3c77005392b8bd8cef2f6","abstract_canon_sha256":"3e632266776fedee082d5213c7c392f0152f26e201de90c22ac64a7453088ed8"},"schema_version":"1.0"},"canonical_sha256":"17c45b1341b59b2a736beb60096f22b3a6f9b1df38fb6e6b30d2a6cf1390bc03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:43.409430Z","signature_b64":"BgI4vAXQaC2h6X34aHC2AvH7hXBbcyb2XnwFfxXNehHKrXaHJ1PR9JGvkYslYjps8CpnWJHi5Ls8d6+cp+IGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17c45b1341b59b2a736beb60096f22b3a6f9b1df38fb6e6b30d2a6cf1390bc03","last_reissued_at":"2026-07-05T09:42:43.408925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:43.408925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00543","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":"2026-07-05T09:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2brn6QcVayjFGNT+B7KpfSAovw3MmkaQ41nrHKjGwGvkkXjHIzEGjsOFYeC8V6DR5dPWc7qyQHKOE69qeHqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:49.729608Z"},"content_sha256":"bd2b54696547c86912a190d4c75cff92e862a95ebc1097ac127ea34104e1f012","schema_version":"1.0","event_id":"sha256:bd2b54696547c86912a190d4c75cff92e862a95ebc1097ac127ea34104e1f012"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C7CFWE2BWWNSU43L5NQAS3ZCWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Consistency of LLM Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James Thorne, Jiwoo Hong, Noah Lee","submitted_at":"2024-11-30T17:29:08Z","abstract_excerpt":"Large language models (LLMs) have shown potential as general evaluators along with the evident benefits of speed and cost. While their correlation against human annotators has been widely studied, consistency as evaluators is still understudied, raising concerns about the reliability of LLM evaluators. In this paper, we conduct extensive studies on the two aspects of consistency in LLM evaluations, Self-Consistency (SC) and Inter-scale Consistency (IC), on different scoring scales and criterion granularity with open-source and proprietary models. Our comprehensive analysis demonstrates that st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00543","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/2412.00543/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":"2026-07-05T09:42:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DewwfgZJ+dE/hD0U/wyrkR3V0LdeMJEbDTCkZd2DJ7/E6PhOTqHbLu6IcuowNGi7iNW5/e42AEBGmTw8aSkGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:18:49.730139Z"},"content_sha256":"fa1e1f2527ca3fcb9286dccb92cc0b576fe652a65e7a3b2a6f73a9d52bc061af","schema_version":"1.0","event_id":"sha256:fa1e1f2527ca3fcb9286dccb92cc0b576fe652a65e7a3b2a6f73a9d52bc061af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/bundle.json","state_url":"https://pith.science/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/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":"2026-08-06T06:18:49Z","links":{"resolver":"https://pith.science/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO","bundle":"https://pith.science/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/bundle.json","state":"https://pith.science/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C7CFWE2BWWNSU43L5NQAS3ZCWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C7CFWE2BWWNSU43L5NQAS3ZCWO","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":"3e632266776fedee082d5213c7c392f0152f26e201de90c22ac64a7453088ed8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:29:08Z","title_canon_sha256":"202f60efdc0c4b9bb1e7be5e74712a18be99a10c01b3c77005392b8bd8cef2f6"},"schema_version":"1.0","source":{"id":"2412.00543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00543","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00543v1","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00543","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"C7CFWE2BWWNS","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"C7CFWE2BWWNSU43L","created_at":"2026-07-05T09:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"C7CFWE2B","created_at":"2026-07-05T09:42:43Z"}],"graph_snapshots":[{"event_id":"sha256:fa1e1f2527ca3fcb9286dccb92cc0b576fe652a65e7a3b2a6f73a9d52bc061af","target":"graph","created_at":"2026-07-05T09:42:43Z","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/2412.00543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown potential as general evaluators along with the evident benefits of speed and cost. While their correlation against human annotators has been widely studied, consistency as evaluators is still understudied, raising concerns about the reliability of LLM evaluators. In this paper, we conduct extensive studies on the two aspects of consistency in LLM evaluations, Self-Consistency (SC) and Inter-scale Consistency (IC), on different scoring scales and criterion granularity with open-source and proprietary models. Our comprehensive analysis demonstrates that st","authors_text":"James Thorne, Jiwoo Hong, Noah Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:29:08Z","title":"Evaluating the Consistency of LLM Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00543","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:bd2b54696547c86912a190d4c75cff92e862a95ebc1097ac127ea34104e1f012","target":"record","created_at":"2026-07-05T09:42:43Z","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":"3e632266776fedee082d5213c7c392f0152f26e201de90c22ac64a7453088ed8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-30T17:29:08Z","title_canon_sha256":"202f60efdc0c4b9bb1e7be5e74712a18be99a10c01b3c77005392b8bd8cef2f6"},"schema_version":"1.0","source":{"id":"2412.00543","kind":"arxiv","version":1}},"canonical_sha256":"17c45b1341b59b2a736beb60096f22b3a6f9b1df38fb6e6b30d2a6cf1390bc03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17c45b1341b59b2a736beb60096f22b3a6f9b1df38fb6e6b30d2a6cf1390bc03","first_computed_at":"2026-07-05T09:42:43.408925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:43.408925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BgI4vAXQaC2h6X34aHC2AvH7hXBbcyb2XnwFfxXNehHKrXaHJ1PR9JGvkYslYjps8CpnWJHi5Ls8d6+cp+IGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:43.409430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd2b54696547c86912a190d4c75cff92e862a95ebc1097ac127ea34104e1f012","sha256:fa1e1f2527ca3fcb9286dccb92cc0b576fe652a65e7a3b2a6f73a9d52bc061af"],"state_sha256":"10a2be29e67f3c2bafbc32116900c4b2ef65f99408a6e88676544d3d2e6963dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eJ6DLRavI5hReLdhzOPPX0h/uFrrRfDePIuLNV2Rvm3+T8bmi8KCqIEl8W9kvLa6ILP4FwCZo4GLzhGplkeZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:18:49.736527Z","bundle_sha256":"3dd6439632de5b94459b6ed9b9f045485869990f50b3fbcaece90a0d2fcbba49"}}