{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZE2RC2GNXWDNNO6MA2A6EJ2FYZ","short_pith_number":"pith:ZE2RC2GN","canonical_record":{"source":{"id":"2402.14860","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:49:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aacd57dacd37ce27e1ad384a92d8f8a79bc7327044144d38d2c3f5a38eabaf06","abstract_canon_sha256":"482571bf4f07257ccc2d6fb417271a5bbec970cac80ea6d46c95df1f0606d2b6"},"schema_version":"1.0"},"canonical_sha256":"c9351168cdbd86d6bbcc0681e22745c64db66a65ad32cd653f8041054719a4f3","source":{"kind":"arxiv","id":"2402.14860","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14860","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14860v4","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14860","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZE2RC2GNXWDN","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZE2RC2GNXWDNNO6M","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZE2RC2GN","created_at":"2026-07-05T08:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZE2RC2GNXWDNNO6MA2A6EJ2FYZ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14860","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:49:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aacd57dacd37ce27e1ad384a92d8f8a79bc7327044144d38d2c3f5a38eabaf06","abstract_canon_sha256":"482571bf4f07257ccc2d6fb417271a5bbec970cac80ea6d46c95df1f0606d2b6"},"schema_version":"1.0"},"canonical_sha256":"c9351168cdbd86d6bbcc0681e22745c64db66a65ad32cd653f8041054719a4f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.890491Z","signature_b64":"ll7vRQYNAPon0M+8VnWjURvbiBlEUHv9usRpZDEQ/W0KM57lqIlbVI27BOrVHBNpb+FlLIj8iNQE/9lk59qcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9351168cdbd86d6bbcc0681e22745c64db66a65ad32cd653f8041054719a4f3","last_reissued_at":"2026-07-05T08:29:22.890000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.890000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14860","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSDXstBtTjCe77/w/KQtvGWiFyWDCGR2xgb61L0YIayOrAR3CkbnyXr/wdmnES8EYEyv8E2l5alPTn45IbjGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:04.764495Z"},"content_sha256":"2ef67408ae6e84b674d7a847deedcb6a1f2edbb370797e06d68a942e68c64857","schema_version":"1.0","event_id":"sha256:2ef67408ae6e84b674d7a847deedcb6a1f2edbb370797e06d68a942e68c64857"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZE2RC2GNXWDNNO6MA2A6EJ2FYZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ranking Large Language Models without Ground Truth","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amit Dhurandhar, Elizabeth Daly, Karthikeyan Natesan Ramamurthy, Moninder Singh, Rahul Nair","submitted_at":"2024-02-21T00:49:43Z","abstract_excerpt":"Evaluation and ranking of large language models (LLMs) has become an important problem with the proliferation of these models and their impact. Evaluation methods either require human responses which are expensive to acquire or use pairs of LLMs to evaluate each other which can be unreliable. In this paper, we provide a novel perspective where, given a dataset of prompts (viz. questions, instructions, etc.) and a set of LLMs, we rank them without access to any ground truth or reference responses. Inspired by real life where both an expert and a knowledgeable person can identify a novice our ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14860","kind":"arxiv","version":4},"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/2402.14860/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":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2GmImtrgUZMfWedygkxavv/SH9gHRyPDh4gQNVfFiC+ANM2weQiTVYRlK46/+1vmeUYHObwwrjuG5Hno9dgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:04.765938Z"},"content_sha256":"df94b6838c3696bc4b8501792f6189e9c94f207716ea91220d12fb5c6fa44a37","schema_version":"1.0","event_id":"sha256:df94b6838c3696bc4b8501792f6189e9c94f207716ea91220d12fb5c6fa44a37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/bundle.json","state_url":"https://pith.science/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/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":"2026-08-06T03:32:04Z","links":{"resolver":"https://pith.science/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ","bundle":"https://pith.science/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/bundle.json","state":"https://pith.science/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZE2RC2GNXWDNNO6MA2A6EJ2FYZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZE2RC2GNXWDNNO6MA2A6EJ2FYZ","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":"482571bf4f07257ccc2d6fb417271a5bbec970cac80ea6d46c95df1f0606d2b6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:49:43Z","title_canon_sha256":"aacd57dacd37ce27e1ad384a92d8f8a79bc7327044144d38d2c3f5a38eabaf06"},"schema_version":"1.0","source":{"id":"2402.14860","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14860","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14860v4","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14860","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZE2RC2GNXWDN","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZE2RC2GNXWDNNO6M","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZE2RC2GN","created_at":"2026-07-05T08:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:df94b6838c3696bc4b8501792f6189e9c94f207716ea91220d12fb5c6fa44a37","target":"graph","created_at":"2026-07-05T08:29:22Z","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/2402.14860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation and ranking of large language models (LLMs) has become an important problem with the proliferation of these models and their impact. Evaluation methods either require human responses which are expensive to acquire or use pairs of LLMs to evaluate each other which can be unreliable. In this paper, we provide a novel perspective where, given a dataset of prompts (viz. questions, instructions, etc.) and a set of LLMs, we rank them without access to any ground truth or reference responses. Inspired by real life where both an expert and a knowledgeable person can identify a novice our ma","authors_text":"Amit Dhurandhar, Elizabeth Daly, Karthikeyan Natesan Ramamurthy, Moninder Singh, Rahul Nair","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:49:43Z","title":"Ranking Large Language Models without Ground Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14860","kind":"arxiv","version":4},"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":"sha256:2ef67408ae6e84b674d7a847deedcb6a1f2edbb370797e06d68a942e68c64857","target":"record","created_at":"2026-07-05T08:29:22Z","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":"482571bf4f07257ccc2d6fb417271a5bbec970cac80ea6d46c95df1f0606d2b6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T00:49:43Z","title_canon_sha256":"aacd57dacd37ce27e1ad384a92d8f8a79bc7327044144d38d2c3f5a38eabaf06"},"schema_version":"1.0","source":{"id":"2402.14860","kind":"arxiv","version":4}},"canonical_sha256":"c9351168cdbd86d6bbcc0681e22745c64db66a65ad32cd653f8041054719a4f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9351168cdbd86d6bbcc0681e22745c64db66a65ad32cd653f8041054719a4f3","first_computed_at":"2026-07-05T08:29:22.890000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:22.890000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ll7vRQYNAPon0M+8VnWjURvbiBlEUHv9usRpZDEQ/W0KM57lqIlbVI27BOrVHBNpb+FlLIj8iNQE/9lk59qcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:22.890491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14860","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ef67408ae6e84b674d7a847deedcb6a1f2edbb370797e06d68a942e68c64857","sha256:df94b6838c3696bc4b8501792f6189e9c94f207716ea91220d12fb5c6fa44a37"],"state_sha256":"83cbd4e52283adc34d3f9bcb7164adfbf1db1dbe384bce7aec748040f1f045f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kYPUo/Zh48UZ19phuBdPAG5kh53eYYoz2X6ARhxxevuA+ANk4CQ9S2XHRLp2ISJP2oCEhN1Voy6hEqcJ5KmkDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:32:04.780166Z","bundle_sha256":"0d9565847662c5c17729332f488f408ba9eeeaad9376bfb68c250cee48da2a87"}}