{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WLK5QSX5LFFCZKD2FMM7ICZY7L","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":"fdfd55e2e2a4cbb5a65bfb571d1291a59551cc5dcaedabd8b59603b56605d6a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T22:21:36Z","title_canon_sha256":"bad5475ee3dd3a4489726e40eafceb84e2c456d2e82c7101a53e0b2ba4f62c4f"},"schema_version":"1.0","source":{"id":"2401.00595","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00595","created_at":"2026-07-05T08:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00595v3","created_at":"2026-07-05T08:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00595","created_at":"2026-07-05T08:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"WLK5QSX5LFFC","created_at":"2026-07-05T08:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"WLK5QSX5LFFCZKD2","created_at":"2026-07-05T08:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"WLK5QSX5","created_at":"2026-07-05T08:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:1729333acdc4d258a5a1b0446e06e9a5737ae56adeb98ad9782a97170087ea97","target":"graph","created_at":"2026-07-05T08:15:43Z","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/2401.00595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks. These benchmarks typically rely on a single instruction template for evaluating all LLMs on a specific task. In this paper, we comprehensively analyze the brittleness of results obtained via single-prompt evaluations across 6.5M instances, involving 20 different LLMs and 39 tasks from 3 benchmarks. To improve robustness of the analysis, we propose to evaluate LLMs with a set of diverse prompts instead. We discuss tailored evaluation metrics for specific use cases (e.g., LLM developers ","authors_text":"Dafna Shahaf, Dan Malkin, Gabriel Stanovsky, Guy Kaplan, Moran Mizrahi, Rotem Dror","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T22:21:36Z","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00595","kind":"arxiv","version":3},"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":"sha256:87d723177d892d2f2b303d982a3ee6f05df8e2803203d629562050e807275724","target":"record","created_at":"2026-07-05T08:15:43Z","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":"fdfd55e2e2a4cbb5a65bfb571d1291a59551cc5dcaedabd8b59603b56605d6a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-31T22:21:36Z","title_canon_sha256":"bad5475ee3dd3a4489726e40eafceb84e2c456d2e82c7101a53e0b2ba4f62c4f"},"schema_version":"1.0","source":{"id":"2401.00595","kind":"arxiv","version":3}},"canonical_sha256":"b2d5d84afd594a2ca87a2b19f40b38fafbe97101b1b7f1db764e7abe14f2dedd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2d5d84afd594a2ca87a2b19f40b38fafbe97101b1b7f1db764e7abe14f2dedd","first_computed_at":"2026-07-05T08:15:43.537271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:43.537271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NSp4biaXvU3Qi0peL5C4+aHO5CF+I+8tfVOE5gvWqNOPyXdYgIk+i6bo3fQcX4tKjnejtbRyxKYezYRxwGnKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:43.537811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00595","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87d723177d892d2f2b303d982a3ee6f05df8e2803203d629562050e807275724","sha256:1729333acdc4d258a5a1b0446e06e9a5737ae56adeb98ad9782a97170087ea97"],"state_sha256":"e2275d45741784649b75ec8cc1b2669071667ef7ae8761a8c0852c7797731ffb"}