{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IPGUHE4XYCIPNENIHX26DN22PP","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":"2e5514d0bf7f8eb2b6339173987d4ab94ddb414d5cf4a00e8ff0050f51808072","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-08T17:48:42Z","title_canon_sha256":"64430a7a1b732e41a691d405161cf397ec105869bd6cb8d87150924e20a85552"},"schema_version":"1.0","source":{"id":"2407.06172","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06172","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06172v3","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06172","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_12","alias_value":"IPGUHE4XYCIP","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_16","alias_value":"IPGUHE4XYCIPNENI","created_at":"2026-07-05T10:20:38Z"},{"alias_kind":"pith_short_8","alias_value":"IPGUHE4X","created_at":"2026-07-05T10:20:38Z"}],"graph_snapshots":[{"event_id":"sha256:159f13862a62cee760a4e0a72250d208d98efb6e74d0c71724bc2dcbea242b74","target":"graph","created_at":"2026-07-05T10:20:38Z","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/2407.06172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing prompt-based methods with Large Language Models (LLMs) requires making numerous decisions, which give rise to a combinatorial search problem over hyper-parameters. This exhaustive evaluation can be time-consuming and costly. In this paper, we propose an $\\textit{adaptive}$ approach to explore this space. We are exploiting the fact that often only few samples are needed to identify clearly superior or inferior settings, and that many evaluation tests are highly correlated. We lean on multi-armed bandits to sequentially identify the next (method, validation sample)-pair to evaluate an","authors_text":"Carla P. Gomes, Christian K. Belardi, Jin Peng Zhou, Kilian Q. Weinberger, Ruihan Wu, Travis Zhang, Wen Sun","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-08T17:48:42Z","title":"On Speeding Up Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06172","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":"sha256:60b560d980815fa97acc5354a0432fcaf1205c9144ecde679495d8b1ba2475a0","target":"record","created_at":"2026-07-05T10:20:38Z","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":"2e5514d0bf7f8eb2b6339173987d4ab94ddb414d5cf4a00e8ff0050f51808072","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-08T17:48:42Z","title_canon_sha256":"64430a7a1b732e41a691d405161cf397ec105869bd6cb8d87150924e20a85552"},"schema_version":"1.0","source":{"id":"2407.06172","kind":"arxiv","version":3}},"canonical_sha256":"43cd439397c090f691a83df5e1b75a7be73f6250cb224a1007f83dbda5c20ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43cd439397c090f691a83df5e1b75a7be73f6250cb224a1007f83dbda5c20ed5","first_computed_at":"2026-07-05T10:20:38.393479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:38.393479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+KptroaXhrb99NL9ha684MPa66cfc9Hno5pKhFHoa5o5pXS7s/SrhKv1AhNOAAyH8wOMsN3sZQrVo4hRnMzPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:38.394010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06172","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60b560d980815fa97acc5354a0432fcaf1205c9144ecde679495d8b1ba2475a0","sha256:159f13862a62cee760a4e0a72250d208d98efb6e74d0c71724bc2dcbea242b74"],"state_sha256":"15a267c42d05f949de1c9939be4040536ab0bbe6acba4fbdb31956aef6955552"}