{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AADCJBXXI33NKHSR722JNH3IHG","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":"7a2a5573162688c5b9e612bd5eebf7234d32d9d025d9fe105394e07692021842","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T00:15:44Z","title_canon_sha256":"0df08a4cf055596f6e909c1c1ae928f3a9adf91f7a143c4bf5545eadf6908f5a"},"schema_version":"1.0","source":{"id":"2411.13760","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13760","created_at":"2026-07-05T09:38:36Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13760v1","created_at":"2026-07-05T09:38:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13760","created_at":"2026-07-05T09:38:36Z"},{"alias_kind":"pith_short_12","alias_value":"AADCJBXXI33N","created_at":"2026-07-05T09:38:36Z"},{"alias_kind":"pith_short_16","alias_value":"AADCJBXXI33NKHSR","created_at":"2026-07-05T09:38:36Z"},{"alias_kind":"pith_short_8","alias_value":"AADCJBXX","created_at":"2026-07-05T09:38:36Z"}],"graph_snapshots":[{"event_id":"sha256:82bc044c96b81a0d68cfbc7621e9b17dea6bc5948214ea1bf08cf477dca2283f","target":"graph","created_at":"2026-07-05T09:38:36Z","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/2411.13760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. However, some tasks can be ambiguous -- i.e., they provide insufficient information to identify a unique interpretation -- or vague -- i.e., they do not clearly indicate where to draw the line when making a determination. Both ambiguity and vagueness can cause task indeterminacy -- the condition where some items in the evaluation corpus have more than one correct response. In this paper, we develop a framework for evaluating LLMs under task indetermi","authors_text":"Alexandra Chouldechova, Hanna Wallach, Luke Guerdan, Solon Barocas","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T00:15:44Z","title":"A Framework for Evaluating LLMs Under Task Indeterminacy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13760","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":"sha256:4610a9491adc79a5dc9ae19ff3d84dfbdebc1416c4036e34a410a148feef063e","target":"record","created_at":"2026-07-05T09:38:36Z","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":"7a2a5573162688c5b9e612bd5eebf7234d32d9d025d9fe105394e07692021842","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T00:15:44Z","title_canon_sha256":"0df08a4cf055596f6e909c1c1ae928f3a9adf91f7a143c4bf5545eadf6908f5a"},"schema_version":"1.0","source":{"id":"2411.13760","kind":"arxiv","version":1}},"canonical_sha256":"00062486f746f6d51e51feb4969f6839af07790612ed43900ebf755b1d188e6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00062486f746f6d51e51feb4969f6839af07790612ed43900ebf755b1d188e6c","first_computed_at":"2026-07-05T09:38:36.834383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:36.834383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XYFAFnoreE6qEIZFKITBElR9zKFn55HNlzujQUAblRaeb9M+Wx/Tcuamvc6h3IuA/DQT4yZSai3P6TXOSA2LBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:36.835023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13760","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4610a9491adc79a5dc9ae19ff3d84dfbdebc1416c4036e34a410a148feef063e","sha256:82bc044c96b81a0d68cfbc7621e9b17dea6bc5948214ea1bf08cf477dca2283f"],"state_sha256":"685711a215c4a7d7c264ab7df862ed0110ad8610f5ac3ed6889474a8bdc1db89"}