{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KJQDPBFD3YPEYGZEWYWU53XI4X","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":"a1c1cc79fa2026b7997c850adabebc61f8265e1b04d21fa533144464f919ee4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T18:58:38Z","title_canon_sha256":"2b70d02bde6614fd12b2356deb720c45025e11d6aca3918a807cf8a9e0b85899"},"schema_version":"1.0","source":{"id":"2411.07237","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07237","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07237v2","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07237","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"KJQDPBFD3YPE","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"KJQDPBFD3YPEYGZE","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"KJQDPBFD","created_at":"2026-07-05T11:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:2536640359f471f65efbc1f48a15999489ebb758548c646e9d55f3c0080478aa","target":"graph","created_at":"2026-07-05T11:08:39Z","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/2411.07237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model users often issue queries that lack specification, where the context under which a query was issued -- such as the user's identity, the query's intent, and the criteria for a response to be useful -- is not explicit. For instance, a good response to a subjective query like \"What book should I read next?\" would depend on the user's preferences, and a good response to an open-ended query like \"How do antibiotics work against bacteria?\" would depend on the user's expertise. This makes evaluation of responses to such queries an ill-posed task, as evaluators may make arbitrary judgme","authors_text":"Chaitanya Malaviya, Dan Roth, Joseph Chee Chang, Kyle Lo, Mark Yatskar, Mohit Iyyer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T18:58:38Z","title":"Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07237","kind":"arxiv","version":2},"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":"sha256:405d14aa309b9ed168d30aaacaafeef0c6d9581002d75206c6b132199da1530d","target":"record","created_at":"2026-07-05T11:08:39Z","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":"a1c1cc79fa2026b7997c850adabebc61f8265e1b04d21fa533144464f919ee4e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-11T18:58:38Z","title_canon_sha256":"2b70d02bde6614fd12b2356deb720c45025e11d6aca3918a807cf8a9e0b85899"},"schema_version":"1.0","source":{"id":"2411.07237","kind":"arxiv","version":2}},"canonical_sha256":"52603784a3de1e4c1b24b62d4eeee8e5c36ceb7d1e292e18f202e69ccb037aec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52603784a3de1e4c1b24b62d4eeee8e5c36ceb7d1e292e18f202e69ccb037aec","first_computed_at":"2026-07-05T11:08:39.277435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:39.277435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GKPevxWEsQytSgYqd36sDl2TOqYM0fgskIlDkHB8uHcx4nVheYahhzC5k2f8dvsXytKC1jr0UCGaDHsbZagHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:39.277930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07237","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:405d14aa309b9ed168d30aaacaafeef0c6d9581002d75206c6b132199da1530d","sha256:2536640359f471f65efbc1f48a15999489ebb758548c646e9d55f3c0080478aa"],"state_sha256":"6c96ca18020c6a4bf555842608f4be040e152a02b0e1141607dfec3e5bc958f3"}