{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZVKZ2CBJWGN33SHPH4G72SL2X","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":"eb803092e7904cd82dc6c16d7e3d419c003e4fc56884837e09777408a39461e1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T02:52:32Z","title_canon_sha256":"65b2ef7c7ab04cec6003219a22f57932b82abb53fc29608f6e2f339b594a8cab"},"schema_version":"1.0","source":{"id":"2406.10786","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10786","created_at":"2026-07-05T11:25:01Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10786v3","created_at":"2026-07-05T11:25:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10786","created_at":"2026-07-05T11:25:01Z"},{"alias_kind":"pith_short_12","alias_value":"LZVKZ2CBJWGN","created_at":"2026-07-05T11:25:01Z"},{"alias_kind":"pith_short_16","alias_value":"LZVKZ2CBJWGN33SH","created_at":"2026-07-05T11:25:01Z"},{"alias_kind":"pith_short_8","alias_value":"LZVKZ2CB","created_at":"2026-07-05T11:25:01Z"}],"graph_snapshots":[{"event_id":"sha256:0390ed60be44f0e2234ae4a5e67124ffccd79af997a4aa3e8148a60c2faca8a5","target":"graph","created_at":"2026-07-05T11:25:01Z","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/2406.10786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper shows the benefits and fruitfulness of evaluating LLMs with multiple problems at once, a paradigm we call multi-problem evaluation (MPE). Unlike conventional single-problem evaluation, where a prompt presents a single problem and expects one specific answer, MPE places multiple problems together in a single prompt and assesses how well an LLM answers all these problems in a single output. Leveraging 6 classification and 12 reasoning benchmarks that already exist, we introduce a new benchmark called ZeMPE (Zero-shot Multi-Problem Evaluation), comprising 53,100 zero-shot multi-problem","authors_text":"Jordan Kodner, Owen Rambow, Zhengxiang Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T02:52:32Z","title":"Evaluating LLMs with Multiple Problems at once"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10786","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":"sha256:371d6690348a105116e84142e7f819a394b67c1121dc0ebf5b298b9eb34174a9","target":"record","created_at":"2026-07-05T11:25:01Z","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":"eb803092e7904cd82dc6c16d7e3d419c003e4fc56884837e09777408a39461e1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T02:52:32Z","title_canon_sha256":"65b2ef7c7ab04cec6003219a22f57932b82abb53fc29608f6e2f339b594a8cab"},"schema_version":"1.0","source":{"id":"2406.10786","kind":"arxiv","version":3}},"canonical_sha256":"5e6aace8414d8cddee4779f86fea4bd5e307ba430c2503cd41b322b3cf10aaed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e6aace8414d8cddee4779f86fea4bd5e307ba430c2503cd41b322b3cf10aaed","first_computed_at":"2026-07-05T11:25:01.985163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:01.985163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4dLNnNVPhEZ0AHfuXekpLdNWqRoGRxfyK70OD5HimosXh3jfpPta2TpL7ljAsTtGk0KCVNZ6eDdl1OYnkVOODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:01.985657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10786","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:371d6690348a105116e84142e7f819a394b67c1121dc0ebf5b298b9eb34174a9","sha256:0390ed60be44f0e2234ae4a5e67124ffccd79af997a4aa3e8148a60c2faca8a5"],"state_sha256":"8514d13909dc6f4deb3e932c9a9258b0d84370dbbde57e9e654313912e4b0e84"}