{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZVKZ2CBJWGN33SHPH4G72SL2X","short_pith_number":"pith:LZVKZ2CB","schema_version":"1.0","canonical_sha256":"5e6aace8414d8cddee4779f86fea4bd5e307ba430c2503cd41b322b3cf10aaed","source":{"kind":"arxiv","id":"2406.10786","version":3},"attestation_state":"computed","paper":{"title":"Evaluating LLMs with Multiple Problems at once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jordan Kodner, Owen Rambow, Zhengxiang Wang","submitted_at":"2024-06-16T02:52:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.10786","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-16T02:52:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"65b2ef7c7ab04cec6003219a22f57932b82abb53fc29608f6e2f339b594a8cab","abstract_canon_sha256":"eb803092e7904cd82dc6c16d7e3d419c003e4fc56884837e09777408a39461e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:01.985657Z","signature_b64":"4dLNnNVPhEZ0AHfuXekpLdNWqRoGRxfyK70OD5HimosXh3jfpPta2TpL7ljAsTtGk0KCVNZ6eDdl1OYnkVOODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6aace8414d8cddee4779f86fea4bd5e307ba430c2503cd41b322b3cf10aaed","last_reissued_at":"2026-07-05T11:25:01.985163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:01.985163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLMs with Multiple Problems at once","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jordan Kodner, Owen Rambow, Zhengxiang Wang","submitted_at":"2024-06-16T02:52:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10786","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.10786/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.10786","created_at":"2026-07-05T11:25:01.985229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10786v3","created_at":"2026-07-05T11:25:01.985229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10786","created_at":"2026-07-05T11:25:01.985229+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZVKZ2CBJWGN","created_at":"2026-07-05T11:25:01.985229+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZVKZ2CBJWGN33SH","created_at":"2026-07-05T11:25:01.985229+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZVKZ2CB","created_at":"2026-07-05T11:25:01.985229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06738","citing_title":"Resurrecting saturated LLM benchmarks with adversarial encoding","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X","json":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X.json","graph_json":"https://pith.science/api/pith-number/LZVKZ2CBJWGN33SHPH4G72SL2X/graph.json","events_json":"https://pith.science/api/pith-number/LZVKZ2CBJWGN33SHPH4G72SL2X/events.json","paper":"https://pith.science/paper/LZVKZ2CB"},"agent_actions":{"view_html":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X","download_json":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X.json","view_paper":"https://pith.science/paper/LZVKZ2CB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10786&json=true","fetch_graph":"https://pith.science/api/pith-number/LZVKZ2CBJWGN33SHPH4G72SL2X/graph.json","fetch_events":"https://pith.science/api/pith-number/LZVKZ2CBJWGN33SHPH4G72SL2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X/action/storage_attestation","attest_author":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X/action/author_attestation","sign_citation":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X/action/citation_signature","submit_replication":"https://pith.science/pith/LZVKZ2CBJWGN33SHPH4G72SL2X/action/replication_record"}},"created_at":"2026-07-05T11:25:01.985229+00:00","updated_at":"2026-07-05T11:25:01.985229+00:00"}