{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W74S6ZUHBGEJFJDLBCHNYQA756","short_pith_number":"pith:W74S6ZUH","schema_version":"1.0","canonical_sha256":"b7f92f6687098892a46b088edc401fef9a543c8d5f189746e23a4941a7b43ecc","source":{"kind":"arxiv","id":"2306.04181","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haozhe Lyu, Jiahao Ying, Jiayin Zhang, Jifan Yu, Juanzi Li, Kaisheng Zeng, Lei Hou, Xiaozhi Wang, Xin Lv, Yijia Xiao, Yixin Cao, Yushi Bai, Yuze He","submitted_at":"2023-06-07T06:29:58Z","abstract_excerpt":"Numerous benchmarks have been established to assess the performance of foundation models on open-ended question answering, which serves as a comprehensive test of a model's ability to understand and generate language in a manner similar to humans. Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its k"},"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":"2306.04181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T06:29:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4e534195ae01f629178bd5f10b700e6791c2823c644d6f41d9392bb9c1f5d9da","abstract_canon_sha256":"c173d5d33d0327ee111e2ff88e2a043fa3b06d631bd0f855589df00e0690833c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:58.632392Z","signature_b64":"fCiztdDb33HtGHHJzR/K64EWswIT7bjnAjiDVQgIX43mDwdJ3CdxY1qQV83XQU8uePpMwdje3jOtcgIHmPUqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7f92f6687098892a46b088edc401fef9a543c8d5f189746e23a4941a7b43ecc","last_reissued_at":"2026-07-05T07:08:58.631872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:58.631872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Foundation Models with Language-Model-as-an-Examiner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haozhe Lyu, Jiahao Ying, Jiayin Zhang, Jifan Yu, Juanzi Li, Kaisheng Zeng, Lei Hou, Xiaozhi Wang, Xin Lv, Yijia Xiao, Yixin Cao, Yushi Bai, Yuze He","submitted_at":"2023-06-07T06:29:58Z","abstract_excerpt":"Numerous benchmarks have been established to assess the performance of foundation models on open-ended question answering, which serves as a comprehensive test of a model's ability to understand and generate language in a manner similar to humans. Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04181","kind":"arxiv","version":2},"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/2306.04181/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":"2306.04181","created_at":"2026-07-05T07:08:58.631935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04181v2","created_at":"2026-07-05T07:08:58.631935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04181","created_at":"2026-07-05T07:08:58.631935+00:00"},{"alias_kind":"pith_short_12","alias_value":"W74S6ZUHBGEJ","created_at":"2026-07-05T07:08:58.631935+00:00"},{"alias_kind":"pith_short_16","alias_value":"W74S6ZUHBGEJFJDL","created_at":"2026-07-05T07:08:58.631935+00:00"},{"alias_kind":"pith_short_8","alias_value":"W74S6ZUH","created_at":"2026-07-05T07:08:58.631935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26346","citing_title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21008","citing_title":"The Metanym Game: A Self-Contained, Self-Consistent LLM Peer-Community Benchmark for Structural Intelligence","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27914","citing_title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12708","citing_title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2308.07201","citing_title":"ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2308.14508","citing_title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756","json":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756.json","graph_json":"https://pith.science/api/pith-number/W74S6ZUHBGEJFJDLBCHNYQA756/graph.json","events_json":"https://pith.science/api/pith-number/W74S6ZUHBGEJFJDLBCHNYQA756/events.json","paper":"https://pith.science/paper/W74S6ZUH"},"agent_actions":{"view_html":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756","download_json":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756.json","view_paper":"https://pith.science/paper/W74S6ZUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04181&json=true","fetch_graph":"https://pith.science/api/pith-number/W74S6ZUHBGEJFJDLBCHNYQA756/graph.json","fetch_events":"https://pith.science/api/pith-number/W74S6ZUHBGEJFJDLBCHNYQA756/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756/action/storage_attestation","attest_author":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756/action/author_attestation","sign_citation":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756/action/citation_signature","submit_replication":"https://pith.science/pith/W74S6ZUHBGEJFJDLBCHNYQA756/action/replication_record"}},"created_at":"2026-07-05T07:08:58.631935+00:00","updated_at":"2026-07-05T07:08:58.631935+00:00"}