{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5RVVDOIQZG5JBQOON44V2YTLJZ","short_pith_number":"pith:5RVVDOIQ","schema_version":"1.0","canonical_sha256":"ec6b51b910c9ba90c1ce6f395d626b4e6e1825e3ad4d1551c20de3e55709b709","source":{"kind":"arxiv","id":"2402.14865","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jindong Wang, Kaijie Zhu, Qinlin Zhao, Ruochen Xu, Xing Xie","submitted_at":"2024-02-21T06:46:34Z","abstract_excerpt":"Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be easily extended to diverse scenarios. Moreover, current evaluation benchmarks can only provide the overall benchmark results and cannot support a fine-grained and multifaceted analysis of LLMs' abilities. In this paper, we propose meta probing agents (MPA), a general dynamic evaluation protocol inspired by psychometrics to evaluate LLMs. MPA is the key component"},"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":"2402.14865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:46:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a1ff304c90df8344022b27e5d4b264c5b5e10191e59139cfe8570d092ac7dc72","abstract_canon_sha256":"2d8513c542741dbae945c1e946928a7a095b6394c30ba8e67bbfa997c3d4fb73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:38.746221Z","signature_b64":"vX23C8boFb+/zkCq+EL0Xc1L/XIGmL70ftCBuct3rr9Tzs6Y7i38qxu31pSwS5tltdKrmdEJXVKTgtukrT3BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec6b51b910c9ba90c1ce6f395d626b4e6e1825e3ad4d1551c20de3e55709b709","last_reissued_at":"2026-07-05T08:28:38.745725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:38.745725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jindong Wang, Kaijie Zhu, Qinlin Zhao, Ruochen Xu, Xing Xie","submitted_at":"2024-02-21T06:46:34Z","abstract_excerpt":"Evaluation of large language models (LLMs) has raised great concerns in the community due to the issue of data contamination. Existing work designed evaluation protocols using well-defined algorithms for specific tasks, which cannot be easily extended to diverse scenarios. Moreover, current evaluation benchmarks can only provide the overall benchmark results and cannot support a fine-grained and multifaceted analysis of LLMs' abilities. In this paper, we propose meta probing agents (MPA), a general dynamic evaluation protocol inspired by psychometrics to evaluate LLMs. MPA is the key component"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14865","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/2402.14865/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":"2402.14865","created_at":"2026-07-05T08:28:38.745812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14865v2","created_at":"2026-07-05T08:28:38.745812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14865","created_at":"2026-07-05T08:28:38.745812+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RVVDOIQZG5J","created_at":"2026-07-05T08:28:38.745812+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RVVDOIQZG5JBQOO","created_at":"2026-07-05T08:28:38.745812+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RVVDOIQ","created_at":"2026-07-05T08:28:38.745812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06546","citing_title":"Elmes*: Automated Construction of Fine-Grained Evaluation Rubrics for Large Language Models in Long-Tail Educational Scenarios","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12708","citing_title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08571","citing_title":"Robust Reasoning Benchmark","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2404.11584","citing_title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08571","citing_title":"Robust Reasoning Benchmark","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ","json":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ.json","graph_json":"https://pith.science/api/pith-number/5RVVDOIQZG5JBQOON44V2YTLJZ/graph.json","events_json":"https://pith.science/api/pith-number/5RVVDOIQZG5JBQOON44V2YTLJZ/events.json","paper":"https://pith.science/paper/5RVVDOIQ"},"agent_actions":{"view_html":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ","download_json":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ.json","view_paper":"https://pith.science/paper/5RVVDOIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14865&json=true","fetch_graph":"https://pith.science/api/pith-number/5RVVDOIQZG5JBQOON44V2YTLJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5RVVDOIQZG5JBQOON44V2YTLJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ/action/storage_attestation","attest_author":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ/action/author_attestation","sign_citation":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ/action/citation_signature","submit_replication":"https://pith.science/pith/5RVVDOIQZG5JBQOON44V2YTLJZ/action/replication_record"}},"created_at":"2026-07-05T08:28:38.745812+00:00","updated_at":"2026-07-05T08:28:38.745812+00:00"}