{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5RVVDOIQZG5JBQOON44V2YTLJZ","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":"2d8513c542741dbae945c1e946928a7a095b6394c30ba8e67bbfa997c3d4fb73","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:46:34Z","title_canon_sha256":"a1ff304c90df8344022b27e5d4b264c5b5e10191e59139cfe8570d092ac7dc72"},"schema_version":"1.0","source":{"id":"2402.14865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14865","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14865v2","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14865","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_12","alias_value":"5RVVDOIQZG5J","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"5RVVDOIQZG5JBQOO","created_at":"2026-07-05T08:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"5RVVDOIQ","created_at":"2026-07-05T08:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:1f6f2b4dc066c1034cbeb63c6f96d538bfed8b1715330f7a08ef92d7882c4111","target":"graph","created_at":"2026-07-05T08:28:38Z","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/2402.14865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jindong Wang, Kaijie Zhu, Qinlin Zhao, Ruochen Xu, Xing Xie","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:46:34Z","title":"Dynamic Evaluation of Large Language Models by Meta Probing Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14865","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":"sha256:5ba5c0214b30c64b7feeb21386b1ecf9e54b5635cf2434db980a9cfb032a3f97","target":"record","created_at":"2026-07-05T08:28:38Z","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":"2d8513c542741dbae945c1e946928a7a095b6394c30ba8e67bbfa997c3d4fb73","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T06:46:34Z","title_canon_sha256":"a1ff304c90df8344022b27e5d4b264c5b5e10191e59139cfe8570d092ac7dc72"},"schema_version":"1.0","source":{"id":"2402.14865","kind":"arxiv","version":2}},"canonical_sha256":"ec6b51b910c9ba90c1ce6f395d626b4e6e1825e3ad4d1551c20de3e55709b709","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec6b51b910c9ba90c1ce6f395d626b4e6e1825e3ad4d1551c20de3e55709b709","first_computed_at":"2026-07-05T08:28:38.745725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:38.745725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vX23C8boFb+/zkCq+EL0Xc1L/XIGmL70ftCBuct3rr9Tzs6Y7i38qxu31pSwS5tltdKrmdEJXVKTgtukrT3BCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:38.746221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ba5c0214b30c64b7feeb21386b1ecf9e54b5635cf2434db980a9cfb032a3f97","sha256:1f6f2b4dc066c1034cbeb63c6f96d538bfed8b1715330f7a08ef92d7882c4111"],"state_sha256":"9210319d7bd93f3bb8cc5c5a5d356568671197656eb14a34c82ffc8a05c72d6e"}