{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E2ECGJRUVDND77BHSIV4JL323W","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":"b7aa335cca37d416c2b571bf60e0d59adfe7682e80e205f45de9931e6c86042d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:40:06Z","title_canon_sha256":"59a42c5cff6dc27a5a139db9a54a1d9456f137bcab4c51d4492e6afb51fc6d9e"},"schema_version":"1.0","source":{"id":"2402.11443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11443","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11443v1","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11443","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"E2ECGJRUVDND","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"E2ECGJRUVDND77BH","created_at":"2026-07-05T07:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"E2ECGJRU","created_at":"2026-07-05T07:46:39Z"}],"graph_snapshots":[{"event_id":"sha256:36e99fbf776a3e77d889563fec475d7ea358af4570e26f7f14108d5e83e6adfa","target":"graph","created_at":"2026-07-05T07:46:39Z","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/2402.11443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a benchmark self-evolving framework to dynamically evaluate rapidly advancing Large Language Models (LLMs), aiming for a more accurate assessment of their capabilities and limitations. We utilize a multi-agent system to manipulate the context or question of original instances, reframing new evolving instances with high confidence that dynamically extend existing benchmarks. Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their probl","authors_text":"Siyuan Wang, Xuanjing Huang, Zhihao Fan, Zhongyu Wei, Zhuohan Long","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:40:06Z","title":"Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11443","kind":"arxiv","version":1},"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":"sha256:4107059c2536cd67309925d00f98dbd85c19d006e349eafb295034bdfd78907e","target":"record","created_at":"2026-07-05T07:46:39Z","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":"b7aa335cca37d416c2b571bf60e0d59adfe7682e80e205f45de9931e6c86042d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:40:06Z","title_canon_sha256":"59a42c5cff6dc27a5a139db9a54a1d9456f137bcab4c51d4492e6afb51fc6d9e"},"schema_version":"1.0","source":{"id":"2402.11443","kind":"arxiv","version":1}},"canonical_sha256":"2688232634a8da3ffc27922bc4af7addbcb34e6cd245a515397eef5355367000","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2688232634a8da3ffc27922bc4af7addbcb34e6cd245a515397eef5355367000","first_computed_at":"2026-07-05T07:46:39.117463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:39.117463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bDJFPvoaS12CNeHp4Du/kEb4IllKhEEq1E0tTv4qWFfHPMZ25Ay686ioXSlMw7QSR2dwDt8jRrzIdpWxyAR3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:39.117967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4107059c2536cd67309925d00f98dbd85c19d006e349eafb295034bdfd78907e","sha256:36e99fbf776a3e77d889563fec475d7ea358af4570e26f7f14108d5e83e6adfa"],"state_sha256":"5368d5c5dc2449cc178769d870591ff57cc59cb5ac5791531fc5d251bec449e1"}