{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NMBNLFMA4F75LGY22MBIIXMGPY","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":"25e73773a451575bf347171c0063c154809d94e858274667f6eb9533a78ea850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T09:48:23Z","title_canon_sha256":"534d95f13da262f643cee1f137d07367226026e8c976e5e7596223df140f013c"},"schema_version":"1.0","source":{"id":"2508.09662","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09662","created_at":"2026-07-05T11:53:19Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09662v1","created_at":"2026-07-05T11:53:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09662","created_at":"2026-07-05T11:53:19Z"},{"alias_kind":"pith_short_12","alias_value":"NMBNLFMA4F75","created_at":"2026-07-05T11:53:19Z"},{"alias_kind":"pith_short_16","alias_value":"NMBNLFMA4F75LGY2","created_at":"2026-07-05T11:53:19Z"},{"alias_kind":"pith_short_8","alias_value":"NMBNLFMA","created_at":"2026-07-05T11:53:19Z"}],"graph_snapshots":[{"event_id":"sha256:6f12568b72c8c1a420eb9ada9be542f7b3d3dc11efb58ab25aa0c0df0a3c4d57","target":"graph","created_at":"2026-07-05T11:53:19Z","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/2508.09662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of large language models (LLMs) and the development of increasingly large and diverse evaluation benchmarks have introduced substantial computational challenges for model assessment. In this paper, we present EffiEval, a training-free approach for efficient benchmarking that effectively addresses data redundancy while maintaining high evaluation reliability. Our method is specifically designed to meet three key criteria for high-quality evaluation: representativeness, by ensuring comprehensive coverage of model capabilities; fairness, by remaining independent of model per","authors_text":"Jiahao Ying, Yaoning Wang, Yixin Cao, Yubo Ma, Yugang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T09:48:23Z","title":"EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09662","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:a4f79d5b5a30e7545ae36c73428808fdc2a10166d2f7762fef5e371862613b16","target":"record","created_at":"2026-07-05T11:53:19Z","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":"25e73773a451575bf347171c0063c154809d94e858274667f6eb9533a78ea850","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T09:48:23Z","title_canon_sha256":"534d95f13da262f643cee1f137d07367226026e8c976e5e7596223df140f013c"},"schema_version":"1.0","source":{"id":"2508.09662","kind":"arxiv","version":1}},"canonical_sha256":"6b02d59580e17fd59b1ad302845d867e2c1b70af32ae877a97498f91acb783ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b02d59580e17fd59b1ad302845d867e2c1b70af32ae877a97498f91acb783ca","first_computed_at":"2026-07-05T11:53:19.402139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:19.402139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5wn8Luus3WxvsLARqBYpM6gszmTsZUup8W1yhDY747/gA7N1EUoC7Cr3JUPCEiFvZwcvOkhX723U9L5ahxeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:19.403249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09662","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4f79d5b5a30e7545ae36c73428808fdc2a10166d2f7762fef5e371862613b16","sha256:6f12568b72c8c1a420eb9ada9be542f7b3d3dc11efb58ab25aa0c0df0a3c4d57"],"state_sha256":"e1836799b31e192399808b167bd8f9af7dcd9ab68b96f52b30a77ad64f6bf5d2"}