{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QUIUDW2BI3PKQC2MXKYGZVF76L","short_pith_number":"pith:QUIUDW2B","schema_version":"1.0","canonical_sha256":"851141db4146dea80b4cbab06cd4bff2e1d151e8b399dbbf990179eb29542320","source":{"kind":"arxiv","id":"2608.00014","version":1},"attestation_state":"computed","paper":{"title":"CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Li, Huacan Wang, Peijie Dong, Qihua Pan, Xiang Liu, Xiaowen Chu, Zhenheng Tang","submitted_at":"2026-06-24T16:14:12Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) incurs prohibitive computational overhead during continuous development processes. While coreset selection accelerates evaluation, existing methods either suffer from a severe ``cold start'' bottleneck requiring massive historical logs (e.g., Item Response Theory) or exhibit a surface lexical bias that misses the underlying reasoning manifold of tasks. We propose CoT-Core, a novel training-free core question selection framework. Recognizing that lexically disparate questions can share equivalent underlying logic, CoT-Core prompts LLMs to unroll zero-shot"},"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":"2608.00014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T16:14:12Z","cross_cats_sorted":[],"title_canon_sha256":"d9dd1e1e0aa91740be86aad2bbe11994325d0da9db439be8bfa8ddf0fce3d573","abstract_canon_sha256":"3c24d92754436f9be873de3448537c0dcbceaf557c92e8a019f6c3d71f314db0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:31:38.644226Z","signature_b64":"MpcGgQkAAcr0w61zmpkzft+ppIzjZGuTe5w5bzj7rj5vF477l7MsROnbdEizoE16kBOPGoPdRdwfolMYVSpnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"851141db4146dea80b4cbab06cd4bff2e1d151e8b399dbbf990179eb29542320","last_reissued_at":"2026-08-04T00:31:38.642525Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:31:38.642525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoT-Core: Accelerating LLM Evaluation via CoT-Aware Coreset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo Li, Huacan Wang, Peijie Dong, Qihua Pan, Xiang Liu, Xiaowen Chu, Zhenheng Tang","submitted_at":"2026-06-24T16:14:12Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) incurs prohibitive computational overhead during continuous development processes. While coreset selection accelerates evaluation, existing methods either suffer from a severe ``cold start'' bottleneck requiring massive historical logs (e.g., Item Response Theory) or exhibit a surface lexical bias that misses the underlying reasoning manifold of tasks. We propose CoT-Core, a novel training-free core question selection framework. Recognizing that lexically disparate questions can share equivalent underlying logic, CoT-Core prompts LLMs to unroll zero-shot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00014","kind":"arxiv","version":1},"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/2608.00014/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":"2608.00014","created_at":"2026-08-04T00:31:38.643536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00014v1","created_at":"2026-08-04T00:31:38.643536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00014","created_at":"2026-08-04T00:31:38.643536+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUIUDW2BI3PK","created_at":"2026-08-04T00:31:38.643536+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUIUDW2BI3PKQC2M","created_at":"2026-08-04T00:31:38.643536+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUIUDW2B","created_at":"2026-08-04T00:31:38.643536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L","json":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L.json","graph_json":"https://pith.science/api/pith-number/QUIUDW2BI3PKQC2MXKYGZVF76L/graph.json","events_json":"https://pith.science/api/pith-number/QUIUDW2BI3PKQC2MXKYGZVF76L/events.json","paper":"https://pith.science/paper/QUIUDW2B"},"agent_actions":{"view_html":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L","download_json":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L.json","view_paper":"https://pith.science/paper/QUIUDW2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00014&json=true","fetch_graph":"https://pith.science/api/pith-number/QUIUDW2BI3PKQC2MXKYGZVF76L/graph.json","fetch_events":"https://pith.science/api/pith-number/QUIUDW2BI3PKQC2MXKYGZVF76L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L/action/storage_attestation","attest_author":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L/action/author_attestation","sign_citation":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L/action/citation_signature","submit_replication":"https://pith.science/pith/QUIUDW2BI3PKQC2MXKYGZVF76L/action/replication_record"}},"created_at":"2026-08-04T00:31:38.643536+00:00","updated_at":"2026-08-04T00:31:38.643536+00:00"}