{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EFNEWTGX3CG2ELASTIIDWQSZ4G","short_pith_number":"pith:EFNEWTGX","schema_version":"1.0","canonical_sha256":"215a4b4cd7d88da22c129a103b4259e1b2a04146d047634420917b5b96a2802d","source":{"kind":"arxiv","id":"2401.15927","version":1},"attestation_state":"computed","paper":{"title":"E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang Ao, Chengming Li, Daijia Tang, Haihong Wu, Jinchang Hou, Min Yang, Ruifeng Xu, Shiwen Ni, Xiangtao Kong, Xiping Hu, Zhigang Zheng","submitted_at":"2024-01-29T07:34:37Z","abstract_excerpt":"With the accelerating development of Large Language Models (LLMs), many LLMs are beginning to be used in the Chinese K-12 education domain. The integration of LLMs and education is getting closer and closer, however, there is currently no benchmark for evaluating LLMs that focuses on the Chinese K-12 education domain. Therefore, there is an urgent need for a comprehensive natural language processing benchmark to accurately assess the capabilities of various LLMs in the Chinese K-12 education domain. To address this, we introduce the E-EVAL, the first comprehensive evaluation benchmark specific"},"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":"2401.15927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T07:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"f7ff463c15b36c4ee14fae5eefe832f70181a934f71c3d0d3090d102541a1ec6","abstract_canon_sha256":"2eff282dcb6645ce41d01bbe43a57a18a80586a8f8a79cfc688b28bdb4646eae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:41.561164Z","signature_b64":"Y1M5hTGd76JvyXbLht2BXfA+QeErk748sTgo3KjANDvCWPwATlK+pt2xckEJ/A0aquXi+sMsWjNmApkQbI5jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"215a4b4cd7d88da22c129a103b4259e1b2a04146d047634420917b5b96a2802d","last_reissued_at":"2026-07-05T07:38:41.560673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:41.560673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang Ao, Chengming Li, Daijia Tang, Haihong Wu, Jinchang Hou, Min Yang, Ruifeng Xu, Shiwen Ni, Xiangtao Kong, Xiping Hu, Zhigang Zheng","submitted_at":"2024-01-29T07:34:37Z","abstract_excerpt":"With the accelerating development of Large Language Models (LLMs), many LLMs are beginning to be used in the Chinese K-12 education domain. The integration of LLMs and education is getting closer and closer, however, there is currently no benchmark for evaluating LLMs that focuses on the Chinese K-12 education domain. Therefore, there is an urgent need for a comprehensive natural language processing benchmark to accurately assess the capabilities of various LLMs in the Chinese K-12 education domain. To address this, we introduce the E-EVAL, the first comprehensive evaluation benchmark specific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15927","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/2401.15927/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":"2401.15927","created_at":"2026-07-05T07:38:41.560738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15927v1","created_at":"2026-07-05T07:38:41.560738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15927","created_at":"2026-07-05T07:38:41.560738+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFNEWTGX3CG2","created_at":"2026-07-05T07:38:41.560738+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFNEWTGX3CG2ELAS","created_at":"2026-07-05T07:38:41.560738+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFNEWTGX","created_at":"2026-07-05T07:38:41.560738+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/EFNEWTGX3CG2ELASTIIDWQSZ4G","json":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G.json","graph_json":"https://pith.science/api/pith-number/EFNEWTGX3CG2ELASTIIDWQSZ4G/graph.json","events_json":"https://pith.science/api/pith-number/EFNEWTGX3CG2ELASTIIDWQSZ4G/events.json","paper":"https://pith.science/paper/EFNEWTGX"},"agent_actions":{"view_html":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G","download_json":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G.json","view_paper":"https://pith.science/paper/EFNEWTGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15927&json=true","fetch_graph":"https://pith.science/api/pith-number/EFNEWTGX3CG2ELASTIIDWQSZ4G/graph.json","fetch_events":"https://pith.science/api/pith-number/EFNEWTGX3CG2ELASTIIDWQSZ4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G/action/storage_attestation","attest_author":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G/action/author_attestation","sign_citation":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G/action/citation_signature","submit_replication":"https://pith.science/pith/EFNEWTGX3CG2ELASTIIDWQSZ4G/action/replication_record"}},"created_at":"2026-07-05T07:38:41.560738+00:00","updated_at":"2026-07-05T07:38:41.560738+00:00"}