{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EFNEWTGX3CG2ELASTIIDWQSZ4G","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":"2eff282dcb6645ce41d01bbe43a57a18a80586a8f8a79cfc688b28bdb4646eae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T07:34:37Z","title_canon_sha256":"f7ff463c15b36c4ee14fae5eefe832f70181a934f71c3d0d3090d102541a1ec6"},"schema_version":"1.0","source":{"id":"2401.15927","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15927","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15927v1","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15927","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"EFNEWTGX3CG2","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"EFNEWTGX3CG2ELAS","created_at":"2026-07-05T07:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"EFNEWTGX","created_at":"2026-07-05T07:38:41Z"}],"graph_snapshots":[{"event_id":"sha256:7389d046e029cc1041c8a6238bff474baa8cf6b28df80d64a24a8a3bdc83cd6f","target":"graph","created_at":"2026-07-05T07:38:41Z","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/2401.15927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chang Ao, Chengming Li, Daijia Tang, Haihong Wu, Jinchang Hou, Min Yang, Ruifeng Xu, Shiwen Ni, Xiangtao Kong, Xiping Hu, Zhigang Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T07:34:37Z","title":"E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15927","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:a49b8907cac79156fd5a4ced54cfae6d559ad996cd592c8d5c161a27d7e81938","target":"record","created_at":"2026-07-05T07:38:41Z","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":"2eff282dcb6645ce41d01bbe43a57a18a80586a8f8a79cfc688b28bdb4646eae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T07:34:37Z","title_canon_sha256":"f7ff463c15b36c4ee14fae5eefe832f70181a934f71c3d0d3090d102541a1ec6"},"schema_version":"1.0","source":{"id":"2401.15927","kind":"arxiv","version":1}},"canonical_sha256":"215a4b4cd7d88da22c129a103b4259e1b2a04146d047634420917b5b96a2802d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"215a4b4cd7d88da22c129a103b4259e1b2a04146d047634420917b5b96a2802d","first_computed_at":"2026-07-05T07:38:41.560673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:41.560673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y1M5hTGd76JvyXbLht2BXfA+QeErk748sTgo3KjANDvCWPwATlK+pt2xckEJ/A0aquXi+sMsWjNmApkQbI5jCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:41.561164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15927","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a49b8907cac79156fd5a4ced54cfae6d559ad996cd592c8d5c161a27d7e81938","sha256:7389d046e029cc1041c8a6238bff474baa8cf6b28df80d64a24a8a3bdc83cd6f"],"state_sha256":"f6946d5f6e57d137bf85287d5af3ea7e823282451650b8fbfbbac13e93f2b0e6"}