{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CRR6CJITT5EGOYB5DVQGNCNEWK","short_pith_number":"pith:CRR6CJIT","schema_version":"1.0","canonical_sha256":"1463e125139f4867603d1d606689a4b292c8e732455b8ad49c7ad40091679886","source":{"kind":"arxiv","id":"2401.10286","version":3},"attestation_state":"computed","paper":{"title":"Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Shi, Hongwei Chen, Hui Liu, Jiayuan Dong, Linghan Zheng, Xiaojun Lin, Yue Sheng, Zhiwei Liu","submitted_at":"2024-01-16T02:11:35Z","abstract_excerpt":"In previous studies, code-based models have consistently outperformed text-based models in reasoning-intensive scenarios. When generating our knowledge base for Retrieval-Augmented Generation (RAG), we observed that code-based models also perform exceptionally well in Chinese QA Pair Extraction task. Further, our experiments and the metrics we designed discovered that code-based models containing a certain amount of Chinese data achieve even better performance. Additionally, the capabilities of code-based English models in specified Chinese tasks offer a distinct perspective for discussion on "},"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":"2401.10286","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T02:11:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09cec5d016f6623f2bcf785ac40d7faee5faf5eb969af187c1941acc439bd080","abstract_canon_sha256":"6f8bd45131d07124c9b292d06a2e0f7cb77170ee9ecc4ed252bd9276fab38334"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:07.497325Z","signature_b64":"FV4a3pFj1jAd2TKhZ220gOC3MwoAj+o95r8bGmnzyJeAzl91mii/tkCcrPut69rBO+1bFLCb+8lLDPHtyLRzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1463e125139f4867603d1d606689a4b292c8e732455b8ad49c7ad40091679886","last_reissued_at":"2026-07-05T07:54:07.496845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:07.496845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gang Shi, Hongwei Chen, Hui Liu, Jiayuan Dong, Linghan Zheng, Xiaojun Lin, Yue Sheng, Zhiwei Liu","submitted_at":"2024-01-16T02:11:35Z","abstract_excerpt":"In previous studies, code-based models have consistently outperformed text-based models in reasoning-intensive scenarios. When generating our knowledge base for Retrieval-Augmented Generation (RAG), we observed that code-based models also perform exceptionally well in Chinese QA Pair Extraction task. Further, our experiments and the metrics we designed discovered that code-based models containing a certain amount of Chinese data achieve even better performance. Additionally, the capabilities of code-based English models in specified Chinese tasks offer a distinct perspective for discussion on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10286","kind":"arxiv","version":3},"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/2401.10286/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":"2401.10286","created_at":"2026-07-05T07:54:07.496905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10286v3","created_at":"2026-07-05T07:54:07.496905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10286","created_at":"2026-07-05T07:54:07.496905+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRR6CJITT5EG","created_at":"2026-07-05T07:54:07.496905+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRR6CJITT5EGOYB5","created_at":"2026-07-05T07:54:07.496905+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRR6CJIT","created_at":"2026-07-05T07:54:07.496905+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/CRR6CJITT5EGOYB5DVQGNCNEWK","json":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK.json","graph_json":"https://pith.science/api/pith-number/CRR6CJITT5EGOYB5DVQGNCNEWK/graph.json","events_json":"https://pith.science/api/pith-number/CRR6CJITT5EGOYB5DVQGNCNEWK/events.json","paper":"https://pith.science/paper/CRR6CJIT"},"agent_actions":{"view_html":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK","download_json":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK.json","view_paper":"https://pith.science/paper/CRR6CJIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10286&json=true","fetch_graph":"https://pith.science/api/pith-number/CRR6CJITT5EGOYB5DVQGNCNEWK/graph.json","fetch_events":"https://pith.science/api/pith-number/CRR6CJITT5EGOYB5DVQGNCNEWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK/action/storage_attestation","attest_author":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK/action/author_attestation","sign_citation":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK/action/citation_signature","submit_replication":"https://pith.science/pith/CRR6CJITT5EGOYB5DVQGNCNEWK/action/replication_record"}},"created_at":"2026-07-05T07:54:07.496905+00:00","updated_at":"2026-07-05T07:54:07.496905+00:00"}