{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PUQUOEU54C363M7BSK4DDDVZWS","short_pith_number":"pith:PUQUOEU5","schema_version":"1.0","canonical_sha256":"7d2147129de0b7edb3e192b8318eb9b48ba183475aa0446d4968dfc7d81c7e01","source":{"kind":"arxiv","id":"2306.06331","version":3},"attestation_state":"computed","paper":{"title":"Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ngoc-Bich Le, Xuan-Quy Dao","submitted_at":"2023-06-10T02:01:02Z","abstract_excerpt":"This study offers a complete analysis of ChatGPT's mathematics abilities in responding to multiple-choice questions for the Vietnamese National High School Graduation Examination (VNHSGE) on a range of subjects and difficulty levels. The dataset included 250 questions divided into four levels: knowledge (K), comprehension (C), application (A), and high application (H), and it included ten themes that covered diverse mathematical concepts. The outcomes demonstrate that ChatGPT's performance varies depending on the difficulty level and subject. It performed best on questions at Level (K), with a"},"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":"2306.06331","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T02:01:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"605f5ee4d889c21f2b218668e47bb0a3872ba2729a18cbac0c1ee09a17e8b7f6","abstract_canon_sha256":"18e26b0bfde63b5fc65f52f32a03ce6852cd37dcd24b0c9979af518ca204b15e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:12.020606Z","signature_b64":"EfG2MxGCQqzao5fnsO/wqbI8luL/eJaXLvGoSjnyQmoxZuaP0RKkKrDI8puiCxNG6zdc7a8uVehVgzCVPCk3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d2147129de0b7edb3e192b8318eb9b48ba183475aa0446d4968dfc7d81c7e01","last_reissued_at":"2026-07-05T07:07:12.020109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:12.020109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ngoc-Bich Le, Xuan-Quy Dao","submitted_at":"2023-06-10T02:01:02Z","abstract_excerpt":"This study offers a complete analysis of ChatGPT's mathematics abilities in responding to multiple-choice questions for the Vietnamese National High School Graduation Examination (VNHSGE) on a range of subjects and difficulty levels. The dataset included 250 questions divided into four levels: knowledge (K), comprehension (C), application (A), and high application (H), and it included ten themes that covered diverse mathematical concepts. The outcomes demonstrate that ChatGPT's performance varies depending on the difficulty level and subject. It performed best on questions at Level (K), with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06331","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/2306.06331/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":"2306.06331","created_at":"2026-07-05T07:07:12.020166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06331v3","created_at":"2026-07-05T07:07:12.020166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06331","created_at":"2026-07-05T07:07:12.020166+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUQUOEU54C36","created_at":"2026-07-05T07:07:12.020166+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUQUOEU54C363M7B","created_at":"2026-07-05T07:07:12.020166+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUQUOEU5","created_at":"2026-07-05T07:07:12.020166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05852","citing_title":"Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS","json":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS.json","graph_json":"https://pith.science/api/pith-number/PUQUOEU54C363M7BSK4DDDVZWS/graph.json","events_json":"https://pith.science/api/pith-number/PUQUOEU54C363M7BSK4DDDVZWS/events.json","paper":"https://pith.science/paper/PUQUOEU5"},"agent_actions":{"view_html":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS","download_json":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS.json","view_paper":"https://pith.science/paper/PUQUOEU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06331&json=true","fetch_graph":"https://pith.science/api/pith-number/PUQUOEU54C363M7BSK4DDDVZWS/graph.json","fetch_events":"https://pith.science/api/pith-number/PUQUOEU54C363M7BSK4DDDVZWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS/action/storage_attestation","attest_author":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS/action/author_attestation","sign_citation":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS/action/citation_signature","submit_replication":"https://pith.science/pith/PUQUOEU54C363M7BSK4DDDVZWS/action/replication_record"}},"created_at":"2026-07-05T07:07:12.020166+00:00","updated_at":"2026-07-05T07:07:12.020166+00:00"}