{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6RO4XJDN4MSEX6OSOTDNJXHRNR","short_pith_number":"pith:6RO4XJDN","schema_version":"1.0","canonical_sha256":"f45dcba46de3244bf9d274c6d4dcf16c74445c355a264fbd8076b6b6072d4096","source":{"kind":"arxiv","id":"2306.17156","version":3},"attestation_state":"computed","paper":{"title":"Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Adish Singla, Gustavo Soares, Jos\\'e Cambronero, Rupak Majumdar, Sumit Gulwani, Tobias Kohn, Tung Phung, Victor-Alexandru P\\u{a}durean","submitted_at":"2023-06-29T17:57:40Z","abstract_excerpt":"Generative AI and large language models hold great promise in enhancing computing education by powering next-generation educational technologies for introductory programming. Recent works have studied these models for different scenarios relevant to programming education; however, these works are limited for several reasons, as they typically consider already outdated models or only specific scenario(s). Consequently, there is a lack of a systematic study that benchmarks state-of-the-art models for a comprehensive set of programming education scenarios. In our work, we systematically evaluate "},"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":"2306.17156","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2023-06-29T17:57:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c56f828e1f9bd716a35f7e59dc7f423ebe9ef876f443adf82c431e8b81cecd2e","abstract_canon_sha256":"bbc753c3a7bba1a457f6d0e72d5e5d1d1b3f5da4d00cfe39b91ee33e130337f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:12.377966Z","signature_b64":"iec+FX8zslOkB1L2svE+AFk5Mvh7D8u+nKH2aDVvfoKvw9k20PUqq3q/l4BEVmdFUmzxBCmB8JM+sU4WocPKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f45dcba46de3244bf9d274c6d4dcf16c74445c355a264fbd8076b6b6072d4096","last_reissued_at":"2026-07-05T06:36:12.377385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:12.377385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CY","authors_text":"Adish Singla, Gustavo Soares, Jos\\'e Cambronero, Rupak Majumdar, Sumit Gulwani, Tobias Kohn, Tung Phung, Victor-Alexandru P\\u{a}durean","submitted_at":"2023-06-29T17:57:40Z","abstract_excerpt":"Generative AI and large language models hold great promise in enhancing computing education by powering next-generation educational technologies for introductory programming. Recent works have studied these models for different scenarios relevant to programming education; however, these works are limited for several reasons, as they typically consider already outdated models or only specific scenario(s). Consequently, there is a lack of a systematic study that benchmarks state-of-the-art models for a comprehensive set of programming education scenarios. In our work, we systematically evaluate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17156","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/2306.17156/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":"2306.17156","created_at":"2026-07-05T06:36:12.377458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17156v3","created_at":"2026-07-05T06:36:12.377458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17156","created_at":"2026-07-05T06:36:12.377458+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RO4XJDN4MSE","created_at":"2026-07-05T06:36:12.377458+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RO4XJDN4MSEX6OS","created_at":"2026-07-05T06:36:12.377458+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RO4XJDN","created_at":"2026-07-05T06:36:12.377458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06418","citing_title":"Trust in AI among Middle Eastern CS Students: Investigating Students' Trust and Usage Patterns Across Saudi Arabia, Kuwait and Jordan","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR","json":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR.json","graph_json":"https://pith.science/api/pith-number/6RO4XJDN4MSEX6OSOTDNJXHRNR/graph.json","events_json":"https://pith.science/api/pith-number/6RO4XJDN4MSEX6OSOTDNJXHRNR/events.json","paper":"https://pith.science/paper/6RO4XJDN"},"agent_actions":{"view_html":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR","download_json":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR.json","view_paper":"https://pith.science/paper/6RO4XJDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17156&json=true","fetch_graph":"https://pith.science/api/pith-number/6RO4XJDN4MSEX6OSOTDNJXHRNR/graph.json","fetch_events":"https://pith.science/api/pith-number/6RO4XJDN4MSEX6OSOTDNJXHRNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR/action/storage_attestation","attest_author":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR/action/author_attestation","sign_citation":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR/action/citation_signature","submit_replication":"https://pith.science/pith/6RO4XJDN4MSEX6OSOTDNJXHRNR/action/replication_record"}},"created_at":"2026-07-05T06:36:12.377458+00:00","updated_at":"2026-07-05T06:36:12.377458+00:00"}