{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3PLTF5AOHDSFNTEULSML3IIDVI","short_pith_number":"pith:3PLTF5AO","schema_version":"1.0","canonical_sha256":"dbd732f40e38e456cc945c98bda103aa2c24563ad18808b9056719791c73b833","source":{"kind":"arxiv","id":"2505.13664","version":1},"attestation_state":"computed","paper":{"title":"Assessing GPT Performance in a Proof-Based University-Level Course Under Blind Grading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Federico Solda, Ming Ding, Rasmus Kyng, Weixuan Yuan","submitted_at":"2025-05-19T19:05:48Z","abstract_excerpt":"As large language models (LLMs) advance, their role in higher education, particularly in free-response problem-solving, requires careful examination. This study assesses the performance of GPT-4o and o1-preview under realistic educational conditions in an undergraduate algorithms course. Anonymous GPT-generated solutions to take-home exams were graded by teaching assistants unaware of their origin. Our analysis examines both coarse-grained performance (scores) and fine-grained reasoning quality (error patterns). Results show that GPT-4o consistently struggles, failing to reach the passing thre"},"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":"2505.13664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-05-19T19:05:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"101624fa55dcd016381cf691a710ffc99f36f76a1ed62e8ebb9f2703b7aa47c7","abstract_canon_sha256":"3d2e25a7eaec66872e143c4ed92b4dd98f22e94736fd414bc7300878b89c483a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:13.957456Z","signature_b64":"qx8YJwnBHhdWLpCx93mIfnnPPOzCr22nNN1q9dkzqiJ5j0eWJk3ISgjj5rMECZtzFxhLilZHmltdXRTsXy4XAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbd732f40e38e456cc945c98bda103aa2c24563ad18808b9056719791c73b833","last_reissued_at":"2026-07-05T11:06:13.956926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:13.956926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing GPT Performance in a Proof-Based University-Level Course Under Blind Grading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Federico Solda, Ming Ding, Rasmus Kyng, Weixuan Yuan","submitted_at":"2025-05-19T19:05:48Z","abstract_excerpt":"As large language models (LLMs) advance, their role in higher education, particularly in free-response problem-solving, requires careful examination. This study assesses the performance of GPT-4o and o1-preview under realistic educational conditions in an undergraduate algorithms course. Anonymous GPT-generated solutions to take-home exams were graded by teaching assistants unaware of their origin. Our analysis examines both coarse-grained performance (scores) and fine-grained reasoning quality (error patterns). Results show that GPT-4o consistently struggles, failing to reach the passing thre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13664","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/2505.13664/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":"2505.13664","created_at":"2026-07-05T11:06:13.956985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13664v1","created_at":"2026-07-05T11:06:13.956985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13664","created_at":"2026-07-05T11:06:13.956985+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PLTF5AOHDSF","created_at":"2026-07-05T11:06:13.956985+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PLTF5AOHDSFNTEU","created_at":"2026-07-05T11:06:13.956985+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PLTF5AO","created_at":"2026-07-05T11:06:13.956985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20995","citing_title":"VArsity: Can Large Language Models Keep Power Engineering Students in Phase?","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI","json":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI.json","graph_json":"https://pith.science/api/pith-number/3PLTF5AOHDSFNTEULSML3IIDVI/graph.json","events_json":"https://pith.science/api/pith-number/3PLTF5AOHDSFNTEULSML3IIDVI/events.json","paper":"https://pith.science/paper/3PLTF5AO"},"agent_actions":{"view_html":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI","download_json":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI.json","view_paper":"https://pith.science/paper/3PLTF5AO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13664&json=true","fetch_graph":"https://pith.science/api/pith-number/3PLTF5AOHDSFNTEULSML3IIDVI/graph.json","fetch_events":"https://pith.science/api/pith-number/3PLTF5AOHDSFNTEULSML3IIDVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI/action/storage_attestation","attest_author":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI/action/author_attestation","sign_citation":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI/action/citation_signature","submit_replication":"https://pith.science/pith/3PLTF5AOHDSFNTEULSML3IIDVI/action/replication_record"}},"created_at":"2026-07-05T11:06:13.956985+00:00","updated_at":"2026-07-05T11:06:13.956985+00:00"}