{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3PLTF5AOHDSFNTEULSML3IIDVI","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":"3d2e25a7eaec66872e143c4ed92b4dd98f22e94736fd414bc7300878b89c483a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-05-19T19:05:48Z","title_canon_sha256":"101624fa55dcd016381cf691a710ffc99f36f76a1ed62e8ebb9f2703b7aa47c7"},"schema_version":"1.0","source":{"id":"2505.13664","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13664","created_at":"2026-07-05T11:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13664v1","created_at":"2026-07-05T11:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13664","created_at":"2026-07-05T11:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"3PLTF5AOHDSF","created_at":"2026-07-05T11:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"3PLTF5AOHDSFNTEU","created_at":"2026-07-05T11:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"3PLTF5AO","created_at":"2026-07-05T11:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:d4523a6757f4b98d9a7ad4557b3242700b99e85f0d1eab8f852906f7b155f575","target":"graph","created_at":"2026-07-05T11:06:13Z","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/2505.13664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Federico Solda, Ming Ding, Rasmus Kyng, Weixuan Yuan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-05-19T19:05:48Z","title":"Assessing GPT Performance in a Proof-Based University-Level Course Under Blind Grading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13664","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":"sha256:5b377fe28ab8a16f762ba13054b4e3f3c9d84c7d440d15b04f910a5aa6033c94","target":"record","created_at":"2026-07-05T11:06:13Z","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":"3d2e25a7eaec66872e143c4ed92b4dd98f22e94736fd414bc7300878b89c483a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2025-05-19T19:05:48Z","title_canon_sha256":"101624fa55dcd016381cf691a710ffc99f36f76a1ed62e8ebb9f2703b7aa47c7"},"schema_version":"1.0","source":{"id":"2505.13664","kind":"arxiv","version":1}},"canonical_sha256":"dbd732f40e38e456cc945c98bda103aa2c24563ad18808b9056719791c73b833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbd732f40e38e456cc945c98bda103aa2c24563ad18808b9056719791c73b833","first_computed_at":"2026-07-05T11:06:13.956926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:13.956926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qx8YJwnBHhdWLpCx93mIfnnPPOzCr22nNN1q9dkzqiJ5j0eWJk3ISgjj5rMECZtzFxhLilZHmltdXRTsXy4XAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:13.957456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13664","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b377fe28ab8a16f762ba13054b4e3f3c9d84c7d440d15b04f910a5aa6033c94","sha256:d4523a6757f4b98d9a7ad4557b3242700b99e85f0d1eab8f852906f7b155f575"],"state_sha256":"b2926f1684c898b9caab58bc9f6cdc9d54258f0002a9398e42a3236e80a581d1"}