{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RFEGH4Q4VKIXYGHTTP2GEE5HXO","short_pith_number":"pith:RFEGH4Q4","schema_version":"1.0","canonical_sha256":"894863f21caa917c18f39bf46213a7bba099ee59d2e01a3ed142681dc36d04af","source":{"kind":"arxiv","id":"2408.11728","version":1},"attestation_state":"computed","paper":{"title":"AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.HO","authors_text":"Gerd Kortemeyer, Julia Chatain, Laura Kobel-Keller, Mrinmaya Sachan, Thomas Willwacher, Tianyi Liu","submitted_at":"2024-08-21T15:54:06Z","abstract_excerpt":"Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of semi-open and open-ended essays, have been facilitated by advances in machine learning. The emergence of pre-trained Large Language Models, such as GPT-4, offers promising new opportunities for efficiently processing diverse response types with minimal customization. This study evaluates the effectiveness of a pre-trained GPT-4 model in grading semi-open handwr"},"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":"2408.11728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.HO","submitted_at":"2024-08-21T15:54:06Z","cross_cats_sorted":[],"title_canon_sha256":"fbaf94e1dbc1103744f9394da26db6804823a5ae38cf5c475b92fe233ec9365f","abstract_canon_sha256":"7d0a4f2b1ceb68da853efc1447d7ed46015318e33d1b619e29fa6f17940628dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:48.203705Z","signature_b64":"N0XAvYtByI6dZ1qifh5TwGlV6kSCi/pQ2Ik+rZCBVcklSnISjnAH4V0il2exo2Uze68v/jDMhFQ9A+iE7215CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894863f21caa917c18f39bf46213a7bba099ee59d2e01a3ed142681dc36d04af","last_reissued_at":"2026-07-05T08:57:48.203253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:48.203253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-assisted Automated Short Answer Grading of Handwritten University Level Mathematics Exams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.HO","authors_text":"Gerd Kortemeyer, Julia Chatain, Laura Kobel-Keller, Mrinmaya Sachan, Thomas Willwacher, Tianyi Liu","submitted_at":"2024-08-21T15:54:06Z","abstract_excerpt":"Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of semi-open and open-ended essays, have been facilitated by advances in machine learning. The emergence of pre-trained Large Language Models, such as GPT-4, offers promising new opportunities for efficiently processing diverse response types with minimal customization. This study evaluates the effectiveness of a pre-trained GPT-4 model in grading semi-open handwr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11728","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/2408.11728/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":"2408.11728","created_at":"2026-07-05T08:57:48.203307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11728v1","created_at":"2026-07-05T08:57:48.203307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11728","created_at":"2026-07-05T08:57:48.203307+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFEGH4Q4VKIX","created_at":"2026-07-05T08:57:48.203307+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFEGH4Q4VKIXYGHT","created_at":"2026-07-05T08:57:48.203307+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFEGH4Q4","created_at":"2026-07-05T08:57:48.203307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28872","citing_title":"Testing the Validity of Embedding-Based Similarity and Clustering for Handwritten Physics Solutions","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19043","citing_title":"Automated Grading of Handwritten Mathematics Using Vision-Capable LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00095","citing_title":"EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO","json":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO.json","graph_json":"https://pith.science/api/pith-number/RFEGH4Q4VKIXYGHTTP2GEE5HXO/graph.json","events_json":"https://pith.science/api/pith-number/RFEGH4Q4VKIXYGHTTP2GEE5HXO/events.json","paper":"https://pith.science/paper/RFEGH4Q4"},"agent_actions":{"view_html":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO","download_json":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO.json","view_paper":"https://pith.science/paper/RFEGH4Q4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11728&json=true","fetch_graph":"https://pith.science/api/pith-number/RFEGH4Q4VKIXYGHTTP2GEE5HXO/graph.json","fetch_events":"https://pith.science/api/pith-number/RFEGH4Q4VKIXYGHTTP2GEE5HXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO/action/storage_attestation","attest_author":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO/action/author_attestation","sign_citation":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO/action/citation_signature","submit_replication":"https://pith.science/pith/RFEGH4Q4VKIXYGHTTP2GEE5HXO/action/replication_record"}},"created_at":"2026-07-05T08:57:48.203307+00:00","updated_at":"2026-07-05T08:57:48.203307+00:00"}