{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NVEKVJXOPDVUBP5UMU2522SHX","short_pith_number":"pith:2NVEKVJX","schema_version":"1.0","canonical_sha256":"d36a45553773c75a05fda329aeeb523dc1941375e6a6d689acb93ed519806728","source":{"kind":"arxiv","id":"2412.18719","version":1},"attestation_state":"computed","paper":{"title":"Using Large Language Models for Automated Grading of Student Writing about Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Impey, Matthew Wenger, Nikhil Garuda, Sarah Stamer, Shahriar Golchin","submitted_at":"2024-12-25T00:31:53Z","abstract_excerpt":"Assessing writing in large classes for formal or informal learners presents a significant challenge. Consequently, most large classes, particularly in science, rely on objective assessment tools such as multiple-choice quizzes, which have a single correct answer. The rapid development of AI has introduced the possibility of using large language models (LLMs) to evaluate student writing. An experiment was conducted using GPT-4 to determine if machine learning methods based on LLMs can match or exceed the reliability of instructor grading in evaluating short writing assignments on topics in astr"},"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":"2412.18719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-25T00:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"3fcb745da543b9afe4dbeb1615779f65a83adaacbfd69965f5ad44ca9469d627","abstract_canon_sha256":"e04881020999dd15f710a6d52ee15767aed35bd3b2881a0ac3dfd4e989923cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:21.264251Z","signature_b64":"FSyyxRIV1+hke1S9YrDKLAlEnXUP6esdLM7y5dfUg3mcyuJTSoI7dgnCsdRlzkvIyX8brL8eyUZjcPM6nMJzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d36a45553773c75a05fda329aeeb523dc1941375e6a6d689acb93ed519806728","last_reissued_at":"2026-07-05T10:04:21.263837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:21.263837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Models for Automated Grading of Student Writing about Science","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Impey, Matthew Wenger, Nikhil Garuda, Sarah Stamer, Shahriar Golchin","submitted_at":"2024-12-25T00:31:53Z","abstract_excerpt":"Assessing writing in large classes for formal or informal learners presents a significant challenge. Consequently, most large classes, particularly in science, rely on objective assessment tools such as multiple-choice quizzes, which have a single correct answer. The rapid development of AI has introduced the possibility of using large language models (LLMs) to evaluate student writing. An experiment was conducted using GPT-4 to determine if machine learning methods based on LLMs can match or exceed the reliability of instructor grading in evaluating short writing assignments on topics in astr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18719","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/2412.18719/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":"2412.18719","created_at":"2026-07-05T10:04:21.263895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18719v1","created_at":"2026-07-05T10:04:21.263895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18719","created_at":"2026-07-05T10:04:21.263895+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NVEKVJXOPDV","created_at":"2026-07-05T10:04:21.263895+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NVEKVJXOPDVUBP5","created_at":"2026-07-05T10:04:21.263895+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NVEKVJX","created_at":"2026-07-05T10:04:21.263895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14499","citing_title":"Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX","json":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX.json","graph_json":"https://pith.science/api/pith-number/2NVEKVJXOPDVUBP5UMU2522SHX/graph.json","events_json":"https://pith.science/api/pith-number/2NVEKVJXOPDVUBP5UMU2522SHX/events.json","paper":"https://pith.science/paper/2NVEKVJX"},"agent_actions":{"view_html":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX","download_json":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX.json","view_paper":"https://pith.science/paper/2NVEKVJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18719&json=true","fetch_graph":"https://pith.science/api/pith-number/2NVEKVJXOPDVUBP5UMU2522SHX/graph.json","fetch_events":"https://pith.science/api/pith-number/2NVEKVJXOPDVUBP5UMU2522SHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX/action/storage_attestation","attest_author":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX/action/author_attestation","sign_citation":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX/action/citation_signature","submit_replication":"https://pith.science/pith/2NVEKVJXOPDVUBP5UMU2522SHX/action/replication_record"}},"created_at":"2026-07-05T10:04:21.263895+00:00","updated_at":"2026-07-05T10:04:21.263895+00:00"}