{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RELUGUUGH5IJKTSQMXTF5DUED4","short_pith_number":"pith:RELUGUUG","schema_version":"1.0","canonical_sha256":"89174352863f50954e5065e65e8e841f3107d2ec9044622369af024811183a88","source":{"kind":"arxiv","id":"2405.02985","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Boxer, Bill Roberts, Libby Hills, Owen Henkel","submitted_at":"2024-05-05T16:11:06Z","abstract_excerpt":"This paper presents reports on a series of experiments with a novel dataset evaluating how well Large Language Models (LLMs) can mark (i.e. grade) open text responses to short answer questions, Specifically, we explore how well different combinations of GPT version and prompt engineering strategies performed at marking real student answers to short answer across different domain areas (Science and History) and grade-levels (spanning ages 5-16) using a new, never-used-before dataset from Carousel, a quizzing platform. We found that GPT-4, with basic few-shot prompting performed well (Kappa, 0.7"},"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":"2405.02985","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-05T16:11:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dae36d74e9ef2d830245b68279fce454ba3d8304cf7b2bfb9e83c6e5b0b56e4a","abstract_canon_sha256":"1fcfb5add3aaf3db315a96360538d63b6671712bae1154a947c0c847f6159da5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:56.870037Z","signature_b64":"WCbSX5k9sdSVEWQad6XOKR6Oe99F37GjVF3YWZsrIUUpKtU2BbZAooyi6MErHv+w4B6pdtL82GxRigDeIdgTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89174352863f50954e5065e65e8e841f3107d2ec9044622369af024811183a88","last_reissued_at":"2026-07-05T08:15:56.869473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:56.869473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adam Boxer, Bill Roberts, Libby Hills, Owen Henkel","submitted_at":"2024-05-05T16:11:06Z","abstract_excerpt":"This paper presents reports on a series of experiments with a novel dataset evaluating how well Large Language Models (LLMs) can mark (i.e. grade) open text responses to short answer questions, Specifically, we explore how well different combinations of GPT version and prompt engineering strategies performed at marking real student answers to short answer across different domain areas (Science and History) and grade-levels (spanning ages 5-16) using a new, never-used-before dataset from Carousel, a quizzing platform. We found that GPT-4, with basic few-shot prompting performed well (Kappa, 0.7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02985","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/2405.02985/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":"2405.02985","created_at":"2026-07-05T08:15:56.869533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.02985v1","created_at":"2026-07-05T08:15:56.869533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02985","created_at":"2026-07-05T08:15:56.869533+00:00"},{"alias_kind":"pith_short_12","alias_value":"RELUGUUGH5IJ","created_at":"2026-07-05T08:15:56.869533+00:00"},{"alias_kind":"pith_short_16","alias_value":"RELUGUUGH5IJKTSQ","created_at":"2026-07-05T08:15:56.869533+00:00"},{"alias_kind":"pith_short_8","alias_value":"RELUGUUG","created_at":"2026-07-05T08:15:56.869533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14759","citing_title":"Students' Perceptions to a Large Language Model's Generated Feedback and Scores of Argumentation Essays","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4","json":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4.json","graph_json":"https://pith.science/api/pith-number/RELUGUUGH5IJKTSQMXTF5DUED4/graph.json","events_json":"https://pith.science/api/pith-number/RELUGUUGH5IJKTSQMXTF5DUED4/events.json","paper":"https://pith.science/paper/RELUGUUG"},"agent_actions":{"view_html":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4","download_json":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4.json","view_paper":"https://pith.science/paper/RELUGUUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.02985&json=true","fetch_graph":"https://pith.science/api/pith-number/RELUGUUGH5IJKTSQMXTF5DUED4/graph.json","fetch_events":"https://pith.science/api/pith-number/RELUGUUGH5IJKTSQMXTF5DUED4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4/action/storage_attestation","attest_author":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4/action/author_attestation","sign_citation":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4/action/citation_signature","submit_replication":"https://pith.science/pith/RELUGUUGH5IJKTSQMXTF5DUED4/action/replication_record"}},"created_at":"2026-07-05T08:15:56.869533+00:00","updated_at":"2026-07-05T08:15:56.869533+00:00"}