{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QIB4FQWY6FY2SLXIK3ZPBDHEAW","short_pith_number":"pith:QIB4FQWY","schema_version":"1.0","canonical_sha256":"8203c2c2d8f171a92ee856f2f08ce40594095070210c145236c39ffcd91ce7fd","source":{"kind":"arxiv","id":"2407.15251","version":1},"attestation_state":"computed","paper":{"title":"Achieving Human Level Partial Credit Grading of Written Responses to Physics Conceptual Question using GPT-3.5 with Only Prompt Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Tong Wan, Zhongzhou Chen","submitted_at":"2024-07-21T19:49:18Z","abstract_excerpt":"Large language modules (LLMs) have great potential for auto-grading student written responses to physics problems due to their capacity to process and generate natural language. In this explorative study, we use a prompt engineering technique, which we name \"scaffolded chain of thought (COT)\", to instruct GPT-3.5 to grade student written responses to a physics conceptual question. Compared to common COT prompting, scaffolded COT prompts GPT-3.5 to explicitly compare student responses to a detailed, well-explained rubric before generating the grading outcome. We show that when compared to human"},"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":"2407.15251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.ed-ph","submitted_at":"2024-07-21T19:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"c0860c6dca03fb4fd06ac7898c1ae95471f8244acc1defc10191f1eb7fe337e6","abstract_canon_sha256":"111c99d729e95129152706eea95f8a7a433bf5a8553960f96a6b46424ba54c04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:40.808381Z","signature_b64":"mDKtdXDuI+KjB8CChwICoy7mPsgat+Yh9w8Qw3iVSkjcLG9ZKsXbN3O7qCoWG9QKwrPgCuM7rKX3v8tGxgnLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8203c2c2d8f171a92ee856f2f08ce40594095070210c145236c39ffcd91ce7fd","last_reissued_at":"2026-07-05T08:46:40.807886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:40.807886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Achieving Human Level Partial Credit Grading of Written Responses to Physics Conceptual Question using GPT-3.5 with Only Prompt Engineering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Tong Wan, Zhongzhou Chen","submitted_at":"2024-07-21T19:49:18Z","abstract_excerpt":"Large language modules (LLMs) have great potential for auto-grading student written responses to physics problems due to their capacity to process and generate natural language. In this explorative study, we use a prompt engineering technique, which we name \"scaffolded chain of thought (COT)\", to instruct GPT-3.5 to grade student written responses to a physics conceptual question. Compared to common COT prompting, scaffolded COT prompts GPT-3.5 to explicitly compare student responses to a detailed, well-explained rubric before generating the grading outcome. We show that when compared to human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15251","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/2407.15251/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":"2407.15251","created_at":"2026-07-05T08:46:40.807943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15251v1","created_at":"2026-07-05T08:46:40.807943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15251","created_at":"2026-07-05T08:46:40.807943+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIB4FQWY6FY2","created_at":"2026-07-05T08:46:40.807943+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIB4FQWY6FY2SLXI","created_at":"2026-07-05T08:46:40.807943+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIB4FQWY","created_at":"2026-07-05T08:46:40.807943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01431","citing_title":"Pensieve Grader: An AI-Powered, Ready-to-Use Platform for Effortless Handwritten STEM Grading","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW","json":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW.json","graph_json":"https://pith.science/api/pith-number/QIB4FQWY6FY2SLXIK3ZPBDHEAW/graph.json","events_json":"https://pith.science/api/pith-number/QIB4FQWY6FY2SLXIK3ZPBDHEAW/events.json","paper":"https://pith.science/paper/QIB4FQWY"},"agent_actions":{"view_html":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW","download_json":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW.json","view_paper":"https://pith.science/paper/QIB4FQWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15251&json=true","fetch_graph":"https://pith.science/api/pith-number/QIB4FQWY6FY2SLXIK3ZPBDHEAW/graph.json","fetch_events":"https://pith.science/api/pith-number/QIB4FQWY6FY2SLXIK3ZPBDHEAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW/action/storage_attestation","attest_author":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW/action/author_attestation","sign_citation":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW/action/citation_signature","submit_replication":"https://pith.science/pith/QIB4FQWY6FY2SLXIK3ZPBDHEAW/action/replication_record"}},"created_at":"2026-07-05T08:46:40.807943+00:00","updated_at":"2026-07-05T08:46:40.807943+00:00"}