{"paper":{"title":"Using Large Language Models to Analyze Engagement in Computational Thinking via Computational Physics Essays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Computational Physics Essays elicit high variety of computational thinking practices in engineering students, with strong correlation to overall quality.","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Amir Bralin, N.Sanjay Rebello, Paul Hur, Sean Savage","submitted_at":"2026-05-07T23:29:50Z","abstract_excerpt":"As computational thinking (CT) becomes increasingly important to physics education, the need for authentic, project-based assessments has grown. While open-ended multimodal assignments, such as Computational Physics Essays (CPEs), help capture student reasoning and encourage active learning, they introduce a significant evaluation bottleneck. Manually grading these complex notebooks across a complex taxonomy of computational practices is resource-intensive and limits scalability in large-enrollment courses. In this study, we investigated the viability of using a multimodal Large Language Model"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The project-based constraint successfully elicited a high variety of CT practices. Students demonstrated high proficiency in Modeling and Systems Thinking, with 99% successfully investigating complex systems as a whole. ... the use of CT practices strongly correlated (ρ=0.75) with expert ratings of the overall quality of the CPE.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the customized 20-item rubric based on Weintrop's taxonomy validly and reliably captures computational thinking practices in this specific engineering context without additional validation or inter-rater reliability checks reported.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Computational Physics Essays as capstone projects elicit high proficiency in computational thinking practices among engineering students, with 99% success in investigating complex systems and a 0.75 correlation to expert-rated quality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Computational Physics Essays elicit high variety of computational thinking practices in engineering students, with strong correlation to overall quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2cbf3186173362054b88e76e1d1e5f85db010d3489c648f36eb9205e217b7742"},"source":{"id":"2605.07036","kind":"arxiv","version":2},"verdict":{"id":"00fca34c-f7c8-4e56-9aa6-ffd003660a33","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:13:34.322964Z","strongest_claim":"The project-based constraint successfully elicited a high variety of CT practices. Students demonstrated high proficiency in Modeling and Systems Thinking, with 99% successfully investigating complex systems as a whole. ... the use of CT practices strongly correlated (ρ=0.75) with expert ratings of the overall quality of the CPE.","one_line_summary":"Computational Physics Essays as capstone projects elicit high proficiency in computational thinking practices among engineering students, with 99% success in investigating complex systems and a 0.75 correlation to expert-rated quality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the customized 20-item rubric based on Weintrop's taxonomy validly and reliably captures computational thinking practices in this specific engineering context without additional validation or inter-rater reliability checks reported.","pith_extraction_headline":"Computational Physics Essays elicit high variety of computational thinking practices in engineering students, with strong correlation to overall quality."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07036/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:42:03.420487Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:37:34.702380Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.877026Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:10:32.099571Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b59a684b82d0f304617dd7d74c6a1823163c3c07bdc00a5a51039e259be8041a"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d08fa18170d2296013b2f008be2655090d5756f287888748cfbbd2ac4622633b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}