{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y6ZCZXS7KLL4FKKUMUYEBZM3VR","short_pith_number":"pith:Y6ZCZXS7","schema_version":"1.0","canonical_sha256":"c7b22cde5f52d7c2a954653040e59bac528ff5ae8cb587da68fe9434fd6e2565","source":{"kind":"arxiv","id":"2507.12674","version":2},"attestation_state":"computed","paper":{"title":"ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CY","authors_text":"Gireeja Ranade, Joseph E. Gonzalez, Mihran Miroyan, Narges Norouzi, Rose Niousha","submitted_at":"2025-07-16T23:12:14Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students - imperfect, iterative, and stylistically diverse? We present ParaStudent, a systematic study of LLM-based \"student-like\" code generation in an introductory programming course setting. Using a dataset of timestamped student submissions across multiple semesters, we design low- and high-resolution experiments to model student progress and evaluate code outputs along semantic, functional, and stylistic dimensions. Our results show that fine-tuning significan"},"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":"2507.12674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-07-16T23:12:14Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"96c7b26114d5e40b67b75e582d7ca8a684ae54844ea116a8b132afc75d305bce","abstract_canon_sha256":"01e7f3020113e6d0d59683f098d8491a4855e512a5bbd1e6cec15a90ffbf9864"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:15.317061Z","signature_b64":"2Kv+D2tlhhTKQc0EzQy4Msal6SaRoVdVF0QhUhE7z57kgI5RG4vUwj2NoO69i5LxqpjhAx3dUNBJ8qei7NAgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7b22cde5f52d7c2a954653040e59bac528ff5ae8cb587da68fe9434fd6e2565","last_reissued_at":"2026-07-05T11:39:15.316538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:15.316538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParaStudent: Generating and Evaluating Realistic Student Code by Teaching LLMs to Struggle","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CY","authors_text":"Gireeja Ranade, Joseph E. Gonzalez, Mihran Miroyan, Narges Norouzi, Rose Niousha","submitted_at":"2025-07-16T23:12:14Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong performance on programming tasks, but can they generate student-like code like real students - imperfect, iterative, and stylistically diverse? We present ParaStudent, a systematic study of LLM-based \"student-like\" code generation in an introductory programming course setting. Using a dataset of timestamped student submissions across multiple semesters, we design low- and high-resolution experiments to model student progress and evaluate code outputs along semantic, functional, and stylistic dimensions. Our results show that fine-tuning significan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12674","kind":"arxiv","version":2},"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/2507.12674/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":"2507.12674","created_at":"2026-07-05T11:39:15.316600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12674v2","created_at":"2026-07-05T11:39:15.316600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12674","created_at":"2026-07-05T11:39:15.316600+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6ZCZXS7KLL4","created_at":"2026-07-05T11:39:15.316600+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6ZCZXS7KLL4FKKU","created_at":"2026-07-05T11:39:15.316600+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6ZCZXS7","created_at":"2026-07-05T11:39:15.316600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18709","citing_title":"LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26969","citing_title":"Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR","json":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR.json","graph_json":"https://pith.science/api/pith-number/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/graph.json","events_json":"https://pith.science/api/pith-number/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/events.json","paper":"https://pith.science/paper/Y6ZCZXS7"},"agent_actions":{"view_html":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR","download_json":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR.json","view_paper":"https://pith.science/paper/Y6ZCZXS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12674&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/action/storage_attestation","attest_author":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/action/author_attestation","sign_citation":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/action/citation_signature","submit_replication":"https://pith.science/pith/Y6ZCZXS7KLL4FKKUMUYEBZM3VR/action/replication_record"}},"created_at":"2026-07-05T11:39:15.316600+00:00","updated_at":"2026-07-05T11:39:15.316600+00:00"}