{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ODU5KEKARWHY653KS3VWGXID74","short_pith_number":"pith:ODU5KEKA","schema_version":"1.0","canonical_sha256":"70e9d511408d8f8f776a96eb635d03ff29d0c13b89c90dc5f4658efa72f44470","source":{"kind":"arxiv","id":"2406.05603","version":1},"attestation_state":"computed","paper":{"title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Bj\\\"orn Hartmann, J.D. Zamfirescu-Pereira, John DeNero, Laryn Qi, Narges Norouzi, Taehan Kim","submitted_at":"2024-06-09T00:58:39Z","abstract_excerpt":"We evaluate an automatic hint generator for CS1 programming assignments powered by GPT-4, a large language model. This system provides natural language guidance about how students can improve their incorrect solutions to short programming exercises. A hint can be requested each time a student fails a test case. Our evaluation addresses three Research Questions:\n  RQ1: Do the hints help students improve their code? RQ2: How effectively do the hints capture problems in student code? RQ3: Are the issues that students resolve the same as the issues addressed in the hints?\n  To address these resear"},"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":"2406.05603","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2024-06-09T00:58:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d22943858e222481451e6decf70bf0176b7f9ae76afaa16058fcce796b82183c","abstract_canon_sha256":"6ab10c6975646f8de633296a9a48ae2e7b3b1d21c4572f09d1f941fef78ee200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:30.469582Z","signature_b64":"dDlroO+FSI1xCHWeNWus629Y137BNa3xd7cROnCxvo0WCKZEdvO/fnrNuirCb5i9CgY6ZM9DYWgMX9EIWhfKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70e9d511408d8f8f776a96eb635d03ff29d0c13b89c90dc5f4658efa72f44470","last_reissued_at":"2026-07-05T08:29:30.469134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:30.469134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Knowledge-Component-Based Methodology for Evaluating AI Assistants","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Bj\\\"orn Hartmann, J.D. Zamfirescu-Pereira, John DeNero, Laryn Qi, Narges Norouzi, Taehan Kim","submitted_at":"2024-06-09T00:58:39Z","abstract_excerpt":"We evaluate an automatic hint generator for CS1 programming assignments powered by GPT-4, a large language model. This system provides natural language guidance about how students can improve their incorrect solutions to short programming exercises. A hint can be requested each time a student fails a test case. Our evaluation addresses three Research Questions:\n  RQ1: Do the hints help students improve their code? RQ2: How effectively do the hints capture problems in student code? RQ3: Are the issues that students resolve the same as the issues addressed in the hints?\n  To address these resear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05603","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/2406.05603/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":"2406.05603","created_at":"2026-07-05T08:29:30.469200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05603v1","created_at":"2026-07-05T08:29:30.469200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05603","created_at":"2026-07-05T08:29:30.469200+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODU5KEKARWHY","created_at":"2026-07-05T08:29:30.469200+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODU5KEKARWHY653K","created_at":"2026-07-05T08:29:30.469200+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODU5KEKA","created_at":"2026-07-05T08:29:30.469200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12594","citing_title":"A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications","ref_index":219,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74","json":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74.json","graph_json":"https://pith.science/api/pith-number/ODU5KEKARWHY653KS3VWGXID74/graph.json","events_json":"https://pith.science/api/pith-number/ODU5KEKARWHY653KS3VWGXID74/events.json","paper":"https://pith.science/paper/ODU5KEKA"},"agent_actions":{"view_html":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74","download_json":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74.json","view_paper":"https://pith.science/paper/ODU5KEKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05603&json=true","fetch_graph":"https://pith.science/api/pith-number/ODU5KEKARWHY653KS3VWGXID74/graph.json","fetch_events":"https://pith.science/api/pith-number/ODU5KEKARWHY653KS3VWGXID74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74/action/storage_attestation","attest_author":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74/action/author_attestation","sign_citation":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74/action/citation_signature","submit_replication":"https://pith.science/pith/ODU5KEKARWHY653KS3VWGXID74/action/replication_record"}},"created_at":"2026-07-05T08:29:30.469200+00:00","updated_at":"2026-07-05T08:29:30.469200+00:00"}