{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLJOXTZV5C5DCF3PDR3FA3WVUF","short_pith_number":"pith:NLJOXTZV","schema_version":"1.0","canonical_sha256":"6ad2ebcf35e8ba31176f1c76506ed5a14d19a275144b67aed03ec7042c0743df","source":{"kind":"arxiv","id":"2606.23629","version":1},"attestation_state":"computed","paper":{"title":"Why Machines Misread Pedagogical Quality: Human-Machine Alignment in LLM-Based Pretest Question Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Mahir Akgun, Pei-Yu Tseng, Peng Liu","submitted_at":"2026-06-22T17:22:22Z","abstract_excerpt":"Designing effective pretest questions is challenging at scale: high-quality questions require careful calibration of openness, cognitive depth, and alignment with learning objectives, yet generating and evaluating them manually is time-consuming. We present an AI-assisted workflow for pretest question development that combines automated generation, rubric-based evaluation, and iterative selection. Because the workflow relies on machine evaluation to filter questions at scale, we investigate the alignment between human and machine judgments across a 2x2 design varying rubric operationalization "},"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":"2606.23629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-06-22T17:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"f0c2b6567b490b9d3875450e734d97a6e51a810c4eb4015d0a7d034da7afb909","abstract_canon_sha256":"cb2a56b8a6e8b251e48c7a4a76b87d4d6514e9ab6b6c6edb3e5fc3690f094396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:32.782184Z","signature_b64":"3H5XHMXsFxIBneygBLT5z0QwEpqAjiA4xjf/Ql3zR/zuuq8udvDOp+JfYOltjnrO68XxZdilnJxKuVZ8rUmsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad2ebcf35e8ba31176f1c76506ed5a14d19a275144b67aed03ec7042c0743df","last_reissued_at":"2026-06-23T03:14:32.781803Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:32.781803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why Machines Misread Pedagogical Quality: Human-Machine Alignment in LLM-Based Pretest Question Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Mahir Akgun, Pei-Yu Tseng, Peng Liu","submitted_at":"2026-06-22T17:22:22Z","abstract_excerpt":"Designing effective pretest questions is challenging at scale: high-quality questions require careful calibration of openness, cognitive depth, and alignment with learning objectives, yet generating and evaluating them manually is time-consuming. We present an AI-assisted workflow for pretest question development that combines automated generation, rubric-based evaluation, and iterative selection. Because the workflow relies on machine evaluation to filter questions at scale, we investigate the alignment between human and machine judgments across a 2x2 design varying rubric operationalization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23629","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/2606.23629/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":"2606.23629","created_at":"2026-06-23T03:14:32.781867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23629v1","created_at":"2026-06-23T03:14:32.781867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23629","created_at":"2026-06-23T03:14:32.781867+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLJOXTZV5C5D","created_at":"2026-06-23T03:14:32.781867+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLJOXTZV5C5DCF3P","created_at":"2026-06-23T03:14:32.781867+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLJOXTZV","created_at":"2026-06-23T03:14:32.781867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF","json":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF.json","graph_json":"https://pith.science/api/pith-number/NLJOXTZV5C5DCF3PDR3FA3WVUF/graph.json","events_json":"https://pith.science/api/pith-number/NLJOXTZV5C5DCF3PDR3FA3WVUF/events.json","paper":"https://pith.science/paper/NLJOXTZV"},"agent_actions":{"view_html":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF","download_json":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF.json","view_paper":"https://pith.science/paper/NLJOXTZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23629&json=true","fetch_graph":"https://pith.science/api/pith-number/NLJOXTZV5C5DCF3PDR3FA3WVUF/graph.json","fetch_events":"https://pith.science/api/pith-number/NLJOXTZV5C5DCF3PDR3FA3WVUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF/action/storage_attestation","attest_author":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF/action/author_attestation","sign_citation":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF/action/citation_signature","submit_replication":"https://pith.science/pith/NLJOXTZV5C5DCF3PDR3FA3WVUF/action/replication_record"}},"created_at":"2026-06-23T03:14:32.781867+00:00","updated_at":"2026-06-23T03:14:32.781867+00:00"}