{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZKD7M2YUH636T2WCHIDQFL7CIR","short_pith_number":"pith:ZKD7M2YU","schema_version":"1.0","canonical_sha256":"ca87f66b143fb7e9eac23a0702afe2447cc0470ac13eb9e80b604ad4701e5930","source":{"kind":"arxiv","id":"2605.25601","version":1},"attestation_state":"computed","paper":{"title":"Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Apartsin, Omri Sason, Yehudit Aperstein","submitted_at":"2026-05-25T08:54:23Z","abstract_excerpt":"Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice by simulating students with known skill components, enabling teachers to rehearse explanations, diagnoses, and instructional responses. For this purpose, however, the central requirement is neither to maximize benchmark accuracy nor to suppress isolated facts, but to control model behavior so that it reflects a specified skill profile. This paper investigates whether prompted language models can be steered to retain "},"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":"2605.25601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T08:54:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5dcfbe256345df373a5a1e926eda28106739643e4ed5f956844f0d736a65b7a","abstract_canon_sha256":"84c97a6ee48014787932ee998204a253cade2de7809ab9b515ce614a5bbf2a4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:45.922498Z","signature_b64":"aiHoHQpHYCrT1EDtl77TtgYJ3AwWa3wrYCs0hEqIRr3JXCoLkTzNZDXCp2zKVwqm/R8UGC89iJ4cnxjMHEv7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca87f66b143fb7e9eac23a0702afe2447cc0470ac13eb9e80b604ad4701e5930","last_reissued_at":"2026-05-26T02:04:45.921784Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:45.921784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward a Benchmark for Controllable Simulation of Imperfect Students with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Apartsin, Omri Sason, Yehudit Aperstein","submitted_at":"2026-05-25T08:54:23Z","abstract_excerpt":"Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice by simulating students with known skill components, enabling teachers to rehearse explanations, diagnoses, and instructional responses. For this purpose, however, the central requirement is neither to maximize benchmark accuracy nor to suppress isolated facts, but to control model behavior so that it reflects a specified skill profile. This paper investigates whether prompted language models can be steered to retain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25601","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/2605.25601/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":"2605.25601","created_at":"2026-05-26T02:04:45.921910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25601v1","created_at":"2026-05-26T02:04:45.921910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25601","created_at":"2026-05-26T02:04:45.921910+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKD7M2YUH636","created_at":"2026-05-26T02:04:45.921910+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKD7M2YUH636T2WC","created_at":"2026-05-26T02:04:45.921910+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKD7M2YU","created_at":"2026-05-26T02:04:45.921910+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/ZKD7M2YUH636T2WCHIDQFL7CIR","json":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR.json","graph_json":"https://pith.science/api/pith-number/ZKD7M2YUH636T2WCHIDQFL7CIR/graph.json","events_json":"https://pith.science/api/pith-number/ZKD7M2YUH636T2WCHIDQFL7CIR/events.json","paper":"https://pith.science/paper/ZKD7M2YU"},"agent_actions":{"view_html":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR","download_json":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR.json","view_paper":"https://pith.science/paper/ZKD7M2YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25601&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKD7M2YUH636T2WCHIDQFL7CIR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKD7M2YUH636T2WCHIDQFL7CIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR/action/storage_attestation","attest_author":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR/action/author_attestation","sign_citation":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR/action/citation_signature","submit_replication":"https://pith.science/pith/ZKD7M2YUH636T2WCHIDQFL7CIR/action/replication_record"}},"created_at":"2026-05-26T02:04:45.921910+00:00","updated_at":"2026-05-26T02:04:45.921910+00:00"}