{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQZWDOCPQP5XYSPVJZOPURKUM7","short_pith_number":"pith:CQZWDOCP","schema_version":"1.0","canonical_sha256":"143361b84f83fb7c49f54e5cfa455467fdeab03baab6253054e5d679cb8cd61f","source":{"kind":"arxiv","id":"2605.06307","version":2},"attestation_state":"computed","paper":{"title":"LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM-generated ADHD student personas hold self-reported traits steady over time, but their observed behaviors drift in unscripted conversations unless interactions use explicit scripted task prompts.","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jana Gonnermann-M\\\"uller, Jennifer Haase, Nicolas Leins, Sebastian Pokutta, Thomas Kosch","submitted_at":"2026-05-07T14:09:31Z","abstract_excerpt":"Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test this prerequisite using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across two experiments testing four clinically-grounded ADHD persona conditions, five LLMs, and three prompt designs, we quantify between-conversation stability (N=4,968) and within-conversation stability (N=3,952 across 9 turns"},"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":"2605.06307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-07T14:09:31Z","cross_cats_sorted":[],"title_canon_sha256":"f735fcf1c7584a9c0cb2d05cc47a257b4eab13bc1cf892216bf89aa5380c243f","abstract_canon_sha256":"2891872d41236c1fe299396918a4d16bbb47fbf7cf5356e90cc23e8acfa345f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:22.172141Z","signature_b64":"xziWVsaqetq0OW/QdXUk6lHZAi/22/jwrefEAsij6H8CAHrhsDTL6VGMo4GX9UQfJsce6PUxm9ows+gxze/kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"143361b84f83fb7c49f54e5cfa455467fdeab03baab6253054e5d679cb8cd61f","last_reissued_at":"2026-05-25T02:01:22.171530Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:22.171530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM-generated ADHD student personas hold self-reported traits steady over time, but their observed behaviors drift in unscripted conversations unless interactions use explicit scripted task prompts.","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jana Gonnermann-M\\\"uller, Jennifer Haase, Nicolas Leins, Sebastian Pokutta, Thomas Kosch","submitted_at":"2026-05-07T14:09:31Z","abstract_excerpt":"Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test this prerequisite using a dual-assessment framework measuring self-reported characteristics and observer-rated behavioral expressions. Across two experiments testing four clinically-grounded ADHD persona conditions, five LLMs, and three prompt designs, we quantify between-conversation stability (N=4,968) and within-conversation stability (N=3,952 across 9 turns"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Self-reported characteristics remain stable for high intensities, constituting a necessary prerequisite for valid behavioral simulation. Observer-rated behavioral expression reveals selective instability: within-conversation drift occurs in unscripted dialog for high and moderate ADHD personas. Scripted interactions with explicit task prompts eliminate this drift entirely.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That observer ratings of behavioral expressions accurately and unbiasedly capture persona alignment without influence from rater expectations or LLM generation artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLM-simulated ADHD student personas show stable self-reported traits but behavioral drift in unscripted interactions that explicit task prompts fully eliminate.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM-generated ADHD student personas hold self-reported traits steady over time, but their observed behaviors drift in unscripted conversations unless interactions use explicit scripted task prompts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"61db56307363f9f4777c7fb6ba6eb4173ac087adf2feede75492d4fbb5852569"},"source":{"id":"2605.06307","kind":"arxiv","version":2},"verdict":{"id":"ce039763-a2e3-41bf-a1c5-2b25fa02ce1e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T07:08:42.923588Z","strongest_claim":"Self-reported characteristics remain stable for high intensities, constituting a necessary prerequisite for valid behavioral simulation. Observer-rated behavioral expression reveals selective instability: within-conversation drift occurs in unscripted dialog for high and moderate ADHD personas. Scripted interactions with explicit task prompts eliminate this drift entirely.","one_line_summary":"LLM-simulated ADHD student personas show stable self-reported traits but behavioral drift in unscripted interactions that explicit task prompts fully eliminate.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That observer ratings of behavioral expressions accurately and unbiasedly capture persona alignment without influence from rater expectations or LLM generation artifacts.","pith_extraction_headline":"LLM-generated ADHD student personas hold self-reported traits steady over time, but their observed behaviors drift in unscripted conversations unless interactions use explicit scripted task prompts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06307/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T12:42:04.082406Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T08:33:45.939342Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:19.515524Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:49:35.181749Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c3cd2e795d7b98021cbb50621ac433aa422ae6862d1e20e89a27e42179723bcf"},"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":"2605.06307","created_at":"2026-05-25T02:01:22.171621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06307v2","created_at":"2026-05-25T02:01:22.171621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06307","created_at":"2026-05-25T02:01:22.171621+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQZWDOCPQP5X","created_at":"2026-05-25T02:01:22.171621+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQZWDOCPQP5XYSPV","created_at":"2026-05-25T02:01:22.171621+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQZWDOCP","created_at":"2026-05-25T02:01:22.171621+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/CQZWDOCPQP5XYSPVJZOPURKUM7","json":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7.json","graph_json":"https://pith.science/api/pith-number/CQZWDOCPQP5XYSPVJZOPURKUM7/graph.json","events_json":"https://pith.science/api/pith-number/CQZWDOCPQP5XYSPVJZOPURKUM7/events.json","paper":"https://pith.science/paper/CQZWDOCP"},"agent_actions":{"view_html":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7","download_json":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7.json","view_paper":"https://pith.science/paper/CQZWDOCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06307&json=true","fetch_graph":"https://pith.science/api/pith-number/CQZWDOCPQP5XYSPVJZOPURKUM7/graph.json","fetch_events":"https://pith.science/api/pith-number/CQZWDOCPQP5XYSPVJZOPURKUM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7/action/storage_attestation","attest_author":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7/action/author_attestation","sign_citation":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7/action/citation_signature","submit_replication":"https://pith.science/pith/CQZWDOCPQP5XYSPVJZOPURKUM7/action/replication_record"}},"created_at":"2026-05-25T02:01:22.171621+00:00","updated_at":"2026-05-25T02:01:22.171621+00:00"}