{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBKUF3GHUTB7WGEPDGX2PVVGNN","short_pith_number":"pith:RBKUF3GH","schema_version":"1.0","canonical_sha256":"885542ecc7a4c3fb188f19afa7d6a66b4ba3f19a0abea073d28a579ac4ba999b","source":{"kind":"arxiv","id":"2410.02110","version":2},"attestation_state":"computed","paper":{"title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Davies, Amogh Mannekote, Jina Kang, Kristy Elizabeth Boyer","submitted_at":"2024-10-03T00:25:40Z","abstract_excerpt":"Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human behavior, such approaches have not gone beyond rudimentary proof-of-concept stages due to key limitations. First, LLMs are highly sensitive to minor prompt variations, raising doubts about their ability to generalize to new scenarios without extensive prompt engineering. Moreover, apparently successful outcomes can often be unreliable, either because domain expe"},"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":"2410.02110","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-03T00:25:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b8e50b736a92a2cc461baada5981760b3dcf8a9d7fe1f390529f55b8c26244b8","abstract_canon_sha256":"fd55801f7d934cce4d9609b8a79d6469a0f6d9d7ce81437e6dfad16c6ef933a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:32.633082Z","signature_b64":"VYfiDT9QNHCO2Svl9VBrB9ajBadfmmbDSn6hfooHICNvnqMvT9eddu+jEh3oUiCAsS7UzCZ2NUZ5KN5drZZUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"885542ecc7a4c3fb188f19afa7d6a66b4ba3f19a0abea073d28a579ac4ba999b","last_reissued_at":"2026-07-05T09:19:32.632595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:32.632595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Davies, Amogh Mannekote, Jina Kang, Kristy Elizabeth Boyer","submitted_at":"2024-10-03T00:25:40Z","abstract_excerpt":"Simulating learner actions helps stress-test open-ended interactive learning environments and prototype new adaptations before deployment. While recent studies show the promise of using large language models (LLMs) for simulating human behavior, such approaches have not gone beyond rudimentary proof-of-concept stages due to key limitations. First, LLMs are highly sensitive to minor prompt variations, raising doubts about their ability to generalize to new scenarios without extensive prompt engineering. Moreover, apparently successful outcomes can often be unreliable, either because domain expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02110","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/2410.02110/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":"2410.02110","created_at":"2026-07-05T09:19:32.632651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02110v2","created_at":"2026-07-05T09:19:32.632651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02110","created_at":"2026-07-05T09:19:32.632651+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBKUF3GHUTB7","created_at":"2026-07-05T09:19:32.632651+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBKUF3GHUTB7WGEP","created_at":"2026-07-05T09:19:32.632651+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBKUF3GH","created_at":"2026-07-05T09:19:32.632651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02348","citing_title":"Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solving","ref_index":1194,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN","json":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN.json","graph_json":"https://pith.science/api/pith-number/RBKUF3GHUTB7WGEPDGX2PVVGNN/graph.json","events_json":"https://pith.science/api/pith-number/RBKUF3GHUTB7WGEPDGX2PVVGNN/events.json","paper":"https://pith.science/paper/RBKUF3GH"},"agent_actions":{"view_html":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN","download_json":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN.json","view_paper":"https://pith.science/paper/RBKUF3GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02110&json=true","fetch_graph":"https://pith.science/api/pith-number/RBKUF3GHUTB7WGEPDGX2PVVGNN/graph.json","fetch_events":"https://pith.science/api/pith-number/RBKUF3GHUTB7WGEPDGX2PVVGNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN/action/storage_attestation","attest_author":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN/action/author_attestation","sign_citation":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN/action/citation_signature","submit_replication":"https://pith.science/pith/RBKUF3GHUTB7WGEPDGX2PVVGNN/action/replication_record"}},"created_at":"2026-07-05T09:19:32.632651+00:00","updated_at":"2026-07-05T09:19:32.632651+00:00"}