{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZD2W3HTMSWKDVLFLOX3QUZQY4X","short_pith_number":"pith:ZD2W3HTM","schema_version":"1.0","canonical_sha256":"c8f56d9e6c95943aacab75f70a6618e5d291a789e82a1f77064b7d0ec80b9e5b","source":{"kind":"arxiv","id":"2605.29582","version":1},"attestation_state":"computed","paper":{"title":"PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianshu Zhang, Jun Du, Linbo Chen, Pengfei Hu, Qikai Chang, Youhui Guo, Zhenrong Zhang","submitted_at":"2026-05-28T08:25:08Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise as educational tutors, yet effective tutoring requires more than solving problems: it must provide progressive Socratic guidance and balance multiple pedagogical objectives across multi-turn interactions. However, training such tutors remains challenging due to limited-fidelity and weakly controllable student simulation, under-specified pedagogical reward modeling, and unstable multi-objective optimization. To overcome these limitations, we propose PEARL, a pedagogically aligned reinforcement learning framework for training Socratic tutoring agen"},"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":"2605.29582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:25:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f5785fa21e1926b100046aa893001a0f817a5b5ec8c98631c137f1b740bc0782","abstract_canon_sha256":"7a067a9e4dc4f6068e56711e938457779b112946b82306571b96e85b5ed9ed00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:48.894504Z","signature_b64":"leZS4DfovFKDD0/BLi9mxEvB3xVoElS7dssxxl94yM7zsfW+fkkguZ26Y52yVu7BKssbS9ZvjtSubkrrqr4WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8f56d9e6c95943aacab75f70a6618e5d291a789e82a1f77064b7d0ec80b9e5b","last_reissued_at":"2026-05-29T01:05:48.893747Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:48.893747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianshu Zhang, Jun Du, Linbo Chen, Pengfei Hu, Qikai Chang, Youhui Guo, Zhenrong Zhang","submitted_at":"2026-05-28T08:25:08Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise as educational tutors, yet effective tutoring requires more than solving problems: it must provide progressive Socratic guidance and balance multiple pedagogical objectives across multi-turn interactions. However, training such tutors remains challenging due to limited-fidelity and weakly controllable student simulation, under-specified pedagogical reward modeling, and unstable multi-objective optimization. To overcome these limitations, we propose PEARL, a pedagogically aligned reinforcement learning framework for training Socratic tutoring agen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29582","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/2605.29582/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":"2605.29582","created_at":"2026-05-29T01:05:48.893885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29582v1","created_at":"2026-05-29T01:05:48.893885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29582","created_at":"2026-05-29T01:05:48.893885+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZD2W3HTMSWKD","created_at":"2026-05-29T01:05:48.893885+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZD2W3HTMSWKDVLFL","created_at":"2026-05-29T01:05:48.893885+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZD2W3HTM","created_at":"2026-05-29T01:05:48.893885+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/ZD2W3HTMSWKDVLFLOX3QUZQY4X","json":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X.json","graph_json":"https://pith.science/api/pith-number/ZD2W3HTMSWKDVLFLOX3QUZQY4X/graph.json","events_json":"https://pith.science/api/pith-number/ZD2W3HTMSWKDVLFLOX3QUZQY4X/events.json","paper":"https://pith.science/paper/ZD2W3HTM"},"agent_actions":{"view_html":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X","download_json":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X.json","view_paper":"https://pith.science/paper/ZD2W3HTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29582&json=true","fetch_graph":"https://pith.science/api/pith-number/ZD2W3HTMSWKDVLFLOX3QUZQY4X/graph.json","fetch_events":"https://pith.science/api/pith-number/ZD2W3HTMSWKDVLFLOX3QUZQY4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X/action/storage_attestation","attest_author":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X/action/author_attestation","sign_citation":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X/action/citation_signature","submit_replication":"https://pith.science/pith/ZD2W3HTMSWKDVLFLOX3QUZQY4X/action/replication_record"}},"created_at":"2026-05-29T01:05:48.893885+00:00","updated_at":"2026-05-29T01:05:48.893885+00:00"}