{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZD2W3HTMSWKDVLFLOX3QUZQY4X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a067a9e4dc4f6068e56711e938457779b112946b82306571b96e85b5ed9ed00","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:25:08Z","title_canon_sha256":"f5785fa21e1926b100046aa893001a0f817a5b5ec8c98631c137f1b740bc0782"},"schema_version":"1.0","source":{"id":"2605.29582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29582","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29582v1","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29582","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZD2W3HTMSWKD","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZD2W3HTMSWKDVLFL","created_at":"2026-05-29T01:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZD2W3HTM","created_at":"2026-05-29T01:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:3759e9a4447c8720539718af0619459a7cc8dae15c21761a10105ff47b8a1f4f","target":"graph","created_at":"2026-05-29T01:05:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.29582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianshu Zhang, Jun Du, Linbo Chen, Pengfei Hu, Qikai Chang, Youhui Guo, Zhenrong Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:25:08Z","title":"PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29582","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:119c35f2a94bf7bcb6f291425d026d08233bd769086c63c748cad42c1d02edc4","target":"record","created_at":"2026-05-29T01:05:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7a067a9e4dc4f6068e56711e938457779b112946b82306571b96e85b5ed9ed00","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:25:08Z","title_canon_sha256":"f5785fa21e1926b100046aa893001a0f817a5b5ec8c98631c137f1b740bc0782"},"schema_version":"1.0","source":{"id":"2605.29582","kind":"arxiv","version":1}},"canonical_sha256":"c8f56d9e6c95943aacab75f70a6618e5d291a789e82a1f77064b7d0ec80b9e5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8f56d9e6c95943aacab75f70a6618e5d291a789e82a1f77064b7d0ec80b9e5b","first_computed_at":"2026-05-29T01:05:48.893747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:48.893747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"leZS4DfovFKDD0/BLi9mxEvB3xVoElS7dssxxl94yM7zsfW+fkkguZ26Y52yVu7BKssbS9ZvjtSubkrrqr4WDA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:48.894504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:119c35f2a94bf7bcb6f291425d026d08233bd769086c63c748cad42c1d02edc4","sha256:3759e9a4447c8720539718af0619459a7cc8dae15c21761a10105ff47b8a1f4f"],"state_sha256":"551199175bf6c938d589f3f46b03bb89cadb7361747079dd6b748d7859d65ad5"}