{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IBOLQAH562KEYHOTALC3BKXLAH","short_pith_number":"pith:IBOLQAH5","schema_version":"1.0","canonical_sha256":"405cb800fdf6944c1dd302c5b0aaeb01d96bbd0ffa985da55426b685ef0eb8c5","source":{"kind":"arxiv","id":"2606.21502","version":1},"attestation_state":"computed","paper":{"title":"Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Kochmar, Kseniia Petukhova, Tien Dat Nguyen","submitted_at":"2026-06-19T14:53:55Z","abstract_excerpt":"Large language models have strong potential for use in intelligent tutoring systems, but they often fail to follow effective pedagogical strategies, such as guiding students without revealing final answers. We study the application of a two-stage alignment pipeline for math mistake remediation, combining supervised fine-tuning on tutoring dialogs with Direct Preference Optimization on synthetic preference pairs. We construct a dataset that integrates existing tutoring corpora with synthetic data generated along pedagogical dimensions, such as scaffolding and factuality, and study different inp"},"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":"2606.21502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T14:53:55Z","cross_cats_sorted":[],"title_canon_sha256":"8cc119e539d837bb894c16b62d340b6bf49c61d76865761fda684f0084869556","abstract_canon_sha256":"deb02efff96d7239cd4296730ca064a52c00da004de2a20ebc2745dfd0058594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:12.692246Z","signature_b64":"9+FCtx239416hSudl3kWY7heyjA0j2IboPOEiwzblJYTNiGcXKPbNXZrTqwaDIYB7gkRdhpmrWjvu6utfOq+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405cb800fdf6944c1dd302c5b0aaeb01d96bbd0ffa985da55426b685ef0eb8c5","last_reissued_at":"2026-06-23T01:13:12.691790Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:12.691790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Pedagogically Aligned LLM Tutors for Math Mistake Remediation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Kochmar, Kseniia Petukhova, Tien Dat Nguyen","submitted_at":"2026-06-19T14:53:55Z","abstract_excerpt":"Large language models have strong potential for use in intelligent tutoring systems, but they often fail to follow effective pedagogical strategies, such as guiding students without revealing final answers. We study the application of a two-stage alignment pipeline for math mistake remediation, combining supervised fine-tuning on tutoring dialogs with Direct Preference Optimization on synthetic preference pairs. We construct a dataset that integrates existing tutoring corpora with synthetic data generated along pedagogical dimensions, such as scaffolding and factuality, and study different inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21502","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/2606.21502/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":"2606.21502","created_at":"2026-06-23T01:13:12.691865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21502v1","created_at":"2026-06-23T01:13:12.691865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21502","created_at":"2026-06-23T01:13:12.691865+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBOLQAH562KE","created_at":"2026-06-23T01:13:12.691865+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBOLQAH562KEYHOT","created_at":"2026-06-23T01:13:12.691865+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBOLQAH5","created_at":"2026-06-23T01:13:12.691865+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/IBOLQAH562KEYHOTALC3BKXLAH","json":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH.json","graph_json":"https://pith.science/api/pith-number/IBOLQAH562KEYHOTALC3BKXLAH/graph.json","events_json":"https://pith.science/api/pith-number/IBOLQAH562KEYHOTALC3BKXLAH/events.json","paper":"https://pith.science/paper/IBOLQAH5"},"agent_actions":{"view_html":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH","download_json":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH.json","view_paper":"https://pith.science/paper/IBOLQAH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21502&json=true","fetch_graph":"https://pith.science/api/pith-number/IBOLQAH562KEYHOTALC3BKXLAH/graph.json","fetch_events":"https://pith.science/api/pith-number/IBOLQAH562KEYHOTALC3BKXLAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH/action/storage_attestation","attest_author":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH/action/author_attestation","sign_citation":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH/action/citation_signature","submit_replication":"https://pith.science/pith/IBOLQAH562KEYHOTALC3BKXLAH/action/replication_record"}},"created_at":"2026-06-23T01:13:12.691865+00:00","updated_at":"2026-06-23T01:13:12.691865+00:00"}