{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CH5LZXLOL4RM7TNTDAXXIAHV4F","short_pith_number":"pith:CH5LZXLO","schema_version":"1.0","canonical_sha256":"11fabcdd6e5f22cfcdb3182f7400f5e166345a9e8f8e0718967dc4f3656f6c36","source":{"kind":"arxiv","id":"2407.09136","version":1},"attestation_state":"computed","paper":{"title":"Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Jakub Macina, Manu Kapur, Mrinmaya Sachan, Nico Daheim","submitted_at":"2024-07-12T10:11:40Z","abstract_excerpt":"Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. A promising approach towards this means is to build dialog tutoring models that scaffold students' problem-solving. However, even though existing LLMs perform well in solving reasoning questions, they struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions and show how grounding to such verificati"},"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":"2407.09136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T10:11:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"30ce7c4f12814a98855edd46669a41a384f9fb7cd387a65ba48fcd475f62bf46","abstract_canon_sha256":"0bffc89505c2ec36d15d51b2e3b137cb325b55b02c5e7e1dd42506e839f08fd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:15.308417Z","signature_b64":"Jh56URq9FATQMDu9H+545uVxXmsY6sqZ3UWujYeGKm8X41T4EFdbQl0DMhxfmjalg5sICyqtMxe8QUe45hxwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11fabcdd6e5f22cfcdb3182f7400f5e166345a9e8f8e0718967dc4f3656f6c36","last_reissued_at":"2026-07-05T08:43:15.307973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:15.307973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Jakub Macina, Manu Kapur, Mrinmaya Sachan, Nico Daheim","submitted_at":"2024-07-12T10:11:40Z","abstract_excerpt":"Large language models (LLMs) present an opportunity to scale high-quality personalized education to all. A promising approach towards this means is to build dialog tutoring models that scaffold students' problem-solving. However, even though existing LLMs perform well in solving reasoning questions, they struggle to precisely detect student's errors and tailor their feedback to these errors. Inspired by real-world teaching practice where teachers identify student errors and customize their response based on them, we focus on verifying student solutions and show how grounding to such verificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09136","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/2407.09136/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":"2407.09136","created_at":"2026-07-05T08:43:15.308040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09136v1","created_at":"2026-07-05T08:43:15.308040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09136","created_at":"2026-07-05T08:43:15.308040+00:00"},{"alias_kind":"pith_short_12","alias_value":"CH5LZXLOL4RM","created_at":"2026-07-05T08:43:15.308040+00:00"},{"alias_kind":"pith_short_16","alias_value":"CH5LZXLOL4RM7TNT","created_at":"2026-07-05T08:43:15.308040+00:00"},{"alias_kind":"pith_short_8","alias_value":"CH5LZXLO","created_at":"2026-07-05T08:43:15.308040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18257","citing_title":"From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F","json":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F.json","graph_json":"https://pith.science/api/pith-number/CH5LZXLOL4RM7TNTDAXXIAHV4F/graph.json","events_json":"https://pith.science/api/pith-number/CH5LZXLOL4RM7TNTDAXXIAHV4F/events.json","paper":"https://pith.science/paper/CH5LZXLO"},"agent_actions":{"view_html":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F","download_json":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F.json","view_paper":"https://pith.science/paper/CH5LZXLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09136&json=true","fetch_graph":"https://pith.science/api/pith-number/CH5LZXLOL4RM7TNTDAXXIAHV4F/graph.json","fetch_events":"https://pith.science/api/pith-number/CH5LZXLOL4RM7TNTDAXXIAHV4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F/action/storage_attestation","attest_author":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F/action/author_attestation","sign_citation":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F/action/citation_signature","submit_replication":"https://pith.science/pith/CH5LZXLOL4RM7TNTDAXXIAHV4F/action/replication_record"}},"created_at":"2026-07-05T08:43:15.308040+00:00","updated_at":"2026-07-05T08:43:15.308040+00:00"}