{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ZNF42TKWLLRYC2C5NOK72V37U","short_pith_number":"pith:5ZNF42TK","schema_version":"1.0","canonical_sha256":"ee5a5e6a6ab2d71c0b42eb5cafeabbfd367d0df57cbfe30c7c7c23018d04b0ee","source":{"kind":"arxiv","id":"2403.01304","version":2},"attestation_state":"computed","paper":{"title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Scarlatos, Andrew Lan, Digory Smith, Simon Woodhead","submitted_at":"2024-03-02T20:25:50Z","abstract_excerpt":"Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other "},"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":"2403.01304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T20:25:50Z","cross_cats_sorted":[],"title_canon_sha256":"4af66b8719dec40a994a72b311d59d6c3b927fd37fa52c37cb60fbfbc79a9dff","abstract_canon_sha256":"2572289df23914aff896ec2749b5d2f7ead453cfd4dc9d48b6febd9b7c98be84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:12.668027Z","signature_b64":"XOVeNnXgy7eDMAl7e0sfHBlhwPbDhNzEcnCGfHe+hJ9oxEBgqnEpPKfkKa2DVrkG4e9sVje4ybz37vEz/3ytCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee5a5e6a6ab2d71c0b42eb5cafeabbfd367d0df57cbfe30c7c7c23018d04b0ee","last_reissued_at":"2026-07-05T09:48:12.667508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:12.667508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Scarlatos, Andrew Lan, Digory Smith, Simon Woodhead","submitted_at":"2024-03-02T20:25:50Z","abstract_excerpt":"Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01304","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/2403.01304/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":"2403.01304","created_at":"2026-07-05T09:48:12.667568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01304v2","created_at":"2026-07-05T09:48:12.667568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01304","created_at":"2026-07-05T09:48:12.667568+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZNF42TKWLLR","created_at":"2026-07-05T09:48:12.667568+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZNF42TKWLLRYC2C","created_at":"2026-07-05T09:48:12.667568+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZNF42TK","created_at":"2026-07-05T09:48:12.667568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27249","citing_title":"Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U","json":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U.json","graph_json":"https://pith.science/api/pith-number/5ZNF42TKWLLRYC2C5NOK72V37U/graph.json","events_json":"https://pith.science/api/pith-number/5ZNF42TKWLLRYC2C5NOK72V37U/events.json","paper":"https://pith.science/paper/5ZNF42TK"},"agent_actions":{"view_html":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U","download_json":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U.json","view_paper":"https://pith.science/paper/5ZNF42TK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01304&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZNF42TKWLLRYC2C5NOK72V37U/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZNF42TKWLLRYC2C5NOK72V37U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U/action/storage_attestation","attest_author":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U/action/author_attestation","sign_citation":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U/action/citation_signature","submit_replication":"https://pith.science/pith/5ZNF42TKWLLRYC2C5NOK72V37U/action/replication_record"}},"created_at":"2026-07-05T09:48:12.667568+00:00","updated_at":"2026-07-05T09:48:12.667568+00:00"}