{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MUPZHHOXIGKJEHIIMGWCHBE2TM","short_pith_number":"pith:MUPZHHOX","schema_version":"1.0","canonical_sha256":"651f939dd74194921d0861ac23849a9b1476376e934b030620b1c3520139aaf3","source":{"kind":"arxiv","id":"2605.16207","version":1},"attestation_state":"computed","paper":{"title":"Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Sam Gilson, Sutapa Dey Tithi, Tahreem Yasir, Tiffany Barnes, Wenbo Li, Xiaoyi Tian","submitted_at":"2026-05-15T17:24:42Z","abstract_excerpt":"Effective tutoring requires distinguishing optimal, valid but suboptimal, and incorrect student solutions, a distinction central to intelligent tutoring systems (ITS) but untested for LLM-based tutors. As LLMs are increasingly explored as conversational complements to ITS, evaluating their diagnostic precision is essential. We present a benchmark of seven LLM feedback agents in propositional logic using knowledge-graph-derived ground truth across 10,836 solution--feedback pairs and three feedback conditions. Models achieved near-ceiling performance on optimal steps but systematically over-reje"},"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":"2605.16207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T17:24:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"60397d4f2d71777c302abf5b9a2184863bc9e0bf5f15df4e25520068c822aa27","abstract_canon_sha256":"ebab76c98d13889dec3c7eadad3ad9327cda6fce3c0b07ee342c09c1409223a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:58.070510Z","signature_b64":"wpzy/R0okoAKpxs+34JJphYlzfZnk4ZjYgr+8zfd0stK1Fh+4PUSvM6AuZTAsH3BZ18DZEghx2oRCmi5EOglDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"651f939dd74194921d0861ac23849a9b1476376e934b030620b1c3520139aaf3","last_reissued_at":"2026-05-20T00:01:58.069897Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:58.069897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Sam Gilson, Sutapa Dey Tithi, Tahreem Yasir, Tiffany Barnes, Wenbo Li, Xiaoyi Tian","submitted_at":"2026-05-15T17:24:42Z","abstract_excerpt":"Effective tutoring requires distinguishing optimal, valid but suboptimal, and incorrect student solutions, a distinction central to intelligent tutoring systems (ITS) but untested for LLM-based tutors. As LLMs are increasingly explored as conversational complements to ITS, evaluating their diagnostic precision is essential. We present a benchmark of seven LLM feedback agents in propositional logic using knowledge-graph-derived ground truth across 10,836 solution--feedback pairs and three feedback conditions. Models achieved near-ceiling performance on optimal steps but systematically over-reje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16207","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/2605.16207/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"shingle_duplication","ran_at":"2026-05-19T17:49:44.678500Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T17:49:44.168543Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:24.838862Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:35.024350Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T17:22:07.148200Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.397867Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b82210afaed38def4606fa673913a8d8c1ddb7622192b5e5b9a15078f625f1f2"},"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":"2605.16207","created_at":"2026-05-20T00:01:58.070014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16207v1","created_at":"2026-05-20T00:01:58.070014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16207","created_at":"2026-05-20T00:01:58.070014+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUPZHHOXIGKJ","created_at":"2026-05-20T00:01:58.070014+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUPZHHOXIGKJEHII","created_at":"2026-05-20T00:01:58.070014+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUPZHHOX","created_at":"2026-05-20T00:01:58.070014+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/MUPZHHOXIGKJEHIIMGWCHBE2TM","json":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM.json","graph_json":"https://pith.science/api/pith-number/MUPZHHOXIGKJEHIIMGWCHBE2TM/graph.json","events_json":"https://pith.science/api/pith-number/MUPZHHOXIGKJEHIIMGWCHBE2TM/events.json","paper":"https://pith.science/paper/MUPZHHOX"},"agent_actions":{"view_html":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM","download_json":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM.json","view_paper":"https://pith.science/paper/MUPZHHOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16207&json=true","fetch_graph":"https://pith.science/api/pith-number/MUPZHHOXIGKJEHIIMGWCHBE2TM/graph.json","fetch_events":"https://pith.science/api/pith-number/MUPZHHOXIGKJEHIIMGWCHBE2TM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM/action/storage_attestation","attest_author":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM/action/author_attestation","sign_citation":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM/action/citation_signature","submit_replication":"https://pith.science/pith/MUPZHHOXIGKJEHIIMGWCHBE2TM/action/replication_record"}},"created_at":"2026-05-20T00:01:58.070014+00:00","updated_at":"2026-05-20T00:01:58.070014+00:00"}