{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7DIL3M67OQEWMCBI6UA4JN3AKG","short_pith_number":"pith:7DIL3M67","schema_version":"1.0","canonical_sha256":"f8d0bdb3df7409660828f501c4b76051936a053bf25431a4adb3c2326913cfba","source":{"kind":"arxiv","id":"2606.10403","version":1},"attestation_state":"computed","paper":{"title":"KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Geewook Kim, Kee-Eung Kim, Sanghee Park","submitted_at":"2026-06-09T04:25:44Z","abstract_excerpt":"Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together the"},"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":"2606.10403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T04:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"4a6cb22b86686a8ed145d777a54d544a6c3f3f8e9b101cffdd6d806c85ff4833","abstract_canon_sha256":"79a865c4a8ab48e1ef051fe1972467fb0ecdfaa0e790725e5cb891930a7c2653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:16.201224Z","signature_b64":"xzyqm047LXVaWjluxu1rsvr9GThlIkTjBBfZ4G5vj21CeTBoM/jZekhuYS+Ddb07Ds1FlXTejBniU/t9P3KFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8d0bdb3df7409660828f501c4b76051936a053bf25431a4adb3c2326913cfba","last_reissued_at":"2026-06-10T01:10:16.200282Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:16.200282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Geewook Kim, Kee-Eung Kim, Sanghee Park","submitted_at":"2026-06-09T04:25:44Z","abstract_excerpt":"Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a decade (2014-2025) of Korean College Scholastic Ability Test (KCSAT; Suneung) mathematics: 664 problems with a 339-item core set carrying official per-item error rates from nationwide cohorts of hundreds of thousands of examinees. We pair the benchmark with Difficulty-aligned Reasoning Gain (DRG): a score-orthogonal metric that asks whether a model's mistakes concentrate on the items humans found hard, or on items humans found easy. Together the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10403","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/2606.10403/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":"2606.10403","created_at":"2026-06-10T01:10:16.200456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10403v1","created_at":"2026-06-10T01:10:16.200456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10403","created_at":"2026-06-10T01:10:16.200456+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DIL3M67OQEW","created_at":"2026-06-10T01:10:16.200456+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DIL3M67OQEWMCBI","created_at":"2026-06-10T01:10:16.200456+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DIL3M67","created_at":"2026-06-10T01:10:16.200456+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/7DIL3M67OQEWMCBI6UA4JN3AKG","json":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG.json","graph_json":"https://pith.science/api/pith-number/7DIL3M67OQEWMCBI6UA4JN3AKG/graph.json","events_json":"https://pith.science/api/pith-number/7DIL3M67OQEWMCBI6UA4JN3AKG/events.json","paper":"https://pith.science/paper/7DIL3M67"},"agent_actions":{"view_html":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG","download_json":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG.json","view_paper":"https://pith.science/paper/7DIL3M67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10403&json=true","fetch_graph":"https://pith.science/api/pith-number/7DIL3M67OQEWMCBI6UA4JN3AKG/graph.json","fetch_events":"https://pith.science/api/pith-number/7DIL3M67OQEWMCBI6UA4JN3AKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG/action/storage_attestation","attest_author":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG/action/author_attestation","sign_citation":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG/action/citation_signature","submit_replication":"https://pith.science/pith/7DIL3M67OQEWMCBI6UA4JN3AKG/action/replication_record"}},"created_at":"2026-06-10T01:10:16.200456+00:00","updated_at":"2026-06-10T01:10:16.200456+00:00"}