{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q3CROSNMFLUUC6WQBGYQW2NURQ","short_pith_number":"pith:Q3CROSNM","schema_version":"1.0","canonical_sha256":"86c51749ac2ae9417ad009b10b69b48c2a0c2c5c6593f573fe3bb04051fcac99","source":{"kind":"arxiv","id":"2606.28186","version":1},"attestation_state":"computed","paper":{"title":"Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawei Zhou, Hong Jiao, Ming Li, Tianyi Zhou, Xinyue Zeng, Zhuochun Li","submitted_at":"2026-06-26T15:32:17Z","abstract_excerpt":"Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on costly human calibration or item-level textual representations, providing limited evidence about the cognitive processes that make items difficult. We argue that difficulty should be viewed not only as a property of item text, but also as an observable consequence of the problem-solving burden an item induces. Large Reasoning Models (LRMs) offer scalable process evidence through reasoning traces, but such evidence mus"},"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":"2606.28186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T15:32:17Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"d2cb0b19721e398219547dfb0ca4f3b7d569f2cab60162ddb8572d195757cc72","abstract_canon_sha256":"77fe833e03e9352962c153d095dfd8ba22c74473b8b3b0ede17819ab8e240eda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:08.688222Z","signature_b64":"2mskJIRlypEAWEx7pacJ3d08pW6ECgx86La/Cm2lQ1QAjXQzSq9oyQ22okSK6sACnAqjKbAXy9D+J2f3KFXDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c51749ac2ae9417ad009b10b69b48c2a0c2c5c6593f573fe3bb04051fcac99","last_reissued_at":"2026-06-29T01:15:08.687790Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:08.687790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawei Zhou, Hong Jiao, Ming Li, Tianyi Zhou, Xinyue Zeng, Zhuochun Li","submitted_at":"2026-06-26T15:32:17Z","abstract_excerpt":"Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on costly human calibration or item-level textual representations, providing limited evidence about the cognitive processes that make items difficult. We argue that difficulty should be viewed not only as a property of item text, but also as an observable consequence of the problem-solving burden an item induces. Large Reasoning Models (LRMs) offer scalable process evidence through reasoning traces, but such evidence mus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28186","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/2606.28186/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":"2606.28186","created_at":"2026-06-29T01:15:08.687857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28186v1","created_at":"2026-06-29T01:15:08.687857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28186","created_at":"2026-06-29T01:15:08.687857+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3CROSNMFLUU","created_at":"2026-06-29T01:15:08.687857+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3CROSNMFLUUC6WQ","created_at":"2026-06-29T01:15:08.687857+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3CROSNM","created_at":"2026-06-29T01:15:08.687857+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/Q3CROSNMFLUUC6WQBGYQW2NURQ","json":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ.json","graph_json":"https://pith.science/api/pith-number/Q3CROSNMFLUUC6WQBGYQW2NURQ/graph.json","events_json":"https://pith.science/api/pith-number/Q3CROSNMFLUUC6WQBGYQW2NURQ/events.json","paper":"https://pith.science/paper/Q3CROSNM"},"agent_actions":{"view_html":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ","download_json":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ.json","view_paper":"https://pith.science/paper/Q3CROSNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28186&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3CROSNMFLUUC6WQBGYQW2NURQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3CROSNMFLUUC6WQBGYQW2NURQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ/action/storage_attestation","attest_author":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ/action/author_attestation","sign_citation":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ/action/citation_signature","submit_replication":"https://pith.science/pith/Q3CROSNMFLUUC6WQBGYQW2NURQ/action/replication_record"}},"created_at":"2026-06-29T01:15:08.687857+00:00","updated_at":"2026-06-29T01:15:08.687857+00:00"}