{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZXFBMOAC2EPVC7CMQP5MADQNZJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7139b3bc8d83870c78b99342625e8544e6377743dd348387ae554eda99a008de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-06-22T09:53:25Z","title_canon_sha256":"cd81e27e518295c1ab8fdd839b87bc005872708251035d1fd0cfe0b005936a54"},"schema_version":"1.0","source":{"id":"2607.26067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26067","created_at":"2026-07-30T00:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26067v1","created_at":"2026-07-30T00:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26067","created_at":"2026-07-30T00:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZXFBMOAC2EPV","created_at":"2026-07-30T00:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZXFBMOAC2EPVC7CM","created_at":"2026-07-30T00:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZXFBMOAC","created_at":"2026-07-30T00:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:9d0fd976e507dd1c96e669f6313b08a1b09da3a649559126c9ee99ae867c3c75","target":"graph","created_at":"2026-07-30T00:08:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.26067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used for estimating item difficulty in educational assessment. However, it remains unclear whether such estimates reflect how learners actually experience difficulty. This study investigates the alignment between LLM-generated difficulty ratings and empirical student performance on basic mathematics tasks. Four widely used LLM-based systems generated difficulty ratings on a 1-100 scale for 32 arithmetic items across multiple runs (N = 640 ratings). These were compared with empirical difficulty derived from responses of 770 Indonesian undergraduates","authors_text":"Amanda La Hadi, A. Taufiq Asyhari, Guanliang Chen, Muhammad Johan Alibasa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-06-22T09:53:25Z","title":"The Easy Trap: Why LLMs Underestimate Misconception-Driven Difficulty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26067","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2fe3966cbd8b5772571414deaaa554fd134ca6c9d2f11f70e9124eda6d395fa4","target":"record","created_at":"2026-07-30T00:08:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7139b3bc8d83870c78b99342625e8544e6377743dd348387ae554eda99a008de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-06-22T09:53:25Z","title_canon_sha256":"cd81e27e518295c1ab8fdd839b87bc005872708251035d1fd0cfe0b005936a54"},"schema_version":"1.0","source":{"id":"2607.26067","kind":"arxiv","version":1}},"canonical_sha256":"cdca163802d11f517c4c83fac00e0dca7b5e860a8b737d1f6b99600d98c83f90","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdca163802d11f517c4c83fac00e0dca7b5e860a8b737d1f6b99600d98c83f90","first_computed_at":"2026-07-30T00:08:17.266313Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T00:08:17.266313Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fe3966cbd8b5772571414deaaa554fd134ca6c9d2f11f70e9124eda6d395fa4","sha256:9d0fd976e507dd1c96e669f6313b08a1b09da3a649559126c9ee99ae867c3c75"],"state_sha256":"1803689ac9065b4a0e585379b8e894a1d60fed15e25c0879562fd92c71e23cad"}