{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JXNDUWUH4STOE2SI6PIJ6IMW23","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"388081cf826dabe090d85772e1c019e4773ab53e10efc84ed5535f1767cb96c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T01:57:35Z","title_canon_sha256":"7d53ea9ef2e5768cab9f4ed43337e4448ba83cb0818ad7a4e6511ac45e362c0f"},"schema_version":"1.0","source":{"id":"2605.14257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14257","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14257v1","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14257","created_at":"2026-05-17T23:39:10Z"},{"alias_kind":"pith_short_12","alias_value":"JXNDUWUH4STO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JXNDUWUH4STOE2SI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JXNDUWUH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4edf20102be6c662e1fa087f541d54c0daba5ff7a95bfbad36886829f3c88c6d","target":"graph","created_at":"2026-05-17T23:39:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The black-box model achieved r > 0.91 and topped the open track, while the explainable model reached r > 0.77 and showed that KVL item difficulty is affected by spelling difficulty or test item construction in addition to genuine production difficulty."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the shared task dataset and KVL lists provide a clean measure of genuine word production difficulty without significant confounding from test design or spelling factors that the models are capturing post-hoc."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Fine-tuned LLM with soft-target loss tops shared task on vocabulary difficulty prediction at r>0.91 while explainable model at r>0.77 shows spelling and item construction affect difficulty beyond word production."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Spelling difficulty and test item construction often drive ratings in standard vocabulary difficulty lists beyond genuine word production demands."}],"snapshot_sha256":"9c8226b5302df29a661301952e5966be951009a708a70696529cc78c8e828497"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We describe two types of models for vocabulary difficulty prediction: a high-accuracy black-box model, which achieved the top shared task result in the open track, and an explainable model, which outperforms a fine-tuned encoder baseline. As the black-box model, we fine-tuned an LLM using a soft-target loss function for effective application to the rating task, achieving r > 0.91. The explainable model provides insights into what impacts the difficulty of each item while maintaining a strong correlation (r > 0.77). We further analyze the results, demonstrating that the difficulty of items in t","authors_text":"Adam Nohejl, Hitomi Yanaka, Maria Angelica Riera Machin, Xuanxin Wu, Yi-Ning Chang, Yusuke Ide","cross_cats":[],"headline":"Spelling difficulty and test item construction often drive ratings in standard vocabulary difficulty lists beyond genuine word production demands.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T01:57:35Z","title":"What Makes Words Hard? Sakura at BEA 2026 Shared Task on Vocabulary Difficulty Prediction"},"references":{"count":35,"internal_anchors":7,"resolved_work":35,"sample":[{"cited_arxiv_id":"","doi":"10.18653/v1/2022.tsar-1.28","is_internal_anchor":false,"ref_index":1,"title":"Dennis Aumiller and Michael Gertz. 2022. https://doi.org/10.18653/v1/2022.tsar-1.28 U ni HD at TSAR -2022 shared task: Is compute all we need for lexical simplification? In Proceedings of the Workshop","work_id":"cffb6528-85d4-4b3f-b7c2-0d9152671c69","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"BNC Consortium . 2007. https://llds.ling-phil.ox.ac.uk/llds/xmlui/handle/20.500.14106/2554 British National Corpus , XML edition . https://llds.ling-phil.ox.ac.uk/llds/xmlui/handle/20.500.14106/2554","work_id":"06b216ce-ad64-4654-a05b-4aaf8a2b0f03","year":2007},{"cited_arxiv_id":"","doi":"10.1017/s2041536212000013","is_internal_anchor":false,"ref_index":3,"title":"Annette Capel. 2012. https://doi.org/10.1017/S2041536212000013 Completing the English Vocabulary Profile : C1 and C2 vocabulary . English Profile Journal, 3:e1","work_id":"61e4b0ae-c6ac-4be6-8f36-9fc00f8ad5be","year":2012},{"cited_arxiv_id":"","doi":"10.1145/2939672.2939785","is_internal_anchor":false,"ref_index":4,"title":"In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp","work_id":"1c2af073-b162-4cd0-a5cd-d8aade23b9b5","year":2016},{"cited_arxiv_id":"","doi":"10.18653/v1/2020.acl-main.747","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the Association for Computational Linguistics (ACL) , pages =","work_id":"bad774d3-20f4-421f-ba75-d1ef99f02a26","year":2020}],"snapshot_sha256":"fd40aa816827763ed96283ddbc2d24450ab44c51d9a6a4aecf67b036a09fd55b"},"source":{"id":"2605.14257","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:56:02.140941Z","id":"c38e04d0-f0a0-4ba5-b797-8d89ebdb6037","model_set":{"reader":"grok-4.3"},"one_line_summary":"Fine-tuned LLM with soft-target loss tops shared task on vocabulary difficulty prediction at r>0.91 while explainable model at r>0.77 shows spelling and item construction affect difficulty beyond word production.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Spelling difficulty and test item construction often drive ratings in standard vocabulary difficulty lists beyond genuine word production demands.","strongest_claim":"The black-box model achieved r > 0.91 and topped the open track, while the explainable model reached r > 0.77 and showed that KVL item difficulty is affected by spelling difficulty or test item construction in addition to genuine production difficulty.","weakest_assumption":"That the shared task dataset and KVL lists provide a clean measure of genuine word production difficulty without significant confounding from test design or spelling factors that the models are capturing post-hoc."}},"verdict_id":"c38e04d0-f0a0-4ba5-b797-8d89ebdb6037"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db3e0e58414f14962140d4fd1a82339dce2c4b09e46ee14c65c32c52ec863605","target":"record","created_at":"2026-05-17T23:39:10Z","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":"388081cf826dabe090d85772e1c019e4773ab53e10efc84ed5535f1767cb96c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-14T01:57:35Z","title_canon_sha256":"7d53ea9ef2e5768cab9f4ed43337e4448ba83cb0818ad7a4e6511ac45e362c0f"},"schema_version":"1.0","source":{"id":"2605.14257","kind":"arxiv","version":1}},"canonical_sha256":"4dda3a5a87e4a6e26a48f3d09f2196d6ed1794bb13e3fe9fec276c8429898ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4dda3a5a87e4a6e26a48f3d09f2196d6ed1794bb13e3fe9fec276c8429898ac1","first_computed_at":"2026-05-17T23:39:10.516776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:10.516776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KnBoz5nozFvp1BqcQ+oPhUHS55zd1spul4vzhkrXgKdwPqbYMljYvEuZqwFteyfEVTwrXFI/eiG+lmuD6/nNDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:10.517262Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3e0e58414f14962140d4fd1a82339dce2c4b09e46ee14c65c32c52ec863605","sha256:4edf20102be6c662e1fa087f541d54c0daba5ff7a95bfbad36886829f3c88c6d","sha256:cfa671a987d474ef118b0b4c1444fa51347c451a28558ee4260157cf204b00c6"],"state_sha256":"aaec275638a7703e34bb9f6d0c68373d898fe7e14f2be46fa80328c4e3503a95"}