{"id":"W4414230855","doi":"10.1109/gem66882.2025.11155795","title":"LADDER: Level Analysis Dataset for Difficulty Evaluation and Ranking","year":2025,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Ranking (information retrieval); Bridge (graph theory); Limiting; Resource (disambiguation); Object (grammar); Focus (optics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032516,0.00005147089,0.00008348141,0.000220012,0.0001060679,0.0001576066,0.0003137489,0.0000328979,0.00001617992],"category_scores_gemma":[0.0001053431,0.00004069018,0.0000287236,0.0006378747,0.00002181945,0.0002500984,0.0001366722,0.00002348267,0.000002327503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001772647,"about_ca_system_score_gemma":0.00002299214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277054,"about_ca_topic_score_gemma":0.0000452057,"domain_scores_codex":[0.9994329,0.0000166488,0.0001138753,0.0002378687,0.0001167631,0.00008195741],"domain_scores_gemma":[0.9994188,0.00009692724,0.00003735746,0.0003675857,0.00006845135,0.0000109102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003443777,0.00003494639,0.002555167,0.00001084428,0.0002000884,8.137052e-8,0.00007115741,0.00006868763,0.0007160584,0.4495411,0.05225848,0.49454],"study_design_scores_gemma":[0.0009975262,0.00002447739,0.07963473,0.000006384789,0.0003850946,3.036116e-7,0.000177501,0.8141659,0.005651773,0.04952288,0.04923816,0.0001952901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003130341,0.00008813454,0.9916306,0.004247718,0.00004439113,0.0002088046,0.00008021586,0.0001379209,0.0004318688],"genre_scores_gemma":[0.940552,0.00001375767,0.05793054,0.0002807339,0.00000423406,0.0000848569,0.0004805572,0.000001097054,0.0006522409],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9374216,"threshold_uncertainty_score":0.1659297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07098476990132718,"score_gpt":0.3651269513298248,"score_spread":0.2941421814284976,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}