{"id":"W4234033320","doi":"10.1145/564410.564412","title":"Document clustering with committees","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Document clustering; Similarity (geometry); Set (abstract data type); Information retrieval; Task (project management); Data mining; Fuzzy clustering; Space (punctuation); Group (periodic table); Cluster (spacecraft); Artificial intelligence; Image (mathematics)","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":[0.001149038,0.0002201316,0.0002150849,0.0007302774,0.0002868666,0.0007046328,0.00262248,0.00008714126,0.000073838],"category_scores_gemma":[0.001096126,0.0001578116,0.00002870219,0.0008616525,0.0002689366,0.003146992,0.002075849,0.0006559549,0.00005952979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003035808,"about_ca_system_score_gemma":0.000147455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000247676,"about_ca_topic_score_gemma":0.000006565279,"domain_scores_codex":[0.9961586,0.0000285128,0.0006155774,0.0003354813,0.002302218,0.000559585],"domain_scores_gemma":[0.9970301,0.0002791018,0.0002426559,0.0002723508,0.001995148,0.0001806088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00400069,0.001878719,0.04467971,0.001714899,0.0005787025,0.00003712305,0.08228683,0.002464949,0.00292021,0.4443112,0.01290504,0.4022219],"study_design_scores_gemma":[0.01387555,0.006699432,0.0883726,0.005158703,0.00001070825,0.0003111844,0.01872851,0.5790321,0.1386289,0.04945184,0.09639509,0.00333544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8604689,0.000129337,0.03001879,0.02428899,0.001015724,0.003185353,0.0000716869,0.0003506079,0.08047061],"genre_scores_gemma":[0.9693052,0.0001643487,0.02896366,0.0001810983,0.00003415169,0.00006906697,0.000005796364,0.00001022859,0.001266406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5765671,"threshold_uncertainty_score":0.679479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517323618068653,"score_gpt":0.3218864163618488,"score_spread":0.2567131801811622,"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."}}