{"id":"W4403344678","doi":"10.1287/ijoc.2024.0938","title":"A Column Generation Algorithm with Dynamic Constraint Aggregation for Minimum Sum-of-Squares Clustering","year":2025,"lang":"en","type":"preprint","venue":"INFORMS journal on computing","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Column (typography); Column generation; Cluster analysis; Constraint (computer-aided design); Explained sum of squares; Mathematical optimization; Algorithm; Computer science; Least-squares function approximation; Mathematics; Combinatorics; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001236309,0.0004373915,0.0006305508,0.000750123,0.0004958796,0.0008791163,0.001443563,0.0002659535,0.000002136303],"category_scores_gemma":[0.0002117921,0.0003807839,0.0002338264,0.000405234,0.0001212131,0.000522879,0.001334597,0.001312819,0.000001695955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006458958,"about_ca_system_score_gemma":0.001078693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002037029,"about_ca_topic_score_gemma":0.00002507404,"domain_scores_codex":[0.9966164,0.00008320825,0.001183803,0.0005822416,0.0008967577,0.0006375544],"domain_scores_gemma":[0.9962372,0.000511512,0.001305867,0.0006515065,0.001113668,0.0001802852],"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":[0.00002310935,0.0000287453,0.000009791868,0.0002170918,0.00008765915,0.00001987131,0.0005473088,0.3805687,0.00006982532,0.0001858279,0.00002630765,0.6182157],"study_design_scores_gemma":[0.001131439,0.0006173507,0.00005227407,0.002245366,0.00001729115,0.000253269,0.0001053352,0.9930226,0.001025785,0.0008724398,0.0002588751,0.0003980384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01206173,0.0001226697,0.9844865,0.0003210612,0.001705008,0.0009405699,0.00004432534,0.0001241462,0.0001940426],"genre_scores_gemma":[0.1607995,0.0000542497,0.8383048,0.0001406452,0.0004382823,0.00003700959,0.00004231571,0.00003014805,0.0001530497],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6178177,"threshold_uncertainty_score":0.9998644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03044026473798135,"score_gpt":0.3275472470552012,"score_spread":0.2971069823172198,"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."}}