{"id":"W2157631542","doi":"10.1145/1807167.1807213","title":"Schema clustering and retrieval for multi-domain pay-as-you-go data integration systems","year":2010,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data integration; Cluster analysis; Schema (genetic algorithms); Data mining; Information retrieval; Conceptual schema; Schema matching; Probabilistic logic; Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006167559,0.0001023383,0.0001397058,0.00004843992,0.0001085261,0.0003377353,0.0007694762,0.00008956404,0.000003126776],"category_scores_gemma":[0.0003750978,0.00006688661,0.00001790218,0.00009087947,0.00004503578,0.0006331407,0.0005574734,0.0001256261,0.0000129989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007654546,"about_ca_system_score_gemma":0.00003805425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001445982,"about_ca_topic_score_gemma":0.0004324111,"domain_scores_codex":[0.9990815,0.00002093319,0.0001829653,0.0004047735,0.0001245913,0.0001852146],"domain_scores_gemma":[0.9989498,0.0001399244,0.00005646841,0.0007345619,0.00006321272,0.0000560431],"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":[0.0001650131,0.0002464358,0.005810409,0.0004579345,0.0001107178,0.0000404815,0.003208883,0.00001563381,0.25536,0.5628588,0.009231497,0.1624942],"study_design_scores_gemma":[0.0005911624,0.00006314612,0.0009037363,0.00002496485,0.000005407041,0.00006622995,0.0004348985,0.9858331,0.005147452,0.0007965305,0.005971204,0.0001621721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06032824,0.0000675898,0.9366847,0.0008827339,0.001164632,0.0002908137,0.000004630906,0.0001641672,0.0004124564],"genre_scores_gemma":[0.5668086,0.00000870158,0.4320777,0.0001063812,0.0001156647,0.000008174216,0.00001199042,0.000006366616,0.0008564505],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9858175,"threshold_uncertainty_score":0.3256789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07672508189442405,"score_gpt":0.3239843287210066,"score_spread":0.2472592468265825,"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."}}