{"sources":{"discoscm":{"status":"ready","family":"discoscm","row_meaning":"unit","query_mode":"any_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":true,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug"],"request_fields_ignored":["source_name"],"note":"Rows are units with latent u_i; cell-wise missing/query; unit-specific response law. See data-generation.pdf."},"scm":{"status":"ready","family":"scm","row_meaning":"iid_sample","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","sigma"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","debug","source_name"],"note":"i.i.d. rows from a random additive-noise DAG over features; last column is the prediction target; missing 0.05."},"sklearn_make_classification":{"status":"ready","family":"sklearn_synthetic","row_meaning":"iid_sample","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"sklearn make_classification; last column is binary y; missing 0.05 / query 0.15 of the label column."},"sklearn_make_regression":{"status":"ready","family":"sklearn_synthetic","row_meaning":"iid_sample","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"sklearn make_regression; last column is continuous y; missing 0.05 / query 0.15 of the label column."},"sklearn_friedman1":{"status":"ready","family":"sklearn_synthetic","row_meaning":"iid_sample","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"sklearn Friedman #1; last column is continuous y; missing 0.05 / query 0.15 of the label column."},"sklearn_low_rank":{"status":"ready","family":"sklearn_synthetic","row_meaning":"iid_sample","query_mode":"any_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"sklearn low-rank matrix; no designated label; cell-wise missing/query like matrix completion."},"sklearn_iris":{"status":"ready","family":"sklearn_real","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"Bundled iris table; last column is the class label; missing 0.05."},"sklearn_wine":{"status":"ready","family":"sklearn_real","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"Bundled wine table; last column is the class label; missing 0.05."},"sklearn_breast_cancer":{"status":"ready","family":"sklearn_real","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"Bundled breast_cancer table; last column is the class label; missing 0.05."},"sklearn_diabetes":{"status":"ready","family":"sklearn_real","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug","source_name"],"note":"Bundled diabetes table; last column is the continuous target; missing 0.05."},"sklearn_synthetic":{"status":"ready","family":"sklearn_synthetic","row_meaning":"iid_sample","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","source_name"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug"],"note":"Alias: pass source_name to pick a maker, or one is drawn at random. Per-maker masks follow the canonical profile.","makers":["make_classification","make_regression","make_friedman1","make_low_rank_matrix"],"alias_of":["sklearn_make_classification","sklearn_make_regression","sklearn_friedman1","sklearn_low_rank"]},"sklearn_real":{"status":"ready","family":"sklearn_real","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","source_name"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug"],"note":"Alias: pass source_name to pick a bundled table, or one is drawn at random.","datasets":["iris","wine","breast_cancer","diabetes"],"alias_of":["sklearn_iris","sklearn_wine","sklearn_breast_cancer","sklearn_diabetes"]},"openml":{"status":"ready","family":"openml","row_meaning":"entity_row","query_mode":"label_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","source_name"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug"],"note":"OpenML-CTR23 as the same episode contract as sklearn/scm: values + missing + query. source_name is a data_id; omit → 44970. n_features=null keeps native width (no 20-col pad). n_units caps rows, no repeat. label_cell / missing 0.05 / query 0.15 same as other supervised sources.","suite":"CTR23","data_ids":[44956,44957,44958,44959,44963,44964,44965,44966,44969,44971,44972,44973,44974,44975,44976,44977,44978,44979,44980,44981,44983,44984,44987,44989,44990,44992,44993,45012,41021,44960,44962,44967,44970,44994,45402]},"recsys":{"status":"placeholder","family":"recsys","row_meaning":"user","query_mode":"any_cell","query_frac":0.15,"missing_frac":0.05,"uses_unit_token":false,"request_fields_used":["n_units","n_features","seed","n_episodes","batch_size","source","missing_frac","query_frac","query_mode","query_column","return_mechanism","source_name"],"request_fields_ignored":["unit_dim","type_weights","independent_frac","dag_edge_p","max_parents","token_heritability","beta_min","beta_max","graph_family","sigma","debug"],"note":"User×Item ratings; compiler missing 0.05 until unobserved-as-missing is wired; returns 501 until cached."}}}