{"id":"W4390245620","doi":"10.1016/j.datak.2023.102274","title":"Mining Keys for Graphs","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Data deduplication; Theoretical computer science; Identification (biology); Data mining; Pruning; Database","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004567647,0.0001313187,0.0002062753,0.0004692119,0.0001094866,0.0002620383,0.002229502,0.00004161456,0.00007234562],"category_scores_gemma":[0.004466019,0.0001169249,0.00005973463,0.001379527,0.00001990837,0.0006643527,0.001509854,0.00006850877,0.001532835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001388198,"about_ca_system_score_gemma":0.00002114853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004652701,"about_ca_topic_score_gemma":0.00003473788,"domain_scores_codex":[0.9982215,0.00003291087,0.0004136611,0.000590915,0.00038635,0.0003546488],"domain_scores_gemma":[0.9966078,0.001549973,0.0000558788,0.001610699,0.00007792504,0.00009774863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004576064,0.0000239463,0.00008389208,0.00005579905,0.00003336164,0.00000509587,0.0005183446,0.0001765242,0.0001846555,0.02217243,0.722056,0.2546853],"study_design_scores_gemma":[0.0001416172,0.0000103174,0.0005229044,0.00001627418,0.000008697933,4.855646e-7,0.0003712991,0.3558231,0.00005740015,0.001343491,0.641587,0.0001173671],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03628521,0.0009712757,0.9299598,0.00208795,0.009235888,0.001306866,0.005426869,0.002074137,0.01265196],"genre_scores_gemma":[0.6081954,0.0005172615,0.2727408,0.0009460003,0.004516815,0.0009858274,0.03168104,0.0005074441,0.07990935],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.657219,"threshold_uncertainty_score":0.9992446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3915863678661295,"score_gpt":0.4561268436149644,"score_spread":0.06454047574883487,"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."}}