{"id":"W1991215305","doi":"10.1145/2245276.2245306","title":"Semi-supervised document clustering with dual supervision through seeding","year":2012,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Cluster analysis; Seeding; Computer science; Document clustering; Pairwise comparison; Artificial intelligence; Cluster (spacecraft); Correlation clustering; Data mining; Pattern recognition (psychology); Machine learning; Engineering","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":[0.0002062235,0.0001577808,0.0001306812,0.0000767195,0.0001609583,0.0002388193,0.00055152,0.00006844824,0.0001303117],"category_scores_gemma":[0.00001313683,0.0001098476,0.00003493908,0.000361674,0.00004290582,0.002873104,0.0005011698,0.0001095479,0.0001258918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006051575,"about_ca_system_score_gemma":0.00001723341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002776636,"about_ca_topic_score_gemma":0.000004132911,"domain_scores_codex":[0.998753,0.00002041112,0.0001934578,0.000287104,0.0003249637,0.0004210298],"domain_scores_gemma":[0.9992213,0.00004779128,0.00005078937,0.0005624752,0.00004192601,0.00007576673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002769888,0.0002687657,0.0278434,0.00006448958,0.0000709296,0.00001024987,0.009057241,0.0001329715,0.0191428,0.7868605,0.006577208,0.1499437],"study_design_scores_gemma":[0.007554067,0.001773979,0.05266232,0.000461946,0.00009770814,0.0005064932,0.01904048,0.1240849,0.4840912,0.02774895,0.2771416,0.004836346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08662919,0.0001949622,0.8923949,0.00366597,0.0003104295,0.0001953528,3.384958e-7,0.001421964,0.01518688],"genre_scores_gemma":[0.8673853,0.0000346549,0.1314265,0.0003030376,0.00005721796,0.00002385203,0.000001758202,0.000008676621,0.0007589436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7807561,"threshold_uncertainty_score":0.4479457,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03048652227191006,"score_gpt":0.2641961432442345,"score_spread":0.2337096209723244,"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."}}