{"id":"W2032328503","doi":"10.1007/s10791-009-9108-x","title":"Document clustering of scientific texts using citation contexts","year":2009,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Information retrieval; Computer science; Document clustering; Citation; Vocabulary; Context (archaeology); Similarity (geometry); Representation (politics); Document retrieval; Natural language processing; Artificial intelligence; World Wide Web; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004991781,0.00008795421,0.0001313024,0.0004504971,0.0001252266,0.0002914423,0.0003874276,0.00004483317,0.000008330959],"category_scores_gemma":[0.0001120901,0.00008700669,0.00005907105,0.001012773,0.00004293321,0.004929793,0.00007694725,0.00006564358,0.00001839687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000102123,"about_ca_system_score_gemma":0.00005679828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003224357,"about_ca_topic_score_gemma":8.041845e-7,"domain_scores_codex":[0.9987367,0.00002385109,0.0004896937,0.0001185582,0.0004796878,0.0001514541],"domain_scores_gemma":[0.9988553,0.00002792194,0.0003641493,0.0003516878,0.0003563927,0.00004456832],"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":[0.00006801321,0.00006210744,0.0001788734,0.00005857395,0.00003056094,0.000002354211,0.005232785,0.01538972,0.04377983,0.08165631,0.0003050675,0.8532358],"study_design_scores_gemma":[0.0007095921,0.0002734871,0.004252001,0.0001070285,0.00001836316,0.000017211,0.00008620138,0.7957874,0.162362,0.03252544,0.003489282,0.0003719551],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07608683,0.00002104312,0.922473,0.0001017454,0.0001384385,0.0001526482,0.000001153878,0.0001453661,0.0008797561],"genre_scores_gemma":[0.8730282,0.000001792197,0.1267933,0.0001273347,0.000009851551,6.357538e-7,0.000008104314,0.000001526252,0.00002923284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8528638,"threshold_uncertainty_score":0.3573981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0160256859248469,"score_gpt":0.2950436954188471,"score_spread":0.2790180094940002,"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."}}