{"id":"W2072344898","doi":"10.1371/journal.pone.0012133","title":"A Method for the Automated, Reliable Retrieval of Publication-Citation Records","year":2010,"lang":"en","type":"article","venue":"PLoS ONE","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Citation; Information retrieval; Computer science; Set (abstract data type); Vocabulary; Raw data; Search engine; Data mining; World Wide Web","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01220914,0.002332322,0.001722963,0.02450533,0.001925726,0.005491103,0.003026013,0.002270731,0.007260299],"category_scores_gemma":[0.07383495,0.001282461,0.00209316,0.01814271,0.001056662,0.004468316,0.002773669,0.002051862,0.01287929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001602418,"about_ca_system_score_gemma":0.006064143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004798058,"about_ca_topic_score_gemma":0.005584264,"domain_scores_codex":[0.982798,0.003645926,0.002567879,0.003052427,0.007534733,0.000401044],"domain_scores_gemma":[0.9422155,0.02446505,0.006194017,0.009972522,0.01651601,0.0006368927],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002734525,0.0001727965,0.008067075,0.001118669,0.0003293817,0.0003079647,0.000508671,0.005499668,0.01482106,0.01310732,0.04384603,0.911948],"study_design_scores_gemma":[0.0004398303,0.0003590872,0.0232504,0.0006643846,0.0005350886,0.003558126,0.0006121497,0.5553861,0.07935464,0.05813615,0.2769994,0.0007047029],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002666057,0.000434843,0.976997,0.0002442777,0.0001756363,0.0004670398,0.003089717,0.0146536,0.001271653],"genre_scores_gemma":[0.01445669,0.0001953242,0.9791707,0.000069858,0.0001249277,0.0007516738,0.00294859,0.0006044838,0.00167777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9877909,"threshold_uncertainty_score":0.06456894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6013699902379935,"score_gpt":0.5521463994613379,"score_spread":0.04922359077665561,"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."}}