{"id":"W2782848721","doi":"10.1515/ling-2017-0032","title":"Reproducible research in linguistics: A position statement on data citation and attribution in our field","year":2017,"lang":"en","type":"article","venue":"Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Attribution; Linguistics; Statement (logic); Citation; Field (mathematics); Applied linguistics; Quantitative linguistics; Authorship attribution; Position statement; Clinical linguistics; Psychology; Computer science; Sociology; Philosophy; Social psychology; Library science; Medicine","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","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5745385,0.002499046,0.007002002,0.01332238,0.02891519,0.0797623,0.0139235,0.09473223,0.006459923],"category_scores_gemma":[0.7133316,0.003255916,0.004212785,0.01796038,0.09172913,0.05650053,0.03272054,0.1003972,0.008033013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02742962,"about_ca_system_score_gemma":0.09346701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005914455,"about_ca_topic_score_gemma":0.004331697,"domain_scores_codex":[0.4241446,0.2677759,0.09318838,0.03858541,0.1642095,0.01209629],"domain_scores_gemma":[0.08779371,0.5594523,0.06061481,0.1008102,0.1654572,0.02587183],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008642318,0.00006725691,0.0007726867,0.0006451564,0.0001111464,0.0002505236,0.003894135,0.0004235346,0.0004170924,0.6334046,0.3246133,0.03531398],"study_design_scores_gemma":[0.00009334875,0.00007585415,0.0004239614,0.002982389,0.0001102077,0.0002450193,0.001318174,0.002043078,0.001267027,0.4127194,0.5783634,0.0003580997],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.000508656,0.004595578,0.02641333,0.9086993,0.05399496,0.0001387305,0.0001191152,0.0002671478,0.005263126],"genre_scores_gemma":[0.0830136,0.01468183,0.1182766,0.5509627,0.2041171,0.0028596,0.0006792421,0.002223494,0.02318594],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9860765,"threshold_uncertainty_score":0.5246698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1868200154824773,"score_gpt":0.4697376448389886,"score_spread":0.2829176293565113,"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."}}