{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002679467,0.00008567631,0.0001110799,0.0002698767,0.0002177652,0.0004182116,0.0009966257,0.0000826571,3.951258e-7],"category_scores_gemma":[0.03102043,0.00008634339,0.000006569964,0.0001870347,0.00002606053,0.00009979183,0.0007510724,0.0004069037,0.000004360737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001242322,"about_ca_system_score_gemma":0.00008197606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005951356,"about_ca_topic_score_gemma":0.000227366,"domain_scores_codex":[0.9984953,0.0000985521,0.0002567304,0.0005889689,0.0003185056,0.0002418736],"domain_scores_gemma":[0.9975211,0.0001631285,0.000128245,0.001671669,0.0004765799,0.00003928895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001268711,0.0003507593,0.01615531,0.0003090688,0.000009191141,0.0005429016,0.001549772,0.00003416826,0.0005807601,0.9105037,0.007463973,0.06237346],"study_design_scores_gemma":[0.001320345,0.0009474818,0.01411142,0.002161491,0.00001154972,0.000007650941,0.0001779332,0.1567514,0.02996729,0.773992,0.01984787,0.000703604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07259694,0.005318496,0.8510512,0.03478178,0.01043959,0.003919933,0.0002280499,0.001283525,0.02038055],"genre_scores_gemma":[0.8526615,0.00004946353,0.1467161,0.00008664814,0.0004025433,0.000008036784,0.00003396016,0.000005531258,0.00003621926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7800645,"threshold_uncertainty_score":0.9771417,"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."}}