{"id":"W4319811928","doi":"10.22541/au.167528154.45763422/v1","title":"D3: A Massive Dataset of Scholarly Metadata for Analyzing the State of Computer Science Research","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Metadata; Computer science; Citation; Data science; Field (mathematics); Information retrieval; World Wide Web; Bibliometrics; Library science","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","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.1247806,0.0001966343,0.0005710938,0.002399182,0.0006071266,0.006481336,0.01364838,0.00005526066,0.00005694325],"category_scores_gemma":[0.01688554,0.0001103232,0.0001858745,0.005347047,0.001814977,0.001723638,0.030172,0.0006301022,0.00008647853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000599508,"about_ca_system_score_gemma":0.0007761807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009024715,"about_ca_topic_score_gemma":0.0002139686,"domain_scores_codex":[0.9886768,0.0006507891,0.001654439,0.002207733,0.006195016,0.0006151696],"domain_scores_gemma":[0.9797795,0.0077224,0.0009528286,0.007237201,0.004172366,0.0001356511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000052433,0.0001064197,0.0004780343,0.0001328428,0.0001631697,0.00000505485,0.0006638908,0.02222463,0.0004448955,0.006370208,0.813255,0.1561034],"study_design_scores_gemma":[0.0004685759,0.0001844058,0.00539756,0.0003317918,0.00009834868,0.000001034535,0.001538684,0.6784257,0.00309249,0.2199887,0.09003652,0.0004362018],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02759263,0.0001139533,0.9381075,0.002829073,0.002462842,0.001434803,0.02726213,0.00004125502,0.0001558232],"genre_scores_gemma":[0.634079,0.0001247495,0.3379448,0.0002969356,0.0004709127,0.0001865123,0.006995874,0.00007745568,0.01982374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7232184,"threshold_uncertainty_score":0.99455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6048854509862936,"score_gpt":0.5447832631191812,"score_spread":0.06010218786711241,"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."}}