{"id":"W4295630651","doi":"10.31274/jlsc.14421","title":"Free and Open-Source Automated Open Access Preprint Harvesting","year":2022,"lang":"en","type":"article","venue":"Journal of Librarianship and Scholarly Communication","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Upload; World Wide Web; Computer science; Metadata; Identifier; JavaScript; License; Preprint; Unique identifier; Open source; MIT License; Process (computing); Scholarly communication; Publishing; Software; Political science; Operating system","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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01372208,0.00110283,0.001310677,0.004666279,0.001987311,0.005154836,0.002810519,0.001254464,0.0189779],"category_scores_gemma":[0.0535299,0.00116233,0.001686607,0.003541729,0.001199621,0.00455128,0.005298006,0.001710031,0.03005602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009412487,"about_ca_system_score_gemma":0.003302284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001093689,"about_ca_topic_score_gemma":0.001267213,"domain_scores_codex":[0.9883436,0.002000822,0.001096397,0.001896827,0.00622225,0.0004400339],"domain_scores_gemma":[0.9433156,0.02212106,0.003527078,0.01841343,0.01052807,0.002094739],"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":[0.001628321,0.0007211843,0.01330001,0.00140771,0.0002194515,0.001289572,0.003190065,0.00245723,0.1020007,0.007749655,0.1764922,0.6895438],"study_design_scores_gemma":[0.0004010198,0.0007463911,0.03458586,0.000595,0.0002023098,0.002399707,0.001755303,0.06355706,0.2174269,0.02242847,0.6550331,0.000868923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06440784,0.0007513111,0.4955016,0.001423874,0.00134771,0.003519874,0.009799687,0.3924167,0.03083136],"genre_scores_gemma":[0.1394069,0.0007991173,0.7544065,0.0009060454,0.0006261311,0.002243815,0.02156048,0.04022952,0.03982155],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9971895,"threshold_uncertainty_score":0.07257015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2453683543165483,"score_gpt":0.4174049630888566,"score_spread":0.1720366087723082,"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."}}