{"id":"W3124630946","doi":"10.2139/ssrn.3718899","title":"Reliance on Science by Inventors: Hybrid Extraction of In-Text Patent-to-Article Citations","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Patent law; Extraction (chemistry); Data science; Engineering ethics; Intellectual property; Information retrieval; Engineering; Computer science; Political science; Chemistry; Law","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":[],"consensus_categories":[],"category_scores_codex":[0.003269552,0.000132913,0.0001864396,0.0001851591,0.0002442843,0.0001444361,0.0006976796,0.00002569648,0.0001829955],"category_scores_gemma":[0.001185457,0.0001211406,0.00003942991,0.0009482147,0.0002014563,0.0006128799,0.00007279249,0.0006689436,0.0003315996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005276178,"about_ca_system_score_gemma":0.001028864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001172702,"about_ca_topic_score_gemma":0.00004288205,"domain_scores_codex":[0.9968095,0.0001554461,0.0004589113,0.0003969411,0.0007101353,0.001469063],"domain_scores_gemma":[0.9991124,0.00006930045,0.0002827253,0.0001882442,0.00013491,0.0002124093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007498331,0.00006200884,0.001945184,0.000006447007,0.000001607615,0.000002449323,0.000339501,0.005348171,0.9862269,0.004946966,0.0001971685,0.0008486866],"study_design_scores_gemma":[0.0008969202,0.001698619,0.008677211,0.0001135692,0.00001152917,0.0001236938,0.001019816,0.007986494,0.9596057,0.01871967,0.0007594954,0.0003873113],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883692,0.0001023941,0.006961717,0.003848541,0.0003323404,0.000145433,0.000006208179,0.00003520701,0.0001989873],"genre_scores_gemma":[0.9984168,0.00009466672,0.0008341512,0.0004657626,0.00009182664,0.00000703155,7.349312e-7,0.0000139954,0.00007498866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02662116,"threshold_uncertainty_score":0.4939968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01727369435926722,"score_gpt":0.2770064280987352,"score_spread":0.259732733739468,"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."}}