{"id":"W4393609385","doi":"10.5281/zenodo.6395308","title":"patccat: A classifier for patent claims","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Intellectual Property and Patents","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Classifier (UML); Artificial intelligence; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008632276,0.0003239908,0.0002987743,0.0005280065,0.004073496,0.001864383,0.001886776,0.0001751836,0.352318],"category_scores_gemma":[0.000708072,0.0003115409,0.0001718785,0.0006299748,0.0001133048,0.0004389498,0.002833351,0.0006604958,0.02223078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001676296,"about_ca_system_score_gemma":0.000005977809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001866637,"about_ca_topic_score_gemma":0.000002478387,"domain_scores_codex":[0.9976538,0.0001087263,0.0004082618,0.0006804487,0.0005697628,0.0005790206],"domain_scores_gemma":[0.9982698,0.0000338092,0.0003003643,0.0006632273,0.0006874398,0.00004534438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002147369,0.0001992154,1.906215e-7,0.0005122863,0.00007589328,0.00001582853,0.00005273418,0.00001739115,0.00003624712,0.0004558512,0.98356,0.01485961],"study_design_scores_gemma":[0.0005792254,0.0001343268,0.000007013471,0.00004607169,0.00008443754,0.00001721911,0.0001411716,0.0003272039,0.000005922991,0.000300007,0.9979539,0.0004035219],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001138932,0.00008884772,0.0003318421,0.0008038628,0.001092758,0.00166525,0.9624746,0.0006872009,0.0327417],"genre_scores_gemma":[0.000709909,0.0000971315,0.00001221852,0.001693869,0.001117141,7.525151e-7,0.9926404,0.001452919,0.002275646],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.3300872,"threshold_uncertainty_score":0.9999337,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2236787735041636,"score_gpt":0.2419190717188506,"score_spread":0.01824029821468706,"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."}}