{"id":"W4385570153","doi":"10.18653/v1/2023.acl-industry.3","title":"Hunt for Buried Treasures: Extracting Unclaimed Embodiments from Patent Specifications","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Task (project management); Computer science; Competitor analysis; Automation; Intellectual property; Inference; Patent visualisation; Transformer; Artificial intelligence; Natural language processing; Software engineering; Engineering drawing; Data science; Engineering; Business; Systems engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001324025,0.0001826829,0.0002292595,0.0001112313,0.0004633663,0.0002971884,0.0005463259,0.00006775305,0.003883825],"category_scores_gemma":[0.000688845,0.0001529515,0.00007214925,0.0003165855,0.0000842939,0.0002526291,0.0001284546,0.00007513223,0.003169867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006828913,"about_ca_system_score_gemma":0.00006489568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006459318,"about_ca_topic_score_gemma":0.00003855952,"domain_scores_codex":[0.9978406,0.0001338113,0.0004421237,0.0006203671,0.0004600705,0.0005030025],"domain_scores_gemma":[0.9984456,0.0005911305,0.0002030198,0.0005242382,0.0001041489,0.0001318742],"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":[0.00003497742,0.00004508127,0.0007478675,0.00001104186,0.000005782246,0.00000370576,0.0003974485,0.001337609,0.9909256,0.001125783,0.00459952,0.0007655519],"study_design_scores_gemma":[0.001412404,0.0001219363,0.08376332,0.00007838388,0.00005655809,0.00000399112,0.001187649,0.0319648,0.8411381,0.01103633,0.02844804,0.0007884915],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784827,0.00001532969,0.01261416,0.001386386,0.001642807,0.0006168227,0.0001485874,0.0008899726,0.004203252],"genre_scores_gemma":[0.9571872,0.000007342983,0.03747246,0.0001678929,0.0004527751,0.0002637152,0.0001449502,0.00003855916,0.004265064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1497875,"threshold_uncertainty_score":0.9976063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1958081442768627,"score_gpt":0.3208010541663181,"score_spread":0.1249929098894554,"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."}}