{"id":"W4393098406","doi":"10.2308/isys-2023-023","title":"Measuring Corporate Human Capital Disclosures: Lexicon, Data, Code, and Research Opportunities","year":2024,"lang":"en","type":"article","venue":"Journal of Information Systems","topic":"Financial Reporting and Valuation Research","field":"Business, Management and Accounting","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lexicon; Code (set theory); Computer science; Accounting; Human capital; Natural language processing; Business; Data science; Programming language; Economics","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0114375,0.00008771518,0.0001861335,0.00102097,0.0003129979,0.002714287,0.0002902473,0.0000396588,0.00001901902],"category_scores_gemma":[0.0007655835,0.00006744894,0.00003608922,0.0003831556,0.00007933555,0.007457168,0.0001890994,0.0003504778,0.00008613276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000502413,"about_ca_system_score_gemma":0.0002857378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002928638,"about_ca_topic_score_gemma":0.00002169891,"domain_scores_codex":[0.9974052,0.00005003401,0.001022639,0.00008646669,0.00123945,0.000196192],"domain_scores_gemma":[0.9972193,0.00009345613,0.0008011798,0.0001995825,0.001656162,0.00003029935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001303529,0.00007934205,0.02783044,0.008334237,0.0003099533,0.0005101044,0.003758857,0.001001108,0.000860458,0.7148588,0.1999135,0.04241291],"study_design_scores_gemma":[0.001051872,0.0001390989,0.01696044,0.003458196,0.00008560081,0.0006575332,0.03206933,0.05554323,0.00006278019,0.01161733,0.8778698,0.0004847061],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813642,0.001114543,0.0008850205,0.0009154229,0.001273115,0.0002606972,0.00001797556,0.00005389096,0.01411517],"genre_scores_gemma":[0.9981652,0.00005534161,0.00002104036,0.00003810546,0.001071093,0.000004915271,0.00004804877,0.000009520556,0.0005866967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7032414,"threshold_uncertainty_score":0.998321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5076878867179168,"score_gpt":0.3959824706749596,"score_spread":0.1117054160429572,"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."}}