{"id":"W4390956213","doi":"10.2139/ssrn.4197489","title":"Measuring Corporate Human Capital Disclosures: Lexicon, Data, Code, and Research Opportunities","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Intellectual Capital and Performance Analysis","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Lexicon; Accounting; Business; Code (set theory); Human capital; Computer science; Data science; Natural language processing; Economics; Programming language","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":[0.005141007,0.0001946519,0.0002087963,0.000748352,0.0009386035,0.001616037,0.0005722293,0.00006598727,0.0002451671],"category_scores_gemma":[0.00007234464,0.0001543618,0.00007822594,0.0005295355,0.000200732,0.002732904,0.0003908475,0.001967833,0.0002645393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00019473,"about_ca_system_score_gemma":0.0007230532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005506575,"about_ca_topic_score_gemma":0.004933146,"domain_scores_codex":[0.9970027,0.00003848649,0.0003352145,0.0003571507,0.0005902746,0.001676128],"domain_scores_gemma":[0.9992382,0.00005627007,0.0001169634,0.000280621,0.0002778812,0.00003008728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005098641,0.00004369233,0.002634034,0.0002086662,0.0004260261,0.00007962444,0.0004505708,0.000012592,0.0004868685,0.970111,0.005276605,0.0202193],"study_design_scores_gemma":[0.0002930267,0.0001252037,0.0003828543,0.0001925962,0.0001862479,0.0002336031,0.01370911,0.005036993,0.00004683932,0.9357747,0.04359068,0.0004281775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9769815,0.01269662,0.0002466675,0.001720164,0.000251253,0.00009978657,0.000009708411,0.00008641637,0.007907856],"genre_scores_gemma":[0.9862449,0.004586638,0.000004451757,0.0001217602,0.00226784,0.000004683031,0.00008850374,0.00003874624,0.006642544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03831407,"threshold_uncertainty_score":0.9994204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2263162557439197,"score_gpt":0.3208079945844212,"score_spread":0.09449173884050152,"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."}}