{"id":"W4414576662","doi":"10.7910/dvn/w5ai5a","title":"Replication Package for \"From Online Job Postings to Economic Insights: A Machine Learning Approach to Structuring Naturally Occurring Data\"","year":2025,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"AI and HR Technologies","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bank of Canada","funders":"","keywords":"Replication (statistics); Replicate; Transparency (behavior); Confidentiality; Raw data; Code (set theory); Pipeline (software)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003242568,0.0005498718,0.0006120383,0.0008573908,0.0004012508,0.0007653183,0.003931434,0.0003427065,0.0002681651],"category_scores_gemma":[0.002216856,0.0005442429,0.00009682155,0.0003643515,0.00003784586,0.001542235,0.006861573,0.0007041986,0.001865305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001711104,"about_ca_system_score_gemma":0.00007248957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005196351,"about_ca_topic_score_gemma":0.001991532,"domain_scores_codex":[0.9968919,0.00001361797,0.0006118586,0.001783409,0.0002231306,0.0004760447],"domain_scores_gemma":[0.9951494,0.000121153,0.0004992152,0.004077043,0.0001137852,0.00003938555],"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":[0.00009574407,0.00003776544,0.00008622248,0.0004846133,0.0000989555,0.000005294312,0.0000188038,0.0002176653,0.00007990352,0.0003053469,0.9956765,0.002893245],"study_design_scores_gemma":[0.0004095017,0.00001597976,0.0001471069,0.000274295,0.0002461769,0.000001271485,0.0002425681,0.00450118,0.00002158382,0.0001321158,0.9933971,0.0006111338],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003021729,0.000009884984,0.001273663,0.00008001685,0.0005738722,0.001255188,0.9930752,0.0004659419,0.0002444974],"genre_scores_gemma":[0.0004981443,0.00004410587,0.008631863,0.002740406,0.001283525,0.00009394886,0.9865317,0.00004260964,0.0001337036],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0073582,"threshold_uncertainty_score":0.9997009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02730397854844898,"score_gpt":0.2575495038037025,"score_spread":0.2302455252552535,"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."}}