{"id":"W4417357121","doi":"10.48550/arxiv.2506.10942","title":"Building a Media Ecosystem Observatory from Scratch: Infrastructure, Methodology, and Insights","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Digital ecosystem; Observatory; Search engine indexing; Normalization (sociology); Raw data; Digital media; Social media","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"],"consensus_categories":[],"category_scores_codex":[0.001764488,0.0003067778,0.0007485703,0.0002480279,0.0004687607,0.0001186247,0.0006122037,0.0005775392,0.000163703],"category_scores_gemma":[0.001764196,0.0002888885,0.0002178842,0.0004398724,0.0002267792,0.000128109,0.0009264327,0.0007069053,0.00001111107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639864,"about_ca_system_score_gemma":0.0006674484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005195606,"about_ca_topic_score_gemma":0.007943351,"domain_scores_codex":[0.9958012,0.002187513,0.0005169259,0.0007901409,0.0004072129,0.0002970312],"domain_scores_gemma":[0.994638,0.004203906,0.0003524855,0.0003669981,0.0002454283,0.0001931804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004330477,0.00005614715,0.8363794,0.0002305569,0.001277269,0.00004263964,0.045853,0.001535711,0.0007016807,0.06497172,0.002002788,0.04690579],"study_design_scores_gemma":[0.0001888795,0.000005688856,0.4021569,0.0002153731,0.0002810649,1.76021e-7,0.001917194,0.0006800386,0.0001729705,0.5731422,0.02085564,0.0003839121],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747609,0.002854311,0.01697664,0.0008965164,0.002302354,0.0002389631,0.000079666,0.0001325093,0.001758183],"genre_scores_gemma":[0.8655214,0.0004521176,0.1317811,0.0007553517,0.001074372,0.00003796263,0.00006794389,0.00001638219,0.0002934345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5081704,"threshold_uncertainty_score":0.9999563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1708779774952619,"score_gpt":0.3940047330366261,"score_spread":0.2231267555413643,"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."}}