{"baselines_definition":{"always_one":"predict_proba=1; recall=1, precision=base_rate","always_zero":"predict_proba=0; trivial F1=0 baseline","base_rate_constant":"predict_proba=train_pos_rate; well-calibrated, no resolution","country_base_rate":"predict_proba=country's historical positive rate; no temporal signal","predict_yesterday":"predict_proba=y[t-1] per (country, ...) group; tough on autocorrelated targets","random_with_base_rate":"Bernoulli sample with p=base_rate; sanity floor"},"generated_at":"2026-10-01T04:45:08+00:00","honest_caveats":["Lift is computed against the predict_yesterday baseline (lag-1 of the label within each country group). This is the toughest trivial baseline on autocorrelated targets like 'will country X be in shutdown next week'.","Some models report training-time sidecar metrics (random or stratified CV) and we compute baselines on a separate last-60d temporal holdout. Lift numbers in those rows are approximate, NOT a clean apples-to-apples test. Look at the `source` field per row to see which are live re-eval.","AUC of None on always_zero / always_one is by design (degenerate constants); those rows still have F1 + Brier.","barely_beats_baseline=true is a yellow flag, not red. Some models (e.g. classifier_v3.3) have legitimate value beyond F1 lift (per-country thresholds, conformal intervals, SHAP attributions).","Per-platform/domain/method are a random sample of 5 each, seeded 20260521 for reproducibility. Re-running will pick the same items."],"n_models":23,"n_rows_filtered":1,"rows":[{"barely_beats_baseline":true,"barely_beats_metric":"f1","baseline_metrics":{"always_one":{"auc":null,"brier":0.7325396825396825,"f1":0.42204132748904194},"always_zero":{"auc":null,"brier":0.26746031746031745,"f1":0.0},"base_rate_constant":{"auc":0.5,"base_rate":0.12618070484007557,"best_threshold":0.05,"brier":0.21588522498646928,"f1":0.42204132748904194},"country_base_rate":{"auc":0.7785395321024526,"best_threshold":0.1,"brier":0.19602729924300924,"f1":0.5819158460161146},"predict_yesterday":{"auc":0.9372128686292601,"best_threshold":0.05,"brier":0.049206349206349205,"f1":0.9080118694362018,"note":"lag-1 of label within each (country, ...) group; falls back to global lag-1 if grouping unavailable"},"random_with_base_rate":{"auc":0.4928580843655863,"brier":0.33174603174603173,"f1":0.15725806451612903}},"family":"forecast","honest_caveats":["Model F1 beats predict_yesterday by less than 5.0pp (lift=4.03pp). Honest reading: the model is mostly memorizing the prior."],"horizon":"7d","lift_vs_predict_yesterday":{"auc_pp":5.557931014528172,"brier_pp":2.439077396907186,"f1_pp":4.028945995818523},"model_id":"forecast_7day","model_metrics":{"auc":0.9927921787745418,"best_threshold":0.55,"brier":0.024815575237277347,"f1":0.948301329394387,"n":1260,"pos_rate":0.26746031746031745},"notes":"XGBoost + isotonic calibrator. Train base rate 0.126; holdout pos rate 0.267","source":"live re-eval on temporal holdout (1260 rows, last 60 days)"}],"schema":"voidly-baseline-benchmark/v1","summary":{"barely_beats_threshold_pp_f1":5.0,"best_model_by_lift":{"family":"per-domain","lift_metric":"auc","lift_pp":50.74168797953964,"model_id":"per_domain_pornhub.com"},"n_models_barely_beating_baseline":7,"n_models_evaluated":23,"toughest_baseline":"predict_yesterday","worst_model_by_lift":{"family":"classifier","lift_metric":"f1","lift_pp":-23.814704318410197,"model_id":"classifier_v3.3"}}}