Insights

Receipts first. Every number traces to a graded row.

The same receipts query feeds Picks, Insights and the Sunday digest — it can never disagree with itself.

Leaderboard · hit rate by lens

Leaderboard · models, lenses, pundits, crews · baseline never leaves

Headline performance is ATS spread win rate. Pushes remain in graded spread plays but are excluded from the ATS spread denominator.

Rows are ordered by ATS spread win rate; prediction_results.clv breaks ties when available.
Entry	Kind	Graded spread plays	ATS spread win rate	Record (W-L-P)	CLV · secondary
[Auto] NFL Spread (MARS) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=37 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	37	64.9% · n=37 live · all-time window · n=37	24-13-0	−0.041
[Auto] NFL Elo Power Ratings Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	60.0% · n=45 live · all-time window · n=45	27-18-0	−0.011
[Auto] Blueprint (Py): Momentum Spread Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	56.9% · n=51 live · all-time window · n=51	29-22-12	−0.190
[Auto] NFL Spread (SVR) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	56.8% · n=44 live · all-time window · n=44	25-19-19	+0.087
[Auto] Blueprint (Py): Full Feature Spread (Stacking Ensemble) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	56.4% · n=39 live · all-time window · n=39	22-17-24	+0.206
[Auto] NFL Spread (ExtraTrees) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	56.4% · n=39 live · all-time window · n=39	22-17-24	−0.135
[Auto] NFL Spread (KNN) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=43 graded spread plays · as of 2026-10-05T00:04:00.23464+00:00	model	43	55.8% · n=43 live · all-time window · n=43	24-19-0	−0.047
[Auto] NFL Elo Power Ratings Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	55.1% · n=49 live · all-time window · n=49	27-22-14	−0.373
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	55.0% · n=40 live · all-time window · n=40	22-18-23	+0.087
[Auto] NFL Spread (KNN) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	55.0% · n=40 live · all-time window · n=40	22-18-23	−0.119
[Auto] Playbook (Py): Full Feature Spread (Stacking Ensemble) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=44 graded spread plays · as of 2026-10-05T00:04:00.23464+00:00	model	44	54.5% · n=44 live · all-time window · n=44	24-20-0	+0.057
[Auto] Blueprint (Py): Momentum Spread Model (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	54.3% · n=46 live · all-time window · n=46	25-21-17	+0.175
[Auto] NFL ATS XGBoost (Custom Objective) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	54.3% · n=46 live · all-time window · n=46	25-21-17	+0.167
model-3950f12e insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=24 graded spread plays · as of 2026-09-22T03:34:00.49759+00:00	model	24	54.2% · n=24 live · all-time window · n=24	13-11-0	+0.250
[Auto] NFL Spread (SVR) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=61 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	61	54.1% · n=61 live · all-time window · n=61	33-28-0	+0.016
[Auto] NFL Spread (MARS) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	53.5% · n=43 live · all-time window · n=43	23-20-20	+0.706
[Auto] NFL GNN Matchup insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	53.3% · n=45 live · all-time window · n=45	24-21-0	+0.122
[Auto] NFL Spread Stacking insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	53.3% · n=45 live · all-time window · n=45	24-21-0	+0.111
[Auto] NFL ATS XGBoost (Custom Objective) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	53.3% · n=45 live · all-time window · n=45	24-21-0	+0.011
[Auto] NFL GNN Matchup insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	52.5% · n=40 live · all-time window · n=40	21-19-23	+0.198
[Auto] Playbook (Py): Full Feature Spread (Mixture of Experts) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=44 graded spread plays · as of 2026-10-05T00:04:00.23464+00:00	model	44	52.3% · n=44 live · all-time window · n=44	23-21-0	+0.023
[Auto] NFL Spread Stacking insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	52.1% · n=48 live · all-time window · n=48	25-23-15	+0.087
[Auto] Blueprint (Py): Full Feature Spread (Mixture of Experts) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	51.1% · n=45 live · all-time window · n=45	23-22-0	+0.100
[Auto] Blueprint (Py): Full Feature Spread (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	51.1% · n=47 live · all-time window · n=47	24-23-16	+0.381
[Auto] NFL Spread (AdaBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	50.0% · n=42 live · all-time window · n=42	21-21-21	−0.008
[Auto] NFL Minimal Signal Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	50.0% · n=44 live · all-time window · n=44	22-22-19	−0.103
[Auto] Blueprint (Py): Momentum Spread Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	50.0% · n=62 live · all-time window · n=62	31-31-1	−0.167
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	48.9% · n=47 live · all-time window · n=47	23-24-16	−0.135
[Auto] Playbook (Py): Momentum Spread Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	48.9% · n=45 live · all-time window · n=45	22-23-0	+0.044
[Auto] NFL Spread (ExtraTrees) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	48.9% · n=45 live · all-time window · n=45	22-23-0	−0.011
[Auto] NFL Spread (CatBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	48.9% · n=45 live · all-time window · n=45	22-23-0	−0.067
[Auto] NFL Spread (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	48.8% · n=41 live · all-time window · n=41	20-21-22	−0.103
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	48.4% · n=62 live · all-time window · n=62	30-32-1	+0.087
[Auto] Blueprint (Py): Turnover Regression Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	48.4% · n=62 live · all-time window · n=62	30-32-1	+0.056
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	48.4% · n=62 live · all-time window · n=62	30-32-1	−0.040
[Auto] Playbook (Py): Momentum Spread Model (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=29 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	29	48.3% · n=29 live · all-time window · n=29	14-15-0	+0.069
[Auto] Playbook (Py): Feature Store Spread Model (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=29 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	29	48.3% · n=29 live · all-time window · n=29	14-15-0	+0.052
[Auto] Playbook (Py): Full Feature Spread (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=29 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	29	48.3% · n=29 live · all-time window · n=29	14-15-0	+0.052
[Auto] Blueprint (Py): SHAP Explainable Elo Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	47.9% · n=48 live · all-time window · n=48	23-25-15	−0.111
[Auto] Blueprint (Py): Full Feature Spread (XGB) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	47.7% · n=44 live · all-time window · n=44	21-23-19	+0.437
[Auto] NFL MLP Spread insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	47.6% · n=42 live · all-time window · n=42	20-22-21	−0.056
[Auto] NFL Multi-Task Spread insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	46.8% · n=47 live · all-time window · n=47	22-25-16	+0.183
model-1758a821 insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=30 graded spread plays · as of 2026-09-23T05:56:07.815427+00:00	model	30	46.7% · n=30 live · all-time window · n=30	14-16-0	+0.200
[Auto] NFL MLP Spread insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	46.7% · n=45 live · all-time window · n=45	21-24-0	+0.022
[Auto] NFL Spread (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	46.7% · n=45 live · all-time window · n=45	21-24-0	+0.022
[Auto] Blueprint (Py): Full Feature Spread (Mixture of Experts) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	46.2% · n=39 live · all-time window · n=39	18-21-24	+0.087
[Auto] NFL Market Efficiency Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	45.2% · n=42 live · all-time window · n=42	19-23-21	−0.103
model-4cbee016 insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=34 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	34	45.2% · n=31 live · all-time window · n=31	14-17-3	+0.265
[Auto] Playbook (Py): Turnover Regression Model (ElasticNet) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	44.4% · n=45 live · all-time window · n=45	20-25-0	+0.044
[Auto] NFL Spread (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	44.4% · n=45 live · all-time window · n=45	20-25-0	+0.022
[Auto] NFL Spread (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	44.4% · n=45 live · all-time window · n=45	20-25-18	−0.008
[Auto] Playbook (Py): Pressure & Efficiency Model (LightGBM) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	44.4% · n=45 live · all-time window · n=45	20-25-0	−0.089
[Auto] Blueprint (Py): Full Feature Spread (Stacking Ensemble) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	43.9% · n=41 live · all-time window · n=41	18-23-22	+0.087
[Auto] Blueprint (Py): SHAP Explainable Elo Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	43.5% · n=62 live · all-time window · n=62	27-35-1	−0.071
[Auto] Blueprint (Py): Simple Elo Spread Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	43.1% · n=51 live · all-time window · n=51	22-29-12	−0.159
[Auto] NFL Multi-Task Spread insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	42.2% · n=45 live · all-time window · n=45	19-26-0	+0.089
[Auto] Blueprint (Py): Pressure & Efficiency Model (LightGBM) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	42.2% · n=45 live · all-time window · n=45	19-26-0	−0.122
[Auto] Playbook (Py): Simple Elo Spread Model (Bayesian) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	42.2% · n=45 live · all-time window · n=45	19-26-0	−0.122
[Auto] Playbook (Py): SHAP Explainable Elo Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	42.2% · n=45 live · all-time window · n=45	19-26-0	−0.133
[Auto] Blueprint (Py): Simple Elo Spread Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	41.9% · n=62 live · all-time window · n=62	26-36-1	−0.119
[Auto] Blueprint (Py): Simple Elo Spread Model (Bayesian) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	40.5% · n=42 live · all-time window · n=42	17-25-21	−0.111
[Auto] NFL Spread (AdaBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	40.0% · n=45 live · all-time window · n=45	18-27-0	+0.033
[Auto] Sharkai Starter: NFL Spread insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	40.0% · n=45 live · all-time window · n=45	18-27-0	−0.056
[Auto] Playbook (Py): Simple Elo Spread Model (Linear) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=45 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	45	40.0% · n=45 live · all-time window · n=45	18-27-0	−0.067
[Auto] Blueprint (Py): Simple Elo Spread Model (Bayesian) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=63 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	63	39.0% · n=41 live · all-time window · n=41	16-25-22	−0.056
[Auto] NFL Minimal Signal Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=29 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	29	34.5% · n=29 live · all-time window · n=29	10-19-0	−0.052
[Auto] NFL Market Efficiency Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=29 graded spread plays · as of 2026-10-05T04:04:00.21858+00:00	model	29	34.5% · n=29 live · all-time window · n=29	10-19-0	−0.224
[Auto] MLB Run Line (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=115 graded spread plays · as of 2026-05-20T09:00:00.606554+00:00	model	115	—	0-0-115	—
[Auto] MLB Run Line (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=115 graded spread plays · as of 2026-05-20T09:00:00.606554+00:00	model	115	—	0-0-115	—
[Auto] Soccer Spread (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (KNN) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] Soccer Spread (MARS) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=20 graded spread plays · as of 2026-09-02T02:48:08.572892+00:00	model	20	—	0-0-20	—
[Auto] NHL Puck Line (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=7 graded spread plays · as of 2026-08-28T01:40:30.487538+00:00	model	7	—	0-0-7	—
[Auto] NHL Puck Line (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=7 graded spread plays · as of 2026-08-28T01:40:30.487538+00:00	model	7	—	0-0-7	—
[Auto] NBA Elo Power Ratings Spread (XGBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (AdaBoost) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (Gaussian Process) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (HistGradientBoosting) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (KNN) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (MARS) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
[Auto] NBA Spread (SVR) insights_model_leaderboard_mat (prediction_results + predictions, refreshed hourly) · grading batch · n=5 graded spread plays · as of 2026-05-18T09:00:00.585548+00:00	model	5	—	0-0-5	—
Market consensus baseline · bet every favourite nfl_schedules · n=7,308 graded spread plays · as of 2026-10-04	baseline	7,308	48.7% · n=7,108 backtest · all-time window · n=7,108	3462-3646-200	—

The baseline's graded spread plays, ATS spread win rate and W-L-P record all come from nfl_schedules. Its CLV cell stays — because nfl_schedules has no closing-value column.

No phase-1 graded ATS spread join is loaded for: community lens, pundit, crew.

What you’ll see

Access and data readiness

What this page can show you about access, sample size, grading freshness and receipt consistency.

Access state

Anon

Signed out

Receipts + Leaderboard public (that's the marketing); Explore links to Data + saved views · this viewer: signed out

Access state

Trial · paid

Signed out

Explore link-out + saved views + share cards; Me · not this viewer: signed out — the tier is not in this page's payload, so no tier is claimed

Query state

Cold query

4,258 graded plays

receipts query · all-time window · n=4,258 · as of Sep 29, 5:23 PM ET

Sample health

Small n

2 / 4 rows under threshold

Insight widgets · current bake · n=4 widget rows · cells under 50 plays grey with the n; never hidden— lens-hit n=0, calibration-curve n=0

Grading window

Week not graded

50 upcoming games

loadGames · 50-game upcoming window · n=50 considered· last graded Sep 29, 5:23 PM ET

Integrity

Disagreement guard

Agrees

receipts aggregate vs per-market sum · all-time window · n=4,258 · checked this render · last graded Sep 29, 5:23 PM ET

Unlock more Insights tools

Keep exploring for free, or unlock the complete Insights toolkit with Pro.

$1 first week, then $2.99/week.

See Pro

Insights · real claim grader

The graded field: the market, mined

Every pundit claim in the transcript corpus, typed and graded against what actually happened. Who has been right, who has enough evidence to judge, and where the observed field sits against the house sample and fade gates.

public.pundit_claim_grades public.pundit_claims · transcript-backed public.pundits.kind=real correct + wrong denominator

22 decided grades across 1 real sources · all-time window · small n is labeled as such. Coverage: top-decile and quadrant labels describe only the currently graded field, not ungraded or unresolved calls.

Claims graded as of Oct 5, 3:54 AM ET · Source registry as of Oct 5, 3:15 AM ET

Pundit claim grading

newest 6 decided claims · same rows as the ledger

Claim	Source	Verdict
“I still think that the Rams have a better chance because of their consistency.”	Ben Solak (The Football Show) · Oct 29	wrong
“I'm gonna pick the Raiders.”	Ben Solak (The Football Show) · Oct 29	wrong
“Speaker picks the Bengals to win over the Patriots.”	Ben Solak (The Football Show) · Oct 29	wrong
“The Patriots really don't got a lot going for them it seems.”	Ben Solak (The Football Show) · Oct 29	correct
“I think the Eagles have together more, they worked together as a team better.”	Ben Solak (The Football Show) · Oct 29	correct
“I think that they are more cohesive and two, just more talented than the Jaguars.”	Ben Solak (The Football Show) · Oct 29	correct

Pundit ledger

Decided, transcript-backed calls by real source. Pushes and unresolved claims never enter the hit-rate denominator.

pundit_claim_grades pundit_claims · transcript evidence pundits.kind=real

Source	W-L	Hit %	n	Window	Verdict
Ben Solak (The Football Show)	13-9	59.1%	22	all-time	hot

22 decided grades across 1 real sources · all-time window

Verdict rules: unproven below n=20; gasbag below 45% after the gate; hot is the top decile of the gated field. With a thin gated field, hot is field-relative coverage, not a claim about ungraded calls.

Gasbag quadrant

More decided claims move right; a higher correct/wrong hit rate moves up. Every dot is a directly labeled real source.

pundit_claim_grades correct + wrong only all-time

Counterfactual boundary: the guide lines classify observed grades only; they do not infer how a source would have performed on unresolved or unmade calls.