| { |
| "prompt": 2, |
| "orders": 1, |
| "method": "temperature per question type and per option-count bucket (choice), by NLL, fitted on the out-of-distribution calibration split only; thresholds per type: the most permissive threshold whose accepted calibration decisions have a one-sided 95% Clopper-Pearson upper bound <= max_error; a type without one defers", |
| "temperature_per_prim": { |
| "choice": 1.3939382634489992, |
| "noul": 2.82842712474619, |
| "score": 2.44810708660931 |
| }, |
| "temperature_per_bucket": { |
| "choice": { |
| "2-10": 1.8340080864093422, |
| "11-26": 1.241857812073484, |
| "27-255": 1.059463094359295 |
| } |
| }, |
| "thresholds": { |
| "0.01": { |
| "confidence": null, |
| "method": "per type: the most permissive threshold whose accepted calibration decisions have a one-sided 95% Clopper-Pearson upper bound <= max_error; a type without one defers", |
| "per_type": { |
| "choice": { |
| "confidence": null, |
| "heldout_coverage": 0.0, |
| "heldout_error": null |
| }, |
| "noul": { |
| "confidence": null, |
| "heldout_coverage": 0.0, |
| "heldout_error": null |
| }, |
| "score": { |
| "confidence": null, |
| "heldout_coverage": 0.0, |
| "heldout_error": null |
| } |
| }, |
| "heldout_coverage": 0.0, |
| "heldout_error": null |
| }, |
| "0.05": { |
| "confidence": null, |
| "method": "per type: the most permissive threshold whose accepted calibration decisions have a one-sided 95% Clopper-Pearson upper bound <= max_error; a type without one defers", |
| "per_type": { |
| "choice": { |
| "confidence": 0.9322699589043795, |
| "heldout_coverage": 0.3940542361462018, |
| "heldout_error": 0.023936738619363074 |
| }, |
| "noul": { |
| "confidence": 0.8915736513972552, |
| "heldout_coverage": 0.37426679280983915, |
| "heldout_error": 0.020222446916076886 |
| }, |
| "score": { |
| "confidence": null, |
| "heldout_coverage": 0.01175285426460712, |
| "heldout_error": 0.22857142857142854 |
| } |
| }, |
| "heldout_coverage": 0.33232358345334456, |
| "heldout_error": 0.02390914524805743 |
| } |
| }, |
| "gates": { |
| "ece_lofo": { |
| "choice": { |
| "pooled": 0.012308234464218113, |
| "n": 11874, |
| "gate": 0.05, |
| "pass": true |
| }, |
| "noul": { |
| "pooled": 0.03186722948382228, |
| "n": 5285, |
| "gate": 0.05, |
| "pass": true |
| }, |
| "score": { |
| "pooled": 0.030276060779249152, |
| "n": 2978, |
| "gate": 0.05, |
| "pass": true |
| } |
| }, |
| "ece_worst_fold": 0.1014424717632049, |
| "worst_fold": "agent", |
| "automated_at": { |
| "0.01": 0.0, |
| "0.05": 0.33232358345334456 |
| }, |
| "automated_error": { |
| "0.01": null, |
| "0.05": 0.02390914524805743 |
| }, |
| "note": "held-out numbers: every evaluation row predicted by the fit without its family" |
| }, |
| "test": { |
| "T": { |
| "choice": { |
| "acc": 0.7870136432541688, |
| "ece": 0.014067322629837065, |
| "n": 11874 |
| }, |
| "noul": { |
| "acc": 0.8306527909176916, |
| "ece": 0.03343366640192696, |
| "n": 5285 |
| }, |
| "score": { |
| "acc": 0.6040967092008059, |
| "ece": 0.02988934980023047, |
| "n": 2978 |
| }, |
| "all": { |
| "acc": 0.771415801757958, |
| "ece": 0.01582616023538169, |
| "n": 20137 |
| } |
| }, |
| "note": "evaluation pool (development and test splits), full fit" |
| }, |
| "n": { |
| "fit": 3560, |
| "many": 1500, |
| "eval": 20137 |
| }, |
| "engine": "fast", |
| "fitted_on": { |
| "split": "out-of-distribution calibration split (sealed-seed BH-, JDI- and agent-shaped families, many-option items)", |
| "orders": 1, |
| "readouts": "basal-serve --mode fast, bf16" |
| }, |
| "certified_on": "the same split", |
| "evaluated_on": "development and test splits, leave-one-family-out and leave-one-language-out" |
| } |
|
|
