# Mislabel detection on Weak Reference Labels Mislabels Source: [Mislabel detection on Weak Reference Labels Mislabels]() Collection index: [llms.txt]() Data updated: 2026-06-01T07:34:16.441Z Evaluation of model performance in detecting mislabels using Average Precision (AP), Precision@100, and Precision@200 on the Weak Reference Labels Mislabels dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Mislabel detection | | Dataset (including any stated split) | Weak Reference Labels Mislabels | | Metric | AP | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [AP](): Higher is better; unit: PERCENT. - [Precision@100](): Higher is better; unit: PERCENT. - [Precision@200](): Higher is better; unit: PERCENT. ## Recorded results | Method | AP | Result date | Report paper | | --- | --- | --- | --- | | 4PL Δℓi (proposed) | 84.3 | Not recorded | 6a1d1206dbd7150506f83f1a | | top-10 disagreement | 76.1 | Not recorded | 6a1d1206dbd7150506f83f1a | | plain 4PL, single-stage (low di) | 71.8 | Not recorded | 6a1d1206dbd7150506f83f1a | | XGBoost (4PL params) | 71.7 | Not recorded | 6a1d1206dbd7150506f83f1a | | 4PL, low di | 70.3 | Not recorded | 6a1d1206dbd7150506f83f1a | | low ri | 69.4 | Not recorded | 6a1d1206dbd7150506f83f1a | | plain 2PL (low ai) | 64.2 | Not recorded | 6a1d1206dbd7150506f83f1a | | GLAD | 62.2 | Not recorded | 6a1d1206dbd7150506f83f1a | | overall disagreement | 53.3 | Not recorded | 6a1d1206dbd7150506f83f1a | ### 4PL Δℓi (proposed) AP: 84.3. Result ID: 6a1d347dfbc373592c1601a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Criterion":"Forced-ceiling likelihood ratio"}. This record does not assert independent reproduction. ### top-10 disagreement AP: 76.1. Result ID: 6a1d347dfbc373592c1601a7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### plain 4PL, single-stage (low di) AP: 71.8. Result ID: 6a1d347dfbc373592c1601ac. [Reporting paper]() Recorded evaluation configuration: {"Model":"4PL","Protocol":"single-stage","Selection":"low difficulty"}. This record does not assert independent reproduction. ### XGBoost (4PL params) AP: 71.7. Result ID: 6a1d347dfbc373592c1601a8. [Reporting paper]() Recorded evaluation configuration: {"Model":"XGBoost","Features":"4PL parameters"}. This record does not assert independent reproduction. ### 4PL, low di AP: 70.3. Result ID: 6a1d347dfbc373592c1601a9. [Reporting paper]() Recorded evaluation configuration: {"Model":"4PL","Selection":"low difficulty"}. This record does not assert independent reproduction. ### low ri AP: 69.4. Result ID: 6a1d347dfbc373592c1601aa. [Reporting paper]() Recorded evaluation configuration: {"Selection":"low response probability"}. This record does not assert independent reproduction. ### plain 2PL (low ai) AP: 64.2. Result ID: 6a1d347dfbc373592c1601ad. [Reporting paper]() Recorded evaluation configuration: {"Model":"2PL","Selection":"low discrimination"}. This record does not assert independent reproduction. ### GLAD AP: 62.2. Result ID: 6a1d347dfbc373592c1601ae. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### overall disagreement AP: 53.3. Result ID: 6a1d347dfbc373592c1601ab. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.