Model card: full-panel top-k coverage (R3.5)
Browse files
README.md
CHANGED
|
@@ -105,10 +105,7 @@ recall-favouring edge of the plateau (0.9 -> 0.95 would trade 1.9 points of in-s
|
|
| 105 |
and 6 points of test recall for +1.6 points of benchmark precision and 13% fewer false
|
| 106 |
fires). Test-set P/R at 0.9: 0.938 / 0.900 (3-seed means).
|
| 107 |
|
| 108 |
-
Top-k coverage of the true entry (test positives): within each abstract's gene-gate
|
| 109 |
-
candidates (the deployment universe, median 2 candidates) top-1 = 0.797 ± 0.013; against the
|
| 110 |
-
279-entry test-set pool top-1 = 0.870, top-3 = 1.00. Full 2,861-entry panel numbers are in
|
| 111 |
-
the repository's `revision/crossencoder_topk_coverage.csv`.
|
| 112 |
|
| 113 |
## Provenance
|
| 114 |
|
|
|
|
| 105 |
and 6 points of test recall for +1.6 points of benchmark precision and 13% fewer false
|
| 106 |
fires). Test-set P/R at 0.9: 0.938 / 0.900 (3-seed means).
|
| 107 |
|
| 108 |
+
Top-k coverage of the true entry (held-out test positives, fp32): against the **full 2,861-entry panel** top-1 = 0.818, top-3 = 0.991, top-5 = 1.00 (previous release 0.818 / 0.991 / 1.00; untrained MedCPT 0.713 / 0.924 / 0.953; the submitted manuscript's Table 2 reported 0.76 / 0.97 / 0.99 as 5-fold CV means); against the 279-entry test-set pool top-1 = 0.870, top-3 = 1.00; within each abstract's own gene-gate candidates (the deployment universe, median 2 candidates) top-1 = 0.797 ± 0.013. Full table: the repository's `revision/crossencoder_topk_coverage.csv`.
|
|
|
|
|
|
|
|
|
|
| 109 |
|
| 110 |
## Provenance
|
| 111 |
|