How right is the AI?
7 recordings, 824 clips with a human verdict. Last experiment logged Sep 11, 2026.
By recording
- Open review
Solo shooting, 15 June
SoloJun 15, 2026 · 12:21 of footage · 75 candidates
75 / 75 reviewed100%- Real shots among proposals
- 100%n=75
- Made/miss accuracy
- 93%n=75
made as positive:Precision 86%Recall 100%F1 93%
- Shooter agreement
- not yet
- Review speed
- 7.4sper shot
- Open review
Solo shooting, 3 June
SoloJun 3, 2026 · 31:17 of footage · 238 candidates
238 / 238 reviewed100%- Real shots among proposals
- 84%n=237
- Made/miss accuracy
- 89%n=198
made as positive:Precision 79%Recall 96%F1 86%
- Shooter agreement
- not yet
- Review speed
- 6.7sper shot
- Open review
2v2, Hunters Hill, 18 Jan
Small-sidedJan 18, 2026 · 18:44 of footage · 83 candidates · 4 filtered
83 / 83 reviewed100%- Real shots among proposals
- 77%n=82
- Made/miss accuracy
- 87%n=63
made as positive:Precision 76%Recall 96%F1 85%
- Shooter agreement
- 96%n=49
- Review speed
- 8.3sper shot
- Open review
Half-court pickup, 29 Mar
PickupMar 29, 2026 · 55:03 of footage · 367 candidates
238 / 367 reviewed65%- Real shots among proposals
- 61%n=232
- Made/miss accuracy
- 93%n=142
made as positive:Precision 88%Recall 97%F1 92%
- Shooter agreement
- not yet
- Review speed
- 8.4sper shot
Over time
226 logged runs from the experiment ledger. Tap a dot for the method and cost.
- game-eltham-1
- game_hd 2v2
- Solo shooting, 15 June
- other
Shot recall
30 runsShot precision
30 runsShot F1
29 runsAccuracy
86 runsMade/miss accuracy
1 runCandidate recall (5s)
18 runsCV-A accuracy
30 runsMade/miss AUC
2 runsHow to read this
A clip's human verdict is the strict majority of its reviewers; ties count as split and drop out of every rate. Shot precision is the share of reviewed candidates that were real shots. Made/miss numbers compare the AI's call with that verdict, with "made" as the positive class, so precision is "when the AI says made, was it" and recall is "of the real makes, how many did it call". Recall of shots themselves is only measured where a recording has an audit game, a continuous interval cut into windows that a human labelled end to end; the other recordings show it as unmeasured.