ILLUSTRATIVE · NASA / SVS · NOT ADITYA-L1 DATA
Model cardsrandom
Model card · reference point
Random
Assigns a uniform random score to every minute.
What is this?
A model card for Random, one of eight detectors evaluated on the frozen Aditya-L1 flare benchmark.
Why should I trust it?
Every figure below is read at build time from the committed benchmark artifact; none is transcribed. The judgements are traceable to the written evaluation protocol and the dataset limitations record.
Where can I verify it?
- The validation evidenceComputed from 192,541 held-out predictions
- Dataset limitationsL-1 … L-10
- Evidence traceabilityclaim → artifact → commit
- The raw payloadfindings/models.json
Section 1
Purpose and intended use
Why it is in the benchmark. The floor. Any detector that does not clear this is measuring nothing.
Intended use. Reference point only.
Out of scope. Everything else.
Section 2
Inputs, outputs, training
Inputs. None.
Outputs. A uniform random score per minute.
Training protocol. None.
Operating point. Decision threshold 0.5000, selected on the training period and then frozen.
Section 3
Evaluation
Both tasks, both reported.
M/X NOWCAST · 192,541 held-out minutes · base rate 1.24%
| Metric | Value | What it measures |
|---|---|---|
| ROC-AUC | 0.497 | Ranking quality across all thresholds |
| PR-AUC | 0.012 | The informative curve at a low base rate |
| Precision | 0.012 | Of the minutes flagged, how many were flares |
| Recall | 0.501 | Of the flare minutes, how many were flagged |
| F1 | 0.024 | Harmonic mean of the two above |
| MCC | -0.000 | Correlation, robust to imbalance |
| Brier | 0.334 | Probability accuracy; undefined for hard classifiers |
| Balanced accuracy | 0.500 | Mean of the two class recalls |
- Events detected
- 81 / 82
- Event recall 0.988 · 95% CI 0.978–1.000
- False alarm runs
- 47,595
- Of 48,204 alarm runs raised. A run, not a minute — the unit an operator actually responds to.
- ROC-AUC interval
- 0.483–0.509
- 95%, day-block bootstrap.
M/X 30-MIN PREDICTION · 192,541 held-out minutes · base rate 1.29%
| Metric | Value | What it measures |
|---|---|---|
| ROC-AUC | 0.493 | Ranking quality across all thresholds |
| PR-AUC | 0.013 | The informative curve at a low base rate |
| Precision | 0.013 | Of the minutes flagged, how many were flares |
| Recall | 0.485 | Of the flare minutes, how many were flagged |
| F1 | 0.024 | Harmonic mean of the two above |
| MCC | -0.004 | Correlation, robust to imbalance |
| Brier | 0.334 | Probability accuracy; undefined for hard classifiers |
| Balanced accuracy | 0.492 | Mean of the two class recalls |
- Events detected
- 82 / 82
- Event recall 1.000 · 95% CI 1.000–1.000
- False alarm runs
- 47,578
- Of 48,204 alarm runs raised. A run, not a minute — the unit an operator actually responds to.
- ROC-AUC interval
- 0.483–0.507
- 95%, day-block bootstrap.
Confusion matrix · M/X NOWCAST
True negative
94,894
False positive
95,254
False negative
1,195
True positive
1,198
Section 4
Strengths and failure modes
Strengths
- Establishes what chance performance looks like at this base rate.
Failure modes
- It is chance.
Section 5
Limitations and ethical considerations
Ethical considerations. None — it is a ruler, not a detector.
Governing limitation clauses
None recorded. This model is a reference point rather than a candidate, so the dataset's constraints on modelling do not bind it.
Clause text is not restated here. It is published in full on the dataset card, from the frozen DATASET_LIMITATIONS_FOR_ML.md report, so there is exactly one copy of every caveat.