Skip to content

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?

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%

MetricValueWhat it measures
ROC-AUC0.497Ranking quality across all thresholds
PR-AUC0.012The informative curve at a low base rate
Precision0.012Of the minutes flagged, how many were flares
Recall0.501Of the flare minutes, how many were flagged
F10.024Harmonic mean of the two above
MCC-0.000Correlation, robust to imbalance
Brier0.334Probability accuracy; undefined for hard classifiers
Balanced accuracy0.500Mean 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%

MetricValueWhat it measures
ROC-AUC0.493Ranking quality across all thresholds
PR-AUC0.013The informative curve at a low base rate
Precision0.013Of the minutes flagged, how many were flares
Recall0.485Of the flare minutes, how many were flagged
F10.024Harmonic mean of the two above
MCC-0.004Correlation, robust to imbalance
Brier0.334Probability accuracy; undefined for hard classifiers
Balanced accuracy0.492Mean 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.