OrganoidBench
Benchmarks

Tracks

Each track covers a different part of organoid electrophysiology or closed-loop behavior.

Track 01

Signal Quality

Electrophysiological recording fidelity from the preparation: SNR, channel yield, spike sortability.

0 runs
Metrics
  • Spike SNR
  • Active channel ratio
  • Sorted units per array
  • ISI violation rate
Tasks
  • Baseline recording
  • Stimulated recording
A closed-loop system cannot score above its recording floor. Signal quality is the baseline precondition for every downstream claim.
Track 02

Responsiveness

Does input change output? Evoked response magnitude, latency, and selectivity under matched controls.

0 runs
Metrics
  • Evoked response effect size
  • Response latency
  • Pattern selectivity
Tasks
  • Evoked vs sham
  • Pattern discrimination
Responsiveness separates preparations that merely produce spontaneous activity from those whose activity is contingent on input.
Track 03

Plasticity

Does repeated input durably change the input-to-output mapping? Open-loop plasticity with matched controls.

0 runs
Metrics
  • Paired vs unpaired delta
  • Induction half-life
Tasks
  • Paired induction
Plasticity is the mechanistic substrate any learning claim depends on. Without paired/unpaired controls, drift and adaptation look identical.
Track 04

Closed-Loop Learning

Task performance under stimulus-contingent feedback, versus matched no-feedback control.

0 runs
Metrics
  • Terminal performance delta
  • Learning curve AUC
Tasks
  • Closed-loop Pong-like task
  • Closed-loop 2AFC
Closed-loop performance improvement (vs control) is the field's operational definition of stimulus-contingent adaptation at the task level. Not a claim about internal cognition.
Track 05

Retention

Does an induced change persist? Re-test at fixed delays against matched pre-induction baseline.

0 runs
Metrics
  • Retention at 1h
  • Retention at 24h
  • Retention at 7d
Tasks
  • Delayed retest
Retention is how a plasticity or learning claim transitions from 'change' to 'memory'. Requires specified delays and no intervening exposure.
Track 06

Reproducibility

Are results stable across batches and labs? Within-lab and cross-lab coefficient of variation on headline metric.

0 runs
Metrics
  • Within-lab CV
  • Cross-lab CV
  • Independent replications
Tasks
  • Replication panel
Per-track scores without reproducibility data hide cross-batch variance. This track is a first-class citizen, not a footnote.