Insights · corpus rollup
What the MESSAI corpus says
Reporting completeness, calibrated prediction intervals, anomalous papers, discovered laws, learned causal edges, and cross-system transfers — sourced from the trainer’s most recent published artifacts. Each panel reports its own status; nothing is silently zeroed out.
Reporting completeness
23.1% corpus average · 289 scored papers · 10,824 indexed across 5 system types
Corpus average
23.1%
reporting completeness
MFC mean
8.7
params reported per paper
MEC mean
3.6
params reported per paper
| System | Papers | Electrode specs | Operating conds | Electrical meas | Bio | Data rep |
|---|---|---|---|---|---|---|
| MFC | 3,847 | 72% | 58% | 45% | 35% | 32% |
| MES | 4,842 | 68% | 55% | 42% | 32% | 28% |
| BES | 1,096 | 65% | 48% | 38% | 28% | 25% |
| MEC | 966 | 70% | 52% | 40% | 30% | 28% |
| MDC | 73 | 55% | 38% | 28% | 20% | 15% |
Source: ISMET 2026 abstract Fig 2A. Live corpus-rollup endpoint pending.
Calibration health
Awaiting trainer export
research/calibration.json not yet published by trainer
Run services/ml-engine/training/calibration.py to publish.
Prior-trust distribution
102 fitted parameters · median 20 papers · max 367
8
8% of params
20
20% of params
71
70% of params
3
3% of params
Papers per parameter
Number of parameters with N supporting papers. Higher bins = stronger priors.
Top calibrated parameters
- power_density_arealn=367
- current_density_arealn=274
- powerDensityn=162
- internal_resistancen=151
- relative_abundancen=52
Flagged parameters (caveat the value)
8% of canonical parameters meet the calibrated threshold (PPC + LOO + convergence all pass). Paper-level reproducibility-score distribution (the 289-paper analysis in the abstract) is tracked as a post-launch trainer pass.
Anomalous papers
Run services/ml-engine/training/score_anomalies.py to publish.
Learned causal edges
1 candidate edge · HillClimbSearch + BICScore · 173 papers
powerDensitycurrentDensity
Discovered symbolic laws
2 successful fits · PySR (Cranmer 2023) — symbolic regression
powerDensityvs.currentDensityMFC · n=51(x0 + (0.22200376 / ((x0 + 2.3158035) * -1.8066067))) - 0.6148749
Logan 2008 §3.4: P = V·I. At matched load V≈V_oc/2 ≈ const → P ∝ I
loss = 0.2252 · complexity = 11 · R² ≈ 0.198
coulombic_efficiencyvs.cod_removalMFC · n=29((x0 + -0.19921306) / ((x0 + (x0 + 0.46581972)) / 0.0033559396)) + -1.308836
Sleutels 2012 §4: at high COD-removal, more substrate goes to biomass (not e-) → CE drops
loss = 0.4429 · complexity = 13 · R² ≈ 0.210
Cross-system transfers
64 viable transfers · 26 within-system pairs analysed
| Parameter | Source | Target | n samples |
|---|---|---|---|
| powerDensity | MFC | MSC | 5 |
| powerDensity | MFC | OTHER | 5 |
| powerDensity | MFC | REVIEW | 5 |
| powerDensity | MSC | MFC | 5 |
| powerDensity | MSC | OTHER | 5 |
| powerDensity | MSC | REVIEW | 5 |
58 more transfers not shown.
Generated 2026-05-10