aetre
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| aetre_system_catalogB | Comprehensive system introspection returning AETRE architecture, bundled synthetic fixtures, optional data adapters, connectors, mathematical tools, and institutional tiers. |
| aetre_triage_proposalB | Applies transparent, uncalibrated lexical routing indicators to proposal text, then calculates a VOI index and demonstration stage route (FAST-PASS, FAST-REJECT, or DEEP REVIEW). Not a validated estimate of scientific quality. |
| aetre_calculate_voiA | Calculates the exact Bayesian Value of Information (VOI) for crossing a top-K selection boundary under Gaussian conjugate updates. |
| aetre_check_governorA | Evaluates evaluator queue load using Kingman's Heavy-Traffic approximation and returns governor throttle recommendations when utilization exceeds rho >= 0.85. |
| aetre_exploration_auditB | Calculates the unbiased Horvitz-Thompson exploration audit estimator (H_hat_D) and 95% confidence intervals on deprioritized candidates to catch false negative breakthroughs. |
| aetre_evaluate_stakingC | Simulates submitter entry equilibrium under generative AI generation costs and refundable submission deposits to curb spam floods. |
| aetre_proposition_1_boundB | Calculates Proposition 1 theoretical recall ceiling R_N <= min(1, K_N / H_N) to determine if a pipeline is mathematically capacity-constrained. |
| aetre_correlated_posterior_updateA | Calculates Bayesian posterior mean and uncertainty under correlated multi-agent evaluator noise (rho_corr), preventing artificial overconfidence from redundant LLM outputs. |
| aetre_heavy_tailed_voiB | Calculates Generalized Pareto / Heavy-Tailed Value of Information (VOI) to optimize selection pipelines for positive black swan breakthrough discovery. |
| aetre_quadratic_stakingA | Calculates super-linear anti-sybil staking deposit requirements (Stake(m) = S_0 * m^gamma) to deter mass AI spam submissions while preserving human entry. |
| aetre_heterogeneous_queuesB | Evaluates a multi-specialist heterogeneous reviewer network, identifying bottleneck domains and generating capacity rebalancing actions. |
| aetre_author_preflight_benchmarkC | Comprehensive pre-submission diagnostic scorecard for authors and researchers, calculating crowd novelty percentile, reviewer disagreement risk, and prescriptive refinement actions. |
| aetre_simulate_benchmarkC | Runs a paired-cohort Monte Carlo simulation across all 4 screening regimes, comparing Quality Throughput, FDR, Unconventional Recall, and Human Reviews with central 95% run-to-run outcome intervals (not confidence intervals for the mean). |
| aetre_batch_triageC | Batch applies disclosed, uncalibrated lexical indicators to a cohort, computing heuristic ranks, VOI ranks, and demonstration stream allocation (Stream A Fast-Reject, Stream B Deep Review, Stream C Fast-Pass). |
| aetre_recall_scaling_curveA | Calculates the Proposition 1 theoretical recall decay curve across arrival expansion scales (e.g. 1x, 2x, 5x, 10x, 20x, 50x) demonstrating capacity collapse points. |
| aetre_heldout_backtestC | Runs a multi-policy held-out review allocation backtest across 8 triage policies under fixed review budget K, evaluating true decision flips, precision, recall, and paired bootstrap intervals. |
| aetre_calibrate_scorerA | Fits Platt logistic scaling on continuous model scores and binary labels, returning slope, intercept, Expected Calibration Error (ECE), and Brier score. |
| aetre_multi_attribute_voiC | Computes multi-attribute Bayesian Value of Information across orthogonal proposal evaluation dimensions (Novelty, Rigor, Impact, Feasibility), outputting composite VOI and optimal dimension-specific review targets. |
| aetre_congestion_matchingA | Optimizes reviewer-to-proposal assignment by maximizing domain/keyword affinity while enforcing Kingman queue utilization constraints (rho <= 0.85) on individual reviewer workloads. |
| aetre_sequential_stopping_ruleC | Calculates optimal dynamic Bayesian stopping boundaries for sequential reviews (Accept, Reject, or Solicit More Reviews) based on posterior decision confidence and boundary VOI. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| author_preflight_review | Pre-submission diagnostic flight simulator: benchmarks paper draft against crowd distributions, flags reviewer split risks, and provides a prescriptive variance reduction plan. |
| pipeline_congestion_audit | Audits review pipeline traffic intensity, wait times, and backlog under Kingman's Heavy-Traffic approximation. |
| multi_agent_panel_debiasing | Debiases multi-LLM reviewer panels by computing effective evaluator sample size (M_eff) under shared training correlation. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| AETRE Benchmark Dataset Catalog | Catalog of bundled synthetic fixtures and optional external-data adapters. |
| AETRE SQL Database Write-Back Schema | SQL DDL and column definitions for PostgreSQL/SQLite/Snowflake write-back integration. |
| Mathematical & Operations Research Specifications | Core formulas: Proposition 1 Bound, Kingman Heavy-Traffic, Gaussian & Pareto VOI, Horvitz-Thompson Estimator. |
| 7 Institutional Deployment Tiers Matrix | Cross-tier institutional matrix: Authors, VCs, Publishers, Grant Agencies, Patent Offices, Corporate R&D, Accelerators. |
TDQS
Scored across 20 tools
Each tool targets a distinct mathematical or operational aspect of the review/triage pipeline, from VOI calculations to staking and congestion management. Even similar tools like aetre_calculate_voi, aetre_heavy_tailed_voi, and aetre_multi_attribute_voi are clearly differentiated by their specific model variants and outputs, eliminating ambiguity.
All tools share the 'aetre_' prefix and follow a consistent snake_case verb_noun or noun_modifier pattern (e.g., 'calculate_voi', 'check_governor', 'system_catalog'). While verbs vary (calculate, check, evaluate, simulate), the naming is uniform and predictable, making tool selection straightforward.
With 20 tools, the set is on the heavier side, but the complexity of the domain (a full simulation and optimization system for scientific review) justifies this count. Each tool addresses a specific functional need, and the server is well-scoped; it would be difficult to reduce the count without losing essential capabilities.
The tool surface covers the major lifecycle stages of the pipeline: triage, VOI, staking, queue analysis, backtesting, calibration, and simulation. Minor gaps exist, such as no explicit tool for managing data inputs/outputs or handling individual review assignments, but these are likely handled by the system catalog and other core functions. Overall, the set is comprehensive for its stated purpose.