Each stage is explicit so the record can change without erasing what came before.
Define the investment question, current view, horizon, assumptions, drivers, and observable conditions.
Bring new evidence and changed conditions back against the preserved view.
Make Maintain, Revise, or Retire an explicit human decision rather than a silent rewrite.
Keep prior states, finalized decisions, provenance, and version history.
Observation, reassessment, human governance, and resolution are recorded separately. Their cadence depends on the record type rather than one universal daily schedule.
Evidence, model reads, and governed factor observations are timestamped when they enter the record according to the relevant workflow.
A Thesis, Factor, or Scenario can be reassessed against new information while its prior version remains available for comparison.
Structural changes and finalized decisions require explicit human action and are preserved with their rationale and resulting state.
Where a resolvable forecast exists, the recorded outcome updates scoring, calibration, and the forward measurement record.
Crene evaluates the latest thesis state against preset detector rules. The public language is constrained to what the evidence actually establishes.
Several important assumptions move materially in the same direction during the review window.
An assumption important to the decision moves quickly while the model ensemble remains materially divided.
The headline spread appears tighter than disagreement across important assumptions underneath it.
Support and resistance move inside the same mechanism, including asymmetric tilts.
A disproportionate share of weighted support comes from one mechanism or narrative cluster.
Underlying conditions move materially while the anchor remains comparatively unchanged.
Findings are ranked by detector score, decision weight, movement, spread, and mechanism coverage. Type caps prevent one detector from filling the entire public set. The selected findings can therefore change from one daily run to the next as the thesis state changes.
Suggested actions are constrained to research, review, escalation, and thesis maintenance. They are not portfolio instructions.
A detector establishes an observable pattern in the thesis map.
A constrained rule proposes a research or review step tied to the detected pattern.
Plausible branches explain how the thesis state would change under different resolutions.
Each branch identifies the evidence that would make that resolution more consistent with the observed record.
The action layer does not recommend buying, selling, hedging, or position sizing. Portfolio decisions require mandate, exposure, liquidity, risk, and correlation context that the public thesis page does not possess.
Timestamped inputs, versioned structure, finalized decisions, and frozen review states preserve what was known, what changed, and what the team chose at the time.
A completed weekly record preserves consensus, available model reads, spread, movement, freshness, and the active structure reference.
Promoted assumption, taxonomy, pathway, or relationship changes create a new structure version with a changelog.
A native weekly freeze records what the system said during that week. It does not resample or substitute a later answer.
These figures are loaded from the live Crene APIs. Counts change as questions resolve and scenario, cluster, and factor records are updated.
Active binary anchors and assumptions are supplied by the live analytics API.
Preserved scenario maps with API supplied component and pathway coverage.
Earlier short horizon events resolved against named sources and included in the scoring layer.
Claude, GPT, Gemini, and Grok are polled without seeing one another.
Crene's resolved scoring corpus comes from an earlier phase focused on short horizon events. It demonstrates that the forecasting pipeline operates end to end, from advance question definition and independent model polling through source governed resolution and scoring. It does not establish the accuracy of Crene's current long horizon thesis maps, which are a different question class and are now building their own forward record.
| Metric | Current value | Population | Purpose |
|---|---|---|---|
| Leakage controlled consensus | — | n=— | Tests ensemble calibration against a — base rate Brier. Reported skill: —. |
| Macro ex earnings | 0.2296 | n=333 | Supplementary evidence for a thinner macro population. Reported separately from the leakage controlled benchmark. |
Timestamped probabilities, resolved outcomes, Brier scores, calibration bins, movement, model spread, detector inputs, governed decisions, version history, and frozen review records.
Assumption maps, mechanisms, pathways, driver families, authored relationships, ontology fields, and editorial taxonomies.
Whether daily movement contains incremental decision value, whether detector findings improve outcomes, and whether disagreement across models predicts realized uncertainty.
Crene uses Theses for binary conviction, Factors for continuous variables, and Scenarios for multiple coherent futures. Each record can be reassessed, versioned, governed, and preserved without pretending the three question shapes are identical.
A binary investment thesis is decomposed into governed, falsifiable assumptions grouped by mechanisms or categories.
A continuous anchor is represented as model percentile distributions and a driver matrix.
A strategic question is represented as multiple internally coherent pathways rather than one compressed probability.
Inspect a live thesis, review the resolved corpus, or see the broader map of scenarios and factors.