# wyze69-sys/quantara architecture

> Architecture diagram of the GitHub repository wyze69-sys/quantara, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/wyze69-sys/quantara
- Repository: https://github.com/wyze69-sys/quantara

## Overview

Quantara is archived research infrastructure for testing preregistered market-data features, not a trading or production-execution system. Its principal workflow acquires and verifies source data, builds canonical series and derived research tables, constructs validation folds, then trains candidates and evaluates them under frozen protocols. Supporting branches cover immutable publication and provenance, protocol-defined features and labels, and deterministic estimators. The README documents additional protocol versions and estimator families; their detailed wiring is not fully visible in the sampled source, so uncertain links are marked dashed or omitted.

Main entry points: [`src/quantara/research/pipeline.py`](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/research/pipeline.py) (Feature research table), [`src/quantara/publication.py`](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/publication.py) (Immutable publication), [`src/quantara/data_foundation/pipeline.py`](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/pipeline.py) (Data foundation pipeline), [`src/quantara/series/pipeline.py`](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series/pipeline.py) (Series ingestion)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_foundation["Data foundation"]
  node_acquisition["Archive acquisition<br/>[acquisition.py]"]
  node_descriptors["Descriptors and rights<br/>[descriptor.py]"]
  node_canonical["Canonical rows<br/>[canonical.py]"]
  node_hashing["Identity hashing<br/>[hashing.py]"]
  node_jcs["Canonical JSON<br/>[jcs.py]"]
  node_quality["Quality approval"]
  node_publication[("Immutable publication<br/>[publication.py]")]
  node_data_pipeline["Data foundation pipeline<br/>[pipeline.py]"]
  node_rust_kernel["Hash kernel<br/>[lib.rs]"]
end

subgraph group_series["Market series"]
  node_series_pipeline["Series ingestion<br/>[pipeline.py]"]
  node_series_canonical["Canonical series"]
  node_series_parsing["Series parsing<br/>[parsing.py]"]
end

subgraph group_tables["Research tables"]
  node_derivation["Series derivation<br/>[pipeline.py]"]
  node_research["Feature research table<br/>[pipeline.py]"]
end

subgraph group_modeling["Modeling and evaluation"]
  node_validation["Walk-forward validation<br/>[pipeline.py]"]
  node_training["Model training<br/>[pipeline.py]"]
  node_estimators["Deterministic estimators<br/>[estimator_c3.py]"]
  node_logistic["Logistic IRLS"]
  node_evaluation["Feature evaluation<br/>[pipeline.py]"]
end

subgraph group_protocols["Frozen protocols"]
  node_features["Protocol features"]
  node_labels["Protocol labels<br/>[protocol_labels.py]"]
  node_protocol_run["Protocol run<br/>[protocol_run.py]"]
  node_protocol_eval["Protocol evaluation"]
  node_v2_orchestrator["V2 candidates"]
end

node_researcher(("Researcher"))

node_researcher -.->|"runs ingestion"| node_data_pipeline
node_data_pipeline -->|"acquires archives"| node_acquisition
node_data_pipeline -->|"normalizes data"| node_canonical
node_data_pipeline -->|"checks quality"| node_quality
node_data_pipeline -->|"publishes artifacts"| node_publication
node_acquisition -->|"validates against"| node_descriptors
node_acquisition -->|"verifies bytes"| node_hashing
node_canonical -->|"uses identity"| node_descriptors
node_canonical -.->|"defines content for"| node_hashing
node_hashing -->|"canonicalizes with"| node_jcs
node_series_pipeline -->|"reuses acquisition"| node_acquisition
node_series_pipeline -->|"parses sources"| node_series_parsing
node_series_pipeline -->|"persists series"| node_series_canonical
node_series_pipeline -->|"publishes artifacts"| node_publication
node_series_canonical -->|"uses parsed rows"| node_series_parsing
node_derivation -->|"aggregates canonical data"| node_canonical
node_derivation -->|"publishes derived table"| node_publication
node_research -->|"authenticates parent"| node_derivation
node_research -->|"publishes research table"| node_publication
node_research -.->|"computes feature table"| node_features
node_protocol_run -->|"builds features"| node_features
node_features -->|"uses labels"| node_labels
node_features -->|"uses canonical series"| node_series_canonical
node_validation -->|"validates parent table"| node_research
node_validation -->|"publishes folds"| node_publication
node_training -->|"loads research data"| node_research
node_training -->|"loads folds"| node_validation
node_training -.->|"fits candidates"| node_estimators
node_estimators -.->|"uses logistic engine"| node_logistic
node_evaluation -->|"loads research data"| node_research
node_evaluation -->|"loads validation folds"| node_validation
node_evaluation -->|"publishes evaluation"| node_publication
node_protocol_eval -->|"evaluates run"| node_protocol_run
node_v2_orchestrator -.->|"selects candidates"| node_estimators
node_hashing -.->|"may use kernel"| node_rust_kernel

click node_acquisition "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/acquisition.py"
click node_descriptors "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/descriptor.py"
click node_canonical "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/canonical.py"
click node_hashing "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/hashing.py"
click node_jcs "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/jcs.py"
click node_quality "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/quality_approval.py"
click node_publication "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/publication.py"
click node_data_pipeline "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/pipeline.py"
click node_series_pipeline "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series/pipeline.py"
click node_series_canonical "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series_canonical.py"
click node_series_parsing "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series/parsing.py"
click node_derivation "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/derivation/pipeline.py"
click node_research "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/research/pipeline.py"
click node_features "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_features.py"
click node_labels "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_labels.py"
click node_validation "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/validation/pipeline.py"
click node_training "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/training/pipeline.py"
click node_estimators "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/estimator_c3.py"
click node_logistic "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/training_metrics_logistic.py"
click node_rust_kernel "https://github.com/wyze69-sys/quantara/blob/main/kernel/src/lib.rs"
click node_evaluation "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/evaluation/pipeline.py"
click node_protocol_run "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_run.py"
click node_protocol_eval "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_evaluation_pipeline.py"
click node_v2_orchestrator "https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocols/v2/dev_orchestrator.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_acquisition,node_descriptors,node_canonical,node_hashing,node_jcs,node_quality,node_publication,node_data_pipeline,node_rust_kernel toneBlue
class node_series_pipeline,node_series_canonical,node_series_parsing toneAmber
class node_derivation,node_research toneMint
class node_validation,node_training,node_estimators,node_logistic,node_evaluation toneRose
class node_features,node_labels,node_protocol_run,node_protocol_eval,node_v2_orchestrator,node_researcher toneIndigo
```

## Components

### Data foundation

- [Archive acquisition](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/acquisition.py): `src/quantara/data_foundation/acquisition.py`
- [Descriptors and rights](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/descriptor.py): `src/quantara/data_foundation/descriptor.py`
- [Canonical rows](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/canonical.py): `src/quantara/data_foundation/canonical.py`
- [Identity hashing](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/hashing.py): `src/quantara/data_foundation/hashing.py`
- [Canonical JSON](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/jcs.py): `src/quantara/data_foundation/jcs.py`
- [Quality approval](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/quality_approval.py): `src/quantara/data_foundation/quality_approval.py`
- [Immutable publication](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/publication.py): `src/quantara/publication.py`
- [Data foundation pipeline](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/data_foundation/pipeline.py): `src/quantara/data_foundation/pipeline.py`
- [Hash kernel](https://github.com/wyze69-sys/quantara/blob/main/kernel/src/lib.rs): `kernel/src/lib.rs`

### Market series

- [Series ingestion](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series/pipeline.py): `src/quantara/series/pipeline.py`
- [Canonical series](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series_canonical.py): `src/quantara/series_canonical.py`
- [Series parsing](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/series/parsing.py): `src/quantara/series/parsing.py`

### Research tables

- [Series derivation](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/derivation/pipeline.py): `src/quantara/derivation/pipeline.py`
- [Feature research table](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/research/pipeline.py): `src/quantara/research/pipeline.py`

### Modeling and evaluation

- [Walk-forward validation](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/validation/pipeline.py): `src/quantara/validation/pipeline.py`
- [Model training](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/training/pipeline.py): `src/quantara/training/pipeline.py`
- [Deterministic estimators](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/estimator_c3.py): `src/quantara/estimator_c3.py`
- [Logistic IRLS](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/training_metrics_logistic.py): `src/quantara/training_metrics_logistic.py`
- [Feature evaluation](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/evaluation/pipeline.py): `src/quantara/evaluation/pipeline.py`

### Frozen protocols

- [Protocol features](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_features.py): `src/quantara/protocol_features.py`
- [Protocol labels](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_labels.py): `src/quantara/protocol_labels.py`
- [Protocol run](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_run.py): `src/quantara/protocol_run.py`
- [Protocol evaluation](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocol_evaluation_pipeline.py): `src/quantara/protocol_evaluation_pipeline.py`
- [V2 candidates](https://github.com/wyze69-sys/quantara/blob/main/src/quantara/protocols/v2/dev_orchestrator.py): `src/quantara/protocols/v2/dev_orchestrator.py`

### Other components

- **Researcher**

## Connections

- Researcher → Data foundation pipeline: runs ingestion
- Data foundation pipeline → Archive acquisition: acquires archives (evidence: `src/quantara/data_foundation/pipeline.py`)
- Data foundation pipeline → Canonical rows: normalizes data (evidence: `src/quantara/data_foundation/pipeline.py`)
- Data foundation pipeline → Quality approval: checks quality (evidence: `src/quantara/data_foundation/pipeline.py`)
- Data foundation pipeline → Immutable publication: publishes artifacts (evidence: `src/quantara/data_foundation/pipeline.py`)
- Archive acquisition → Descriptors and rights: validates against (evidence: `src/quantara/data_foundation/acquisition.py`)
- Archive acquisition → Identity hashing: verifies bytes (evidence: `src/quantara/data_foundation/acquisition.py`)
- Canonical rows → Descriptors and rights: uses identity (evidence: `src/quantara/data_foundation/canonical.py`)
- Canonical rows → Identity hashing: defines content for (evidence: `src/quantara/data_foundation/canonical.py`)
- Identity hashing → Canonical JSON: canonicalizes with (evidence: `src/quantara/data_foundation/hashing.py`)
- Series ingestion → Archive acquisition: reuses acquisition (evidence: `src/quantara/series/pipeline.py`)
- Series ingestion → Series parsing: parses sources (evidence: `src/quantara/series/pipeline.py`)
- Series ingestion → Canonical series: persists series (evidence: `src/quantara/series/pipeline.py`)
- Series ingestion → Immutable publication: publishes artifacts (evidence: `src/quantara/series/pipeline.py`)
- Canonical series → Series parsing: uses parsed rows (evidence: `src/quantara/series_canonical.py`)
- Series derivation → Canonical rows: aggregates canonical data (evidence: `src/quantara/derivation/pipeline.py`)
- Series derivation → Immutable publication: publishes derived table (evidence: `src/quantara/derivation/pipeline.py`)
- Feature research table → Series derivation: authenticates parent (evidence: `src/quantara/research/pipeline.py`)
- Feature research table → Immutable publication: publishes research table (evidence: `src/quantara/research/pipeline.py`)
- Feature research table → Protocol features: computes feature table
- Protocol run → Protocol features: builds features (evidence: `src/quantara/protocol_run.py`)
- Protocol features → Protocol labels: uses labels (evidence: `src/quantara/protocol_features.py`)
- Protocol features → Canonical series: uses canonical series (evidence: `src/quantara/protocol_features.py`)
- Walk-forward validation → Feature research table: validates parent table (evidence: `src/quantara/validation/pipeline.py`)
- Walk-forward validation → Immutable publication: publishes folds (evidence: `src/quantara/validation/pipeline.py`)
- Model training → Feature research table: loads research data (evidence: `src/quantara/training/pipeline.py`)
- Model training → Walk-forward validation: loads folds (evidence: `src/quantara/training/pipeline.py`)
- Model training → Deterministic estimators: fits candidates
- Deterministic estimators → Logistic IRLS: uses logistic engine
- Feature evaluation → Feature research table: loads research data (evidence: `src/quantara/evaluation/pipeline.py`)
- Feature evaluation → Walk-forward validation: loads validation folds (evidence: `src/quantara/evaluation/pipeline.py`)
- Feature evaluation → Immutable publication: publishes evaluation (evidence: `src/quantara/evaluation/pipeline.py`)
- Protocol evaluation → Protocol run: evaluates run (evidence: `src/quantara/protocol_evaluation_pipeline.py`)
- V2 candidates → Deterministic estimators: selects candidates
- Identity hashing → Hash kernel: may use kernel
