# duckartem-arts/improving-scoring-models-using-public-data architecture

> Architecture diagram of the GitHub repository duckartem-arts/improving-scoring-models-using-public-data, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/duckartem-arts/improving-scoring-models-using-public-data
- Repository: https://github.com/duckartem-arts/improving-scoring-models-using-public-data

## Overview

The repository combines two workflows: KAD case collection and enrichment in `enricher`, followed by tax-case classification and evidence extraction in `judical_search`. The first incrementally gathers case listings, details, and decision text; the second normalizes and filters case data, extracts structured artifacts, and produces results or optional reports. The README documents several modes and capabilities not visible in the sampled code; those are shown as documented relationships rather than claims of source inspection.

Main entry points: [`judical_search/src/main.py`](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/main.py) (Judicial search runner), [`enricher/main.py`](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/main.py) (Enricher runner), [`judical_search/src/extractors/evidence_extractor.py`](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/extractors/evidence_extractor.py) (Evidence extraction), [`enricher/services/cases.py`](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/cases.py) (Case search)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_collect["Case collection"]
  node_enricher_entry["Enricher runner<br/>[main.py]"]
  node_cookie_service["Cookie handling<br/>[cookies.py]"]
  node_case_search["Case search<br/>[cases.py]"]
  node_case_details["Case details<br/>[case_details.py]"]
  node_pdf_text["Decision PDF text<br/>[case_details.py]"]
end

subgraph group_classify["Tax analysis"]
  node_search_entry["Judicial search runner<br/>[main.py]"]
  node_normalizer["Text normalization<br/>[normalization.py]"]
  node_synonyms["Term synonyms<br/>[synonyms.py]"]
  node_tax_filter["Tax relevance filter<br/>[tax_filter.py]"]
end

subgraph group_extract["Evidence processing"]
  node_evidence_extractor["Evidence extraction"]
  node_artifact_model["Artifact model<br/>[artifact.py]"]
  node_quality["Data quality"]
end

subgraph group_reports["Results and reports"]
  node_result_store["Tax results<br/>[result.json]"]
  node_metrics["Quality metrics<br/>[metrics.py]"]
  node_visualizer["Result visualization<br/>[visualization.py]"]
end

node_operator(("Operator"))
node_kad["KAD court search"]

node_operator -->|"runs collection"| node_enricher_entry
node_enricher_entry -->|"updates cookies"| node_cookie_service
node_cookie_service -.->|"opens site"| node_kad
node_enricher_entry -->|"fetches cases"| node_case_search
node_case_search -->|"loads cookies"| node_cookie_service
node_case_search -->|"searches cases"| node_kad
node_enricher_entry -->|"fetches details"| node_case_details
node_case_details -->|"requests case page"| node_kad
node_enricher_entry -->|"extracts decisions"| node_pdf_text
node_pdf_text -->|"fetches PDFs"| node_kad
node_operator -->|"runs analysis"| node_search_entry
node_search_entry -->|"normalizes text"| node_normalizer
node_tax_filter -->|"normalizes for filter"| node_normalizer
node_search_entry -->|"classifies cases"| node_tax_filter
node_search_entry -->|"extracts evidence"| node_evidence_extractor
node_evidence_extractor -->|"normalizes text"| node_normalizer
node_evidence_extractor -->|"uses terms"| node_synonyms
node_evidence_extractor -->|"creates artifacts"| node_artifact_model
node_search_entry -->|"enhances data"| node_quality
node_quality -->|"uses terms"| node_synonyms
node_search_entry -->|"writes results"| node_result_store
node_operator -->|"requests metrics"| node_metrics
node_metrics -.->|"evaluates predictions"| node_result_store
node_operator -->|"requests visualization"| node_visualizer
node_search_entry -->|"creates demo view"| node_visualizer
node_visualizer -.->|"reads results"| node_result_store

click node_enricher_entry "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/main.py"
click node_cookie_service "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/cookies.py"
click node_case_search "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/cases.py"
click node_case_details "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/case_details.py"
click node_pdf_text "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/case_details.py"
click node_search_entry "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/main.py"
click node_normalizer "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/utils/normalization.py"
click node_synonyms "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/utils/synonyms.py"
click node_tax_filter "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/core/tax_filter.py"
click node_evidence_extractor "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/extractors/evidence_extractor.py"
click node_artifact_model "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/core/artifact.py"
click node_quality "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/processors/quality_enhancer.py"
click node_result_store "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/output/result.json"
click node_metrics "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/metrics.py"
click node_visualizer "https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/visualization.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_enricher_entry,node_cookie_service,node_case_search,node_case_details,node_pdf_text toneBlue
class node_search_entry,node_normalizer,node_synonyms,node_tax_filter toneAmber
class node_evidence_extractor,node_artifact_model,node_quality toneMint
class node_result_store,node_metrics,node_visualizer toneRose
class node_operator,node_kad toneIndigo
```

## Components

### Case collection

- [Enricher runner](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/main.py): `enricher/main.py`
- [Cookie handling](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/cookies.py): `enricher/services/cookies.py`
- [Case search](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/cases.py): `enricher/services/cases.py`
- [Case details](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/case_details.py): `enricher/services/case_details.py`
- [Decision PDF text](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/enricher/services/case_details.py): `enricher/services/case_details.py`

### Tax analysis

- [Judicial search runner](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/main.py): `judical_search/src/main.py`
- [Text normalization](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/utils/normalization.py): `judical_search/src/utils/normalization.py`
- [Term synonyms](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/utils/synonyms.py): `judical_search/src/utils/synonyms.py`
- [Tax relevance filter](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/core/tax_filter.py): `judical_search/src/core/tax_filter.py`

### Evidence processing

- [Evidence extraction](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/extractors/evidence_extractor.py): `judical_search/src/extractors/evidence_extractor.py`
- [Artifact model](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/core/artifact.py): `judical_search/src/core/artifact.py`
- [Data quality](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/processors/quality_enhancer.py): `judical_search/src/processors/quality_enhancer.py`

### Results and reports

- [Tax results](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/output/result.json): `judical_search/output/result.json`
- [Quality metrics](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/metrics.py): `judical_search/src/metrics.py`
- [Result visualization](https://github.com/duckartem-arts/improving-scoring-models-using-public-data/blob/main/judical_search/src/visualization.py): `judical_search/src/visualization.py`

### Other components

- **Operator**
- **KAD court search**

## Connections

- Operator → Enricher runner: runs collection (evidence: `README.md`)
- Enricher runner → Cookie handling: updates cookies (evidence: `enricher/main.py`)
- Cookie handling → KAD court search: opens site
- Enricher runner → Case search: fetches cases (evidence: `enricher/main.py`)
- Case search → Cookie handling: loads cookies (evidence: `enricher/services/cases.py`)
- Case search → KAD court search: searches cases (evidence: `README.md`)
- Enricher runner → Case details: fetches details (evidence: `enricher/main.py`)
- Case details → KAD court search: requests case page (evidence: `README.md`)
- Enricher runner → Decision PDF text: extracts decisions (evidence: `enricher/main.py`)
- Decision PDF text → KAD court search: fetches PDFs (evidence: `README.md`)
- Operator → Judicial search runner: runs analysis (evidence: `README.md`)
- Judicial search runner → Text normalization: normalizes text (evidence: `README.md`)
- Tax relevance filter → Text normalization: normalizes for filter (evidence: `judical_search/src/core/tax_filter.py`)
- Judicial search runner → Tax relevance filter: classifies cases (evidence: `judical_search/src/main.py`)
- Judicial search runner → Evidence extraction: extracts evidence (evidence: `judical_search/src/main.py`)
- Evidence extraction → Text normalization: normalizes text (evidence: `judical_search/src/extractors/evidence_extractor.py`)
- Evidence extraction → Term synonyms: uses terms (evidence: `judical_search/src/extractors/evidence_extractor.py`)
- Evidence extraction → Artifact model: creates artifacts (evidence: `judical_search/src/extractors/evidence_extractor.py`)
- Judicial search runner → Data quality: enhances data (evidence: `judical_search/src/main.py`)
- Data quality → Term synonyms: uses terms (evidence: `judical_search/src/processors/quality_enhancer.py`)
- Judicial search runner → Tax results: writes results (evidence: `README.md`)
- Operator → Quality metrics: requests metrics (evidence: `README.md`)
- Quality metrics → Tax results: evaluates predictions
- Operator → Result visualization: requests visualization (evidence: `README.md`)
- Judicial search runner → Result visualization: creates demo view (evidence: `judical_search/src/main.py`)
- Result visualization → Tax results: reads results
