Skip to main content
Challenge

Build an OCDS Procurement Release Language Normalization Pipeline

Parse Open Contracting Data Standard releases containing multi-lingual free-text fields. Extract default language tags, consolidate language-suffixed descriptions, and validate procurement party arrays for translation consistency.

CybersecurityHosted by Vera
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Parse Open Contracting Data Standard releases containing multi-lingual free-text fields. Extract default language tags, consolidate language-suffixed descriptions, and validate procurement party arrays for translation consistency.

Public procurement risk officer

Ingest OCDS release packages containing planning and tender objects with multi-lingual suffixed fields.

Identify the declared default language tag from the OCDS release schema.

Extract and map suffixed fields (e.g., description_es) into a normalized translation map.

Generate a consolidated multi-lingual procurement summary for analyst review.

Queue management view presenting contracting awards, supplier metadata, and consolidated translation maps.

Download standard public sample OCDS release packages featuring multi-lingual suffixed fields such as title_es and title_fr. Evaluate with simplified synthetic app records. Starter examples below are synthetic. They are not downloaded records.

Open Contracting Data Standard Extracts parties, language tags, and release structures from Open Contracting Data Standard schema reference 5.

pydantic-ai, fastapi, pandas. Pydantic AI enables strict schema validation and reliable LLM-driven parsing of diverse language-suffixed fields. Local or hosted LLM compatible with Pydantic AI for schema extraction and normalization tasks.

Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

Parses standard OCDS release package JSON without structural parsing errors.

Extracts the default language tag and groups suffixed language fields accurately.

Outputs a consolidated JSON translation map mapping fields by language code.

```json [ { "input": { "language": "en", "tender": { "title": "Road construction", "title_es": "Construcción de carreteras" } }, "expected_output": { "default_language": "en", "translations": { "en": { "title": "Road construction" }, "es": { "title": "Construcción de carreteras" } }, "status": "VALID", "record_type": "Simplified synthetic app record, not complete official schema file" } }, { "input": { "language": "es", "tender": { "description": "Servicios", "description_fr": "Services" } }, "expected_output": { "default_language": "es", "translations": { "es": { "description": "Servicios" }, "fr": { "description": "Services" } }, "status": "VALID", "record_type": "Simplified synthetic app record, not complete official schema file" } } ] ```

Procurement screening simulations only; does not cancel public tenders or disqualify real commercial vendors. Use mock external writes. Require human review before any real deployment.

Rules

Participation guide

Procurement screening simulations only; does not cancel public tenders or disqualify real commercial vendors. Use mock external writes and human review.

Delivery guide

How work is evaluated

Evaluation

Parses standard OCDS release package JSON without structural parsing errors. Extracts the default language tag and groups suffixed language fields accurately. Outputs a consolidated JSON translation map mapping fields by language code.

Submission format

Runnable source, pinned dependencies, setup commands, working interface, example outputs, recorded demo, tests, and action logs.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
4 scoring checks
Binary
1 pass or fail dimensions
Ordinal
3 scaled dimensions
Dimension 1

Complete workflow

Ingest OCDS release packages containing planning and tender objects with multi-lingual suffixed fields. Identify the declared default language tag from the OCDS release schema. Extract and map suffixed fields (e.g., description_es) into a normalized translation map. Generate a consolidated multi-lingual procurement summary for analyst review.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 2

Correctness and evidence

Parses standard OCDS release package JSON without structural parsing errors. Extracts the default language tag and groups suffixed language fields accurately. Outputs a consolidated JSON translation map mapping fields by language code.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 3

Review interface

Queue management view presenting contracting awards, supplier metadata, and consolidated translation maps.

Score scale
012
Score 0

Missing or incorrect.

Score 1

Partly complete, with documented gaps.

Score 2

Complete, with reproducible evidence.

Dimension 4

Safe execution

Procurement screening simulations only; does not cancel public tenders or disqualify real commercial vendors.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Ingest OCDS release packages containing planning and tender objects with multi-lingual suffixed fields.

  • Identify the declared default language tag from the OCDS release schema.

  • Extract and map suffixed fields (e.g., description_es) into a normalized translation map.

  • Generate a consolidated multi-lingual procurement summary for analyst review.

Resources and assets

Reference links and supporting material

Dataset notes

Download standard public sample OCDS release packages featuring multi-lingual suffixed fields such as title_es and title_fr. Evaluate with simplified synthetic app records. Supplied starter examples are synthetic, not source extracts.

Challenge setup

Configuration summary for this challenge.

Challenge input

Input details are not configured.

Pydantic AI

Typed Python agent framework.

Evaluated output

No output checks are configured.

Evaluation checks
  • Ingest OCDS release packages containing planning and tender objects with multi-lingual suffixed fields. Ide...
  • Parses standard OCDS release package JSON without structural parsing errors. Extracts the default language...
  • Queue management view presenting contracting awards, supplier metadata, and consolidated translation maps.
Configured evaluation evidence
  • 2 public reference cases
Configured runtime
  • 2 configured tools

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Pydantic AI · Optional
Orchestration
  • Pydantic AI · Optional

Evaluation contract

  • Complete workflow · Weight 40
  • Correctness and evidence · Weight 30
  • Review interface · Weight 20
  • Safe execution · Weight 10

Reference cases

  • 2 public reference cases

Workflow tasks

No workflow tasks are configured.

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an OCDS Procurement Release Language Normalization Pipeline