1.7 KiB
1.7 KiB
Data Contract
1. Machine-Readable Format
Use JSON for machine-readable data.
Main JSON objects:
- Model spec
- Source article
- Source excerpt
- Regression case
- Selector example
2. Human-Readable Format
Use Markdown for:
- Model cards
- Project documentation
- Extraction notes
- Validation reports
- Handoff reports
3. Model Spec Contract
Every model JSON should include:
model_idmodel_namemodel_typepipeline_positionone_sentence_definitioncore_questioncore_mechanismsource_articlessource_evidenceinput_typesoutput_typescall_whendo_not_call_whencommon_misusesfailure_modesselection_priorityconfidence_levelstability_profileregression_statusproductization_notes
4. Source Article Contract
Every source article should include:
source_idtitlesource_typerelated_modelssource_status
Optional:
authordatefile_pathnotes
5. Source Excerpt Contract
Every source excerpt should include:
excerpt_idsource_idrelated_model_idexcerpt_typesummaryused_for
Optional:
raw_excerptconfidencenotes
6. Regression Case Contract
Every regression case should include:
case_idmodel_idcase_typeinputexpected_behaviorfailure_signal
Optional:
expected_output_elementsnotes
7. Reference Integrity
The following references must be valid:
model.source_articles->sources/source_articles.jsonmodel.source_evidence->sources/source_excerpts.jsonregression_case.model_id->models/*.model.jsonsource_excerpt.source_id->sources/source_articles.jsonsource_excerpt.related_model_id->models/*.model.json