markitect-main/examples/infospace-with-history/output/metrics/metrics.yaml

coherence_components: 0.0
consistency_cycles: 0.0
coverage_ratio: 0.619048
granularity_entropy: 2.674752
modularity: 0.0
per_entity_mean: 3.955635
redundancy_ratio: 0.006073
infospace: process book-1-chapter-03 Extract entities, map to VSM, and synthesize analysis. 2026-02-19 15:04:57 +01:00			`coherence_components: 0.0`
			`consistency_cycles: 0.0`
feat(infospace): add eval-summary command and improve evaluate pipeline (S3.3) - Fix evaluate dimensions to match template file: definition_precision, source_grounding, domain_placement, vsm_relevance, explanatory_value (was domain_relevance, discipline_alignment, conceptual_clarity) - Add VSM background context to evaluation prompt so LLM can score vsm_relevance without macro injection - Fix model_name bug: was sending literal "default" to API (HTTP 400) - Refactor run_entity_evaluation to write files incrementally via callback rather than all at once after the batch — long runs are now resumable if interrupted - Add incremental skip in CLI: entities with existing eval files are skipped automatically on re-run (acts as resume) - Add eval-summary command: reads all eval files, shows per-dimension means, optionally writes per_entity_mean to metrics.yaml - Fix record_check_results to merge rather than overwrite metrics.yaml so per_entity_mean survives subsequent check runs - Add per_entity_mean viability threshold (min: 3.5) to infospace.yaml Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-02-23 01:26:45 +01:00			`coverage_ratio: 0.619048`
			`granularity_entropy: 2.674752`
infospace: process book-1-chapter-03 Extract entities, map to VSM, and synthesize analysis. 2026-02-19 15:04:57 +01:00			`modularity: 0.0`
feat(example): add per-entity LLM evaluations for 985 WoN entities (S3.3) Batch evaluation of all 988 entities via OpenRouter. 984 succeeded on first pass; 3 failed (network errors). eval-summary --update-metrics written with per_entity_mean=3.9556. Viability dashboard: 6/6 PASS redundancy_ratio 0.0061 (max 0.10) coverage_ratio 0.6190 (min 0.40) coherence_comps 0.0000 (max 3) consistency_cycles 0.0000 (max 0) granularity_entropy 2.6748 (min 1.0) per_entity_mean 3.9556 (min 3.5) Dimension breakdown (mean across 985 entities): definition_precision 3.62 source_grounding 4.36 domain_placement 4.56 vsm_relevance 3.31 explanatory_value 3.94 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-02-23 09:36:46 +01:00			`per_entity_mean: 3.955635`
feat(infospace): add eval-summary command and improve evaluate pipeline (S3.3) - Fix evaluate dimensions to match template file: definition_precision, source_grounding, domain_placement, vsm_relevance, explanatory_value (was domain_relevance, discipline_alignment, conceptual_clarity) - Add VSM background context to evaluation prompt so LLM can score vsm_relevance without macro injection - Fix model_name bug: was sending literal "default" to API (HTTP 400) - Refactor run_entity_evaluation to write files incrementally via callback rather than all at once after the batch — long runs are now resumable if interrupted - Add incremental skip in CLI: entities with existing eval files are skipped automatically on re-run (acts as resume) - Add eval-summary command: reads all eval files, shows per-dimension means, optionally writes per_entity_mean to metrics.yaml - Fix record_check_results to merge rather than overwrite metrics.yaml so per_entity_mean survives subsequent check runs - Add per_entity_mean viability threshold (min: 3.5) to infospace.yaml Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> 2026-02-23 01:26:45 +01:00			`redundancy_ratio: 0.006073`