Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A native DuckDB SQL extension for enrichment workloads: it classifies every row cheaply with System One, escalates only ambiguous rows to System Two, and keeps the final value plus decision provenance in the relation.
How it uses Jev
Jev (TypeSafe System One) makes bounded judgments over row state: system_one_choice classifies against a finite taxonomy, system_one_noul returns a proposition probability, system_one_score and system_one_resolve select canonical keys or abstain. Results carry choice, confidence and cache_hit; a confidence threshold in SQL decides which rows escalate to System Two.
Primitives:choicescorenoul
Technique worth stealing
Confidence-gated escalation: run System One across all rows, route only low-confidence rows to System Two, and merge both into one typed column with a provenance STRUCT.
Try it
Run ./build.sh, LOAD the built dc.duckdb_extension, CREATE SECRET cognition with both provider keys, then call the system_one_* functions in SQL.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectnot found in the excerpt0.05
- Shows a System One patternFound in material0.81
- Describes handling uncertaintynot found in the excerpt0.29
- Reports measured numbersnot found in the excerpt0.06
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.10
- Is a replica of the modelnot found in the excerpt0.25
- Solves a common problem (0–2)score on a 0–2 scale1.17 / 2
- About JevFound in material0.96
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 21 Oct 2026.