Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Factbag combines narrow judgments from Jev with explicit rules in a knowledge base, turning documents into evidence and conclusions for applications that need to assess claims against a ruleset.
How it uses Jev
Jev assesses whether each passage supports, contradicts, or is irrelevant to candidate claims defined as predicates. The classifier runs jobs that make live Jev requests, producing evidence admitted into a knowledge base. Queries combine this evidence with facts and rules to yield true, false, conflicted, or unknown conclusions.
Primitives:choice
Technique worth stealing
Use a guard to permit Jev to assert or deny specific predicates, then combine admitted evidence with explicit rules for queryable conclusions.
Try it
Install factbag@alpha, @factbag/jev@alpha, and @typesafe-ai/sdk@^0.7.0; set TYPESAFE_API_KEY; run classifier jobs.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 projectFound in material0.79
- Shows a System One patternunclear0.49
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.92
- Top-10 learning shortlist signalnot found in the excerpt0.39
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.34 / 2
- About JevFound in material0.99
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 3 Nov 2026.