From the hash-bound evidence releases
Recorded claims
Each claim states what the inspected source says, at the recorded location—bounded by its scope and graded by its confidence. Nothing here is a synthesis across works.
A computational study using 1.69 million stock-keeping-unit records reports that a compact genetic algorithm matched random-search held-out accuracy and F1 at about 0.89 across five learners and five random seeds while reducing tuning time by 28.5% and model evaluations by 16.2%; a separate pilot with 21 practicing planners reports positive associations between trust and adoption intention and between transparency and perceived team performance.
Scope: Study 1: public dataset of 1.69 million SKU records, five learners, five random seeds, with dataset period unstated. Study 2: 21 practicing planners, with recruitment universe, study period, and condition denominator unstated; reported coefficients were beta=.49 (p=.023) and beta=.65 (p=.004)
Structured relationships
In-corpus citations
Only source-supplied cites relationships whose two endpoints are admitted are shown. Invocation evidence remains a separate relationship.
Cites (0)
No in-corpus outgoing citation is available in the current enrichment coverage.
Cited by (0)
No in-corpus incoming citation is available in the current enrichment coverage.
Boundaries
Limitations & independence
Recorded at coding time, carried with the work forever. A claim without its limits is not evidence.
Recorded limitations
- Abstract-level evidence only; full text and PDFs were not inspected.
- The SSRN page explicitly labels the work a preprint that has not been peer reviewed.
- The abstract does not state the stock-keeping-unit dataset period or firm universe, nor the pilot recruitment frame, study period, condition structure, uncertainty intervals, or multiple-testing plan.
- The 21-planner pilot is described as instrument validation; the page says a preregistered controlled experiment is planned rather than completed.
Source independence
ssrn-only