BASKET and ROCKET workflow construction

Experimental contract

What this family tests

frozen workflow and reranking studies

BASKET partial-order workflow construction
ROCKET section-aware reranking
Action-vocabulary and plan-manifest audit

Book-to-code crosswalk

The highlighted Experiment cards covered here

Experiment: predictive-state variant comparison.24.10.2 PSR Variant Comparison · reported result or audit · direct chapter family

Implementation map

From entry point to source surface

Start here

These concrete files are selected from the complete registered source surface to orient the reader.

implementation · public-pinned — basket-rocket-archive:src/tenk.py ↗Open the pinned public source file.
implementation · public-pinned — basket-rocket-archive:src/rocket.py ↗Open the pinned public source file.
implementation · public-pinned — basket-rocket-archive:src/plan_ket_scoring.py ↗Open the pinned public source file.
implementation · public-pinned — basket-rocket-archive:src/psr.py ↗Open the pinned public source file.

Author-declared entry points

BASKET package and output manifests

Resolved code

implementation · 11

Evidence record

Artifacts and frozen runs

Result artifacts

summary.json
reranked_summary.json
action_vocab.csv

Run records

No run-level packet is registered. The family retains code-level provenance, but public run reproduction still requires curation.

Evidence boundary

Validation loss and constructed reranking scores are not workflow accuracy, financial forecasts, or causal effects.

This registry links the experiments reported by the three books to their executable or archived code surfaces. A code link establishes traceability, not independent reproduction, correctness, or support for a claim beyond the experiment's stated boundary.