# LINCS-KET blockwise repair

- **Registry ID:** `lincs-ket-family`
- **Book:** Machine Learning from Enforcing Compositionality
- **Documentation status:** `public-code-linked`
- **Experimental status:** synthetic and PTB repair studies
- **Canonical documentation URL:** https://categorical-ai.sridharmahadevan.com/experiments/lincs-ket-family

## Purpose

Five-seed synthetic architecture test and frozen-module PTB block-repair experiments.

## Book location

- Chapter 12: Repairing Kan-Extension Structure

## Documented studies

- Five-seed synthetic architecture test
- Frozen-module PTB block repair
- Local admission-gate ablation
- Joint-gate negative result

## Associated code packages

- `lincs-allora` — [LINCS ALLORA and LINCS-KET package](https://github.com/sridharmahadevan/LINCS/tree/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora); **public**; Apache-2.0. Adapter-composition and KET repair implementations with smoke and extended experiment entry points.

## Start here

These concrete files are selected from the complete resolved source surface. They orient the reader; they are not a claim that every family is independently reproducible.

- **runner · public-pinned** — [`lincs-allora:scripts/run_confirmatory_ket.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_confirmatory_ket.sh). Open the pinned public source file.
- **runner · public-pinned** — [`lincs-allora:scripts/run_full.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_full.sh). Open the pinned public source file.
- **runner · public-pinned** — [`lincs-allora:scripts/run_gpt2_medium_cuda_registered.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_gpt2_medium_cuda_registered.sh). Open the pinned public source file.
- **runner · public-pinned** — [`lincs-allora:scripts/run_gpt2_medium_cuda_seed7.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_gpt2_medium_cuda_seed7.sh). Open the pinned public source file.

## Entry points

- `KET and theory-diagnostic scripts`

## Result artifacts

- `repair traces and PTB summaries`

## Resolved code surfaces (37)

- **runner** — [`lincs-allora:KET/__init__.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/__init__.py)
- **runner** — [`lincs-allora:KET/aggregate_gpt2_cuda_replication.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/aggregate_gpt2_cuda_replication.py)
- **runner** — [`lincs-allora:KET/aggregate_model_zoo.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/aggregate_model_zoo.py)
- **runner** — [`lincs-allora:KET/allora_ket_adapters.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/allora_ket_adapters.py)
- **runner** — [`lincs-allora:KET/analyze_adapter_sweep.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/analyze_adapter_sweep.py)
- **runner** — [`lincs-allora:KET/analyze_capability_safety.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/analyze_capability_safety.py)
- **runner** — [`lincs-allora:KET/analyze_confirmatory.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/analyze_confirmatory.py)
- **runner** — [`lincs-allora:KET/analyze_lora_text_sweep.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/analyze_lora_text_sweep.py)
- **runner** — [`lincs-allora:KET/analyze_theory_diagnostics.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/analyze_theory_diagnostics.py)
- **runner** — [`lincs-allora:KET/capability_safety_composition.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/capability_safety_composition.py)
- **runner** — [`lincs-allora:KET/cross_fitted_quotient_prediction.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/cross_fitted_quotient_prediction.py)
- **runner** — [`lincs-allora:KET/factor_quotient_projectability.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/factor_quotient_projectability.py)
- **runner** — [`lincs-allora:KET/gpt2_medium_expanded_eval.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/gpt2_medium_expanded_eval.py)
- **runner** — [`lincs-allora:KET/gpt2_medium_mps_pilot.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/gpt2_medium_mps_pilot.py)
- **runner** — [`lincs-allora:KET/gpt2_sequential_lora_smoke.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/gpt2_sequential_lora_smoke.py)
- **runner** — [`lincs-allora:KET/ket_adapter_smoke.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/ket_adapter_smoke.py)
- **runner** — [`lincs-allora:KET/ket_coend_comparison.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/ket_coend_comparison.py)
- **runner** — [`lincs-allora:KET/ket_ptb_adapter_train.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/ket_ptb_adapter_train.py)
- **runner** — [`lincs-allora:KET/lora_text_source_smoke.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/lora_text_source_smoke.py)
- **runner** — [`lincs-allora:KET/model_registry.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/model_registry.py)
- **runner** — [`lincs-allora:KET/reflective_allora_order.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/reflective_allora_order.py)
- **runner** — [`lincs-allora:KET/stochastic_quotient_aggregation.py`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/KET/stochastic_quotient_aggregation.py)
- **runner** — [`lincs-allora:scripts/run_confirmatory_ket.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_confirmatory_ket.sh)
- **runner** — [`lincs-allora:scripts/run_full.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_full.sh)
- **runner** — [`lincs-allora:scripts/run_gpt2_medium_cuda_registered.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_gpt2_medium_cuda_registered.sh)
- **runner** — [`lincs-allora:scripts/run_gpt2_medium_cuda_seed7.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_gpt2_medium_cuda_seed7.sh)
- **runner** — [`lincs-allora:scripts/run_licket_mps_ket_arch_cross_probe.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_licket_mps_ket_arch_cross_probe.sh)
- **runner** — [`lincs-allora:scripts/run_licket_mps_ket_arch_nested_probe.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_licket_mps_ket_arch_nested_probe.sh)
- **runner** — [`lincs-allora:scripts/run_licket_mps_learned_split_probe.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_licket_mps_learned_split_probe.sh)
- **runner** — [`lincs-allora:scripts/run_lora_text_mps_big.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_lora_text_mps_big.sh)
- **runner** — [`lincs-allora:scripts/run_lora_text_mps_lambda_probe.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_lora_text_mps_lambda_probe.sh)
- **runner** — [`lincs-allora:scripts/run_lora_text_mps_multiseed.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_lora_text_mps_multiseed.sh)
- **runner** — [`lincs-allora:scripts/run_lora_text_mps_placement_sweep.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_lora_text_mps_placement_sweep.sh)
- **runner** — [`lincs-allora:scripts/run_lora_text_mps_rank_sweep.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_lora_text_mps_rank_sweep.sh)
- **runner** — [`lincs-allora:scripts/run_smoke.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_smoke.sh)
- **runner** — [`lincs-allora:scripts/run_theory_diagnostics.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/run_theory_diagnostics.sh)
- **runner** — [`lincs-allora:scripts/setup_gpt2_composition.sh`](https://github.com/sridharmahadevan/LINCS/blob/c78bfe50ded8d40db90c614e40dd2e0e146a9875/packages/allora/scripts/setup_gpt2_composition.sh)

## Frozen run records (0)

- No frozen run-level record is registered. Consult the result-artifact list and evidence boundary above for the exact surviving evidence; absence of a run record is not evidence that no experiment was run.

## Evidence boundary

The failed joint gate and all admission conditions remain visible; accepted local steps do not establish general KET superiority.

A code or artifact link establishes traceability. It does not by itself establish independent reproduction, statistical adequacy, correctness, or support for a claim beyond this boundary.