Epistemic-Humility-Research

Author, organize, and launch tuner-backed mechanistic-interpretation cells (activation reading and writing) for the Epistemic-Humility project. Use when designing a new steering / extraction / probe-fit / gate-scoring cell, deciding where its config, direction, grader, and outputs live, or launching one locally or on Modal. This skill is about USING the synaptic-tuner `mechinterp` verbs via declarative recipe YAML plus project plug-ins; it never modifies the tuner submodule and never touches the frozen legacy machinery.

Operational runbook for the Epistemic-Humility Locked Matrix Experiment Runner - expands the PROTOCOL v0.3 (LOCKED) run matrix (3-seed headline + LR/beta sensitivity panel at 4B, 3-seed confirm at 8B, 2 bridge replication cells) into per-cell tuner invocations across two lanes (local RTX 3090 / HF Jobs cloud), with hard pre-registration count assertions, prerequisite gating, data staging, and committed provenance run records. Use when launching, dry-running, or gating the locked matrix, materializing per-cell recipes, or inspecting run records. This skill is about USING the runner via checked-in scripts; it never modifies the synaptic-tuner submodule.

Lifecycle tooling for the experiments-first repo layout - one self-contained directory per evidence-producing experiment (steer cell, training run, eval, probe-fit, or lab diagnostic) under experiments/, each with a signed AMENDMENT.md, a thin machine-readable experiment.yaml manifest, pinned instrument configs, and generated indices. Use to scaffold, sign, list, show, resolve, and validate experiments, to regenerate the registry, and to understand the draft -> sign -> run -> resolve lifecycle and the shared-input promotion rule. The bin/exp wrapper runs these scripts; validation and registry regeneration run at commit time via .githooks/pre-commit.

Package a terminal experiment's data exhaust (aggregate stats and, where license-permitted, row-level generation text) into reproducible Hugging Face datasets, with a license gate, containment lint, and a thin uploader. Use when an experiment under experiments/<slug>/ reaches a terminal verdict (resolved, null-result, or falsified) and its analysis-committed/ artifacts should be published.

Standardize the per-model layer-mapping extraction (full-depth hidden-state capture, workspace-dimension profile, three-axis held-out read panel) so any new model, family, or size entering the Epistemic-Humility program gets a fast, cheap, uniform layer atlas before any actuation design. Use when a new model/family/size enters the program, before designing any per-family actuation cell, or when an existing family's substrate changes (new revision, new checkpoint).

Create, validate, normalize, export, and analyze typed Obsidian knowledge graph metadata in the Professor Synapse vault, including `kg` node metadata, `relationships` edge objects, `related` link projections, ontology-governed edge types, legacy relationship shorthand, and graph analysis reports.

Run, plan, validate, or aggregate Epistemic-Humility local mechanistic-interpretability sweeps, including hidden-state candidate inventories, causal-pilot sweep planning, explicit non-GPU/GPU gates, base-original skip handling, and offline result aggregation. Use when working on local mech-interp sweeps, causal-pilot diagnostics, activation-addition/logit-diagnostic runs, behavior-axis scans, SAE feature screens, or future reruns of the legacy full candidate inventory.

Ingest a research paper (or a batch) into the library's atomic knowledge graph the Agents-K1 way. Use when you are handed a paper (URL, arXiv id, or a note already in library/) and you want it folded in as typed concept atoms, mechanisms, lineage edges, and a patched paper note, reconciled against the atoms already in the vault rather than re-extracted from scratch. Also use to backfill spine papers not yet atomized. This is the standing ingestion posture for growing the graph one paper at a time.