CALL THIS FIRST, before proposing any hypothesis (pre-mortem gate).

Returns ranked past hypotheses/experiments. Refuted and inconclusive matches are ranked to the TOP with a one-line reason they failed and the diagnostic delta that killed them — so you never silently re-walk a dead end. Also returns a calibration note if the query touches a diagnostic with a track record. After reading this, propose a NEW hypothesis (or supersede a prior one) with a committed prediction.

Register an open research question / failure mode. Do this once per distinct problem. Use recall first to check it isn't already logged.

Fetch a single problem by id.

List problems, optionally filtered by status {open|resolved|parked} or tags.

Register a named, fixed, measurable metric. Diagnostics are a DELIBERATE fixed basis — comparability across experiments is what makes the causal map possible. Do this before predicting on a metric.

List the registered diagnostic basis.

Register a named, reusable change (e.g. unfreeze-projector). Reused across hypotheses so the causal map can attribute deltas to it.

List registered interventions.

Propose an explanation/intervention for a problem. You MUST commit ≥1 predicted_effect on a REGISTERED diagnostic BEFORE testing — this is rejected otherwise. Committing the prediction up front is what turns this log into a calibration signal. Call recall first. To revise a dead end, pass supersedes rather than deleting it.

Begin testing a hypothesis. If git_ref is omitted the server reads the current branch@commit from git HEAD. Reference the external W&B/MLflow run — this server stores verdicts, not loss curves.

Record before/after values for measured diagnostics. Re-recording the same diagnostic overwrites it (idempotent). Observed deltas/directions are derived.

Finalize: compute observed_effects, prediction_match (per-diagnostic + overall) and the verdict (supports/refutes/inconclusive), then propagate the status to the hypothesis. The verdict is COMPUTED from the primary prediction vs the observation — you cannot assert 'confirmed'. On a positive match it RETURNS a suggestion to commit your git_ref; it never commits for you.

Add an external reference (metadata + key claims). Cite it from hypotheses to ground your rationale.

Link a paper to a problem or hypothesis (adds a cites edge).

Aggregated intervention → Δdiagnostic subgraph across all experiments in scope: what has ever moved a diagnostic, in which direction, how often, by how much. A mini meta-analysis of your own runs. Scope by problem_id or tag.

Prediction-accuracy report: the fraction of experiments where predicted direction == observed direction. Answers 'where is my intuition miscalibrated?'. Scope by diagnostic, tag, or intervention.

Rebuild the disposable SQLite index from the markdown vault (files are truth). Safe to call anytime; produces identical query results.