Add IPA trial evidence quality checks

docs/ipa-vocal-tract-roadmap.md

@@ -699,6 +699,10 @@ one-patch golf. A useful round tests whether a contour, source, tract,
 radiation, or DSL-lowering idea generalizes across the target sets. Full-patch
 FM/AM/noise dressing is allowed as parity pressure, but the evaluator must
 label it as dressing when primitive or gesture evidence does not improve.
+The loop also judges evidence quality directly: retrieval receipts should be
+specific, comparable, falsifiable, and reusable by the next round. A pretty
+report with vague receipts is a failed science artifact even if it obeys the
+file-count contract.
 
 ## CultMesh Render/Scoring Work
 

state/evidence.jsonl

@@ -239,3 +239,4 @@
 {"date":"2026-05-29","area":"ipa-trial-render-orchestration","summary":"Added the first local IPA trial worker/evaluator loop. `IpaTrialOrchestrator.RunAsync` generates candidates through `IpaGestureExperiment`, renders them through Faust, compares spectrogram/articulation evidence against local Pink Trombone fixture references, writes WAV/report artifacts, and stores typed `IpaTrialResult` records in `ipa-trial-results.cc`. The first five-seed run proved the pipeline but exposed silent vowel/nasal candidates; the accepted refinement moved voiced excitation into primitive `SourcePort` lowering. The second run at `artifacts/parity/ipa-trials/20260529T214127955/five-seed-trials` improved open `a` to log-mel cosine `0.5693`, `m` to `0.5199`, and `s` to `0.5498`, while `p` stayed weak at `-0.1024`, pointing to closure/release ownership next. Focused verification passes 94/94 plus opt-in IPA trial run.","evidence":"src/AquaSynth.Core/IpaTrialResults.cs; src/AquaSynth.Faust/IpaTrialOrchestrator.cs; src/AquaSynth.Core/FaustExport.cs; src/AquaSynth.Core/IpaGestureExperiment.cs; tests/AquaSynth.Dsl.Tests/IpaTrialOrchestratorTests.cs; docs/ipa-vocal-tract-roadmap.md; state/spine.yaml; state/scratch.md"}
 {"date":"2026-05-29","area":"ipa-trial-loop","lesson":"External IPA exploration needs a semantic retrieval tool over the CultCache .cc trial store, not crude full-memory dumps. Hypothesis agents should use search/show to retrieve ranked metric and artifact context, then write batches across the five five-phoneme target sets; the worker owns rendering, scoring, and .cc upserts."}
 {"date":"2026-05-29","area":"ipa-trial-loop-prompts","lesson":"Prompt smoke found that agent prompts need hard acceptance contracts, not just instructions: exact candidate count, canonical filename schema, normalized family ids, retrieval receipts, claim-to-metric audit rows, and fail-closed evaluator compliance prevent report-shaped fog from passing as loss-landscape science."}
+{"date":"2026-05-29","area":"ipa-trial-evidence-quality","lesson":"The IPA exploration loop should optimize evidence quality, not just prompt compliance. Hypothesizers must publish specificity/comparability/falsifiability/reuse ledgers per family, and evaluators must penalize vague receipts even when candidate metrics look better."}

state/scratch.md

@@ -36,9 +36,10 @@ Current slice:
   contradictory count/name instructions, hardened candidate naming to
   `<targetId>__<family>__<hypothesis>.aqua`, made family ids lowercase
   kebab-case, required exact 25-lane output, added pre-evidence digest and
-  claim-audit sections, forced semantic-search/show receipts, and made the
-  evaluator fail closed when receipts, target coverage, filename validation, or
-  family extraction are incomplete. Final script syntax smoke passes with
+  claim-audit sections, forced semantic-search/show receipts, added evidence
+  quality ledgers/verdicts for specificity/comparability/falsifiability/reuse,
+  and made the evaluator fail closed when receipts, target coverage, filename
+  validation, or family extraction are incomplete. Final script syntax smoke passes with
   `tools\run-ipa-trial-loop.ps1 -Rounds 0 -SkipLocalTrialRun`.
 
 - Implemented the first IPA trial render/scoring orchestration. Core now has

state/spine.yaml

@@ -145,7 +145,7 @@ live_invariants:
   - IPA training scoring contract is documented. Reports must keep `gesture_score`, `clean_vocal_score`, and `full_parity_score` separate. Gesture score measures descriptor-to-surface coverage, motion direction, spline contour/timing, primitive timeline consequences, and optional external articulation landmarks. Full parity patches may use FM/AM/modulators/envelopes/filters, auxiliary animated voices, and recording-condition helpers, but those helpers cannot count as articulation evidence unless gesture and clean-vocal scores move coherently.
   - `IpaGestureExperiment.WriteRound` is the first frozen batch harness for IPA hypothesis work. It writes `manifest.yaml`, candidate `.aqua` scripts, primitive `ProbeTimelineReport` CSVs, gesture-layer `metrics.csv`, and per-candidate `evidence.jsonl` under a caller-provided artifact root. `IpaGestureExperiment.AnalyzeRound` writes `analysis/metric-summary.csv`, `analysis/candidate-clusters.csv`, and `analysis/science-brief.md` for the science-worker handoff. This harness owns frozen descriptor/spline/primitive evidence only; clean vocal identity, full spectrogram parity, optimizer checkpoints, and worker orchestration stay downstream. Focused verification: `PatchScriptTests` pass 93/93.
   - `IpaTrialOrchestrator.RunAsync` is the first local render/scoring worker for IPA trials. It generates candidate patches through `IpaGestureExperiment`, renders them through Faust, compares against local PT fixture references with `AudioAnalyzer`, writes WAV/report artifacts, and stores typed `IpaTrialResult` records in `ipa-trial-results.cc`. The five-seed trial run at `tests/AquaSynth.Dsl.Tests/bin/Debug/net10.0/artifacts/parity/ipa-trials/20260529T214127955/five-seed-trials` showed voiced vowels/nasals became audible only after primitive `SourcePort` lowering gained a true oscillatory voiced carrier; sibilants are pressure, plosives remain weak. Verification: opt-in IPA trial test passed, and focused `PatchScriptTests|IpaTrialResultsRoundTripThroughCultCache` pass 94/94.
-  - External IPA exploration now has a worker/tool boundary. `tools/IpaTrialWorker` owns `seed`, `score`, `search`, `show`, and audit-only `dump` commands over the typed `.cc` trial-result store; `score` renders external Codex-authored `.aqua` candidates through `IpaTrialOrchestrator.RunCandidateScriptsAsync`, while `search` is the semantic retrieval organ for hypothesis agents. `tools/run-ipa-trial-loop.ps1` orchestrates external `codex exec` hypothesis/evaluator workers around that store. The active trial shape is five target sets of five phoneme lanes each: vowels, nasals/approximants, fricatives, stops, and mixed generalization. Candidate names are exactly `<targetId>__<family>__<hypothesis-name>.aqua`, with lowercase kebab-case family ids. Three dry external Codex smoke passes refined hypothesizer/evaluator prompts into exact 25-lane output, retrieval receipts, claim audits, and fail-closed evaluator compliance. Verification: `IpaTrialWorker` builds, `search` smoke reads the seed store, and the loop skeleton runs with `-Rounds 0 -SkipLocalTrialRun`.
+  - External IPA exploration now has a worker/tool boundary. `tools/IpaTrialWorker` owns `seed`, `score`, `search`, `show`, and audit-only `dump` commands over the typed `.cc` trial-result store; `score` renders external Codex-authored `.aqua` candidates through `IpaTrialOrchestrator.RunCandidateScriptsAsync`, while `search` is the semantic retrieval organ for hypothesis agents. `tools/run-ipa-trial-loop.ps1` orchestrates external `codex exec` hypothesis/evaluator workers around that store. The active trial shape is five target sets of five phoneme lanes each: vowels, nasals/approximants, fricatives, stops, and mixed generalization. Candidate names are exactly `<targetId>__<family>__<hypothesis-name>.aqua`, with lowercase kebab-case family ids. Three dry external Codex smoke passes refined hypothesizer/evaluator prompts into exact 25-lane output, retrieval receipts, claim audits, evidence-quality ledgers/verdicts, and fail-closed evaluator compliance. Verification: `IpaTrialWorker` builds, `search` smoke reads the seed store, and the loop skeleton runs with `-Rounds 0 -SkipLocalTrialRun`.
   - TurbulenceJet now includes a release-timed burst-noise component in addition to the deterministic pressure pulse, but a stronger trial barely moved papa; the source is not the main remaining articulation bottleneck. Graph radiation now mixes 30% raw boundary flow with 70% high-passed flow after local admittance weighting, down from the over-bright 15/85 blend. Latest radiation/source artifact under `artifacts/parity/pink-trombone-utterance-logmel/20260527T174236049`: mama/papa/thrombosis cosine 0.6578/0.7692/0.5585, rmsRatio 3.0006/2.6153/2.3488, articulation 0.1437/0.1173/0.1191. Static `closure-release` under `artifacts/parity/pink-trombone-logmel/20260527T174139661` has rmsRatio 0.9900 and speechBandRatio 0.0842. This is still not speaking; next pressure is true tract resonance/passive scattering and pressure storage, not more burst gain.
   - Same-path two-port area discontinuities now emit `graph_area_energy_in_*` and `graph_area_energy_out_*` probes alongside the three-port branch `graph_connection_energy_*` probes. Use these to inspect passivity and formant-body failures at the scatter sites rather than judging only final output loudness.
   - `FaustExportOptions.DebugProbeUi` wraps graph probe signals in Faust `vbargraph` UI controls under `/debug/...` without changing audio output arity. Native streaming Faust patches now separate writable controls from read-only probe zones and can read/snapshot probe values after `ProcessBlock`; use this for acoustic graph passivity/radiation inspection, leave it off for normal parity renders.

tools/run-ipa-trial-loop.ps1

@@ -294,6 +294,7 @@ Required `$roundDir/hypotheses.md` shape:
 - `Loss Landscape Read`: strongest and weakest evidence by family.
 - `Hypothesis Families`: 3-5 families, each with owner layer, transfer status, evidence_refs, cited trial_ids, at least one concrete metric key/value from `show`, and predicted metric movement using `gesture:+/-/flat`, `logmel:+/-/flat`, `articulation:+/-/flat`, `rms:+/-/flat`, `timeline:+/-/flat/risk`.
 - `Claim Audit`: one row per family: claim -> evidence file(s) -> metric key/value(s) -> predicted movement.
+- `Evidence Quality Ledger`: one row per family with specificity, comparability, falsifiability, reuse value for the next round, and the weakest missing evidence. Use `high`, `medium`, or `low` for each quality field.
 - `Candidate Matrix`: exactly 25 rows with target id, filename, family, expected metric movement, and risk.
 - `Source Edit Decision`: `none` unless source edits are allowed and justified by evidence.
 - `Acceptance Checklist`: 25 files, one per target id, filename schema, required report sections, >=3 search receipts, >=3 show receipts.
@@ -411,6 +412,7 @@ Required `$roundDir/evaluation.md` shape:
 - `Commands Run`: exact search/show commands and output paths used to support claims.
 - `Round Compliance`: passed/failed, candidate count, target coverage, naming validity, family extraction, and whether the report had the required matrix.
 - `Family Verdicts`: one row per canonical filename family with improved/flat/regressed/unknown metrics. Treat |delta| < 0.01 as flat; if deltas are not present in cited show artifacts, write `unknown` and reason=`no delta in receipts`.
+- `Evidence Quality Verdicts`: one row per family with specificity, comparability, falsifiability, reuse value, and weakest missing evidence. Penalize vague receipts even when metrics improve.
 - `Generalization Read`: whether effects transferred across target sets or overfit one phoneme.
 - `Dressing Audit`: articulation evidence requires movement in gesture/articulation/primitive timeline metrics; FM/AM/noise/envelope evidence without those is dressing.
 - `Next Target`: exactly one markdown bullet, final line of the file, and no continuation text: `<file-or-module> | <invariant> | <expected metric movement>`.