Published 14 July 2026 · Current production decision
A valid number is not necessarily a useful fingering
Piano fingering is contextual. Several paths can be playable. Editorial choices depend on articulation, phrasing, hand shape, learned technique, and what comes before and after the visible passage. A system that fills every note can appear complete while hiding uncertainty.
Helicon treats fingering as a sequence problem with provenance. The current decision is to ship the physically constrained generator and its confidence-gated practice interface, while keeping the difficult-arpeggio specialist experimental.
The product contract comes first
Practice Setup exposes four source policies:
- No finger numbers—the default.
- Human-authored only—MusicXML and manual edits.
- Human-authored, then fill gaps—recorded values become anchors.
- Machine-generated only—an independent generated layer.
A 20–99% confidence threshold previews shown human labels, generated labels, ambiguous notes removed by the threshold, and notes that cannot be safely analyzed. Human and generated values use different visual treatment. The generator never overwrites recorded evidence.
Abstention is a feature. A conservative generator must not be rewarded merely for avoiding every hard note, but the product must not force low-confidence advice into practice.
Search the path, not the isolated note
The generator uses dynamic programming with hard physical constraints, ergonomic costs, and complete-path alternatives. Candidate finger assignments are evaluated as transitions through time rather than independent classifications.
This lets the solver represent reach, vertical chord geometry, crossings, repeated notes, hand travel, and the cost of one decision on the next. Confidence comes from competing complete paths rather than a decorative probability added afterward.
Data volume is not evidence quality
The research harness assembled 94,015 mechanically clean labels from 1,247 pieces before cross-corpus deduplication. The sources ranged from public-domain symbolic scores to community MusicXML and research-only material. Those categories remain separate because a clean label is not necessarily authoritative or redistributable.
| Evaluation requirement | Why it matters |
|---|---|
| Whole-work splits | Prevent related exercises from leaking across training and test folds |
| Coverage with precision | Prevent abstention from masquerading as accuracy |
| Physical violations | Keep impossible paths visible even when note accuracy looks good |
| Pattern and hand breakdowns | Expose localized weaknesses hidden by one aggregate score |
| Rights and provenance tiers | Separate useful research inputs from publishable material |
What the current generator can claim
On a manually checked 22-score public corpus with 612 labelled notes, the available comparison was:
| Generator | Coverage | Precision | Violations |
|---|---|---|---|
| Keyfire, reporting threshold 0% | 78.9% | 60.0% | 0 |
| PianoPlayer 3.0.2 | 100.0% | 45.3% | 0 |
The coverage difference matters. This result supports selective output; it does not establish that Helicon has solved full-coverage fingering. On 94 arpeggio-like positions, Keyfire covered 42.6% at 70.0% precision, while PianoPlayer covered all positions at 43.6% precision.
The negative results changed the product
An all-corpus fitted model improved the held-out result by only 11 net labels, with p = 0.704. That is not evidence of improvement, so the model was not promoted.
An earlier positive result disappeared after Hanon exercises were grouped by complete work. The split had leaked closely related material. The benchmark caught the error and preserved the stronger existing hand-built baseline.
The difficult-arpeggio specialist also remains experimental. Its raw result was worse than the general generator, and confidence-gated routing returned essentially to baseline. A hand-position planner produced inspectable movement hypotheses, but the alternatives were too ambiguous to affect production ranking.
A research harness earns its keep when it prevents a plausible model from shipping.
What comes next
More undifferentiated labels are unlikely to be the best next investment. Future collection should target independently annotated difficult arpeggios, multiple acceptable paths, and specific failure cells. The current generator remains useful precisely because its product boundary is narrower than the unsolved research problem.