Beta Stage Notice

Resomix is currently in beta. You may encounter bugs or incomplete features while we continue improving the sonic discovery experience. If you find an issue, please report it through our contact page.

Private Catalogue Pilot // Managed evaluation · Powered by PYXIS-1

Test PYXIS-1 on the music that matters to your team.

A managed private pilot for labels, distributors and catalogue teams that want to evaluate sonic discovery using authorised material and success criteria agreed in advance.

MANAGED EVALUATION · PARTNER-SCOPED · NO PUBLIC SANDBOX

Pilot at a glance
  • Managed evaluation
  • Representative catalogue sample
  • Agreed scorecard
  • Private partner index
  • Joint findings review
  • No public sandbox
The pilot protocol · One sample, six stagesTIMELINE AGREED DURING SCOPING
01 SCOPEagree question · sample · criteria02 INGESTmanaged sftp · audio + csv03 INDEXvalidate · process · private index04 TESTranked results per reference05 MEASUREexpert review · scorecard06 DECIDEstop · extend · plan productionONE REPRESENTATIVE SAMPLE, START TO DECISIONEVIDENCE AT EVERY STAGE
  1. Scope

    Agree the question, the sample and the success criteria.

  2. Ingest

    Deliver audio + CSV manifest through managed SFTP.

  3. Index

    Validation, PYXIS-1 processing, private index build.

  4. Test

    Ranked results from your agreed reference set.

  5. Measure

    Expert review against the agreed scorecard.

  6. Decide

    Joint findings review: stop, extend or plan production.

agree the questions and success criteria before reviewing the resultsone bounded process · evidence at every stage

01 // Fit

Built for catalogue teams with a real question to test

Label / label group

Can older tracks be surfaced from current references?

Distributor

Are our catalogue relationships discoverable beyond metadata?

Catalogue owner

Where does our current catalogue search break down?

Store / platform

Can similarity fit inside our current product and journey?

Music library

Does the analysis produce useful structured data for briefs?

You must control or be authorised to supply the evaluation material. Submitting an inquiry starts a qualification conversation, and not every request will fit a pilot immediately.

Strong fit
  • Authorised catalogue access
  • Electronic-music repertoire
  • Clear discovery or product question
  • Representative sample available
  • Expert reviewers available
  • Willing to agree measures up front
May need more scoping
  • Very small or highly uniform sample
  • No relevant comparison method
  • No authorised audio delivery
  • Unclear rights position
  • Depends on roadmap features

02 // The sample

Bring a representative sample, not your entire catalogue

Sample size and composition are scoped together, around your use case and the catalogue's diversity.

Authorised audio

MP3, WAV, FLAC or AIFF: material you control or are authorised to supply.

CSV metadata

Partner track ID, ISRC where available, title, artist and filename, with optional BPM and duration.

Current + older repertoire

A meaningful mix, with enough related recordings to test similarity properly.

Known reference tracks

Tracks your team already understands, the anchors the evaluation is scored against.

Expert reviewers

A small group of catalogue experts or selectors who will judge relevance.

A clear use case

The question the pilot should answer: discovery, catalogue or product.

Optional event data

Only where you want to evaluate product behaviour downstream.

no universal track count; the sample is scoped around the use case, not a number

03 // The method

One bounded process. Six clear stages.

Every stage states what Resomix does, what your team does, and what evidence it produces.

STAGE 01 · SCOPE · FIT AND AGREEMENT FIRSTTIMELINE AGREED DURING SCOPING
Resomix does
  • Assesses fit against the qualification principles
  • Proposes sample composition and evaluation method
  • Drafts the scorecard for agreement
Your team does
  • Define the pilot question
  • Nominate expert reviewers
  • Confirm rights and sample availability
Evidence produced
  • Agreed scope document
  • Agreed scorecard with targets
no ingestion before approval

04 // The scorecard

Agree the scorecard before you see the results

No pre-filled percentages, no fabricated outcomes. Targets are agreed in scoping, results are measured in the pilot.

measurehow it is assessedtargetresult
Precision@10

Proportion of the first ten results your agreed reviewers accept as musically relevant.

agreed in scopingmeasured in pilot
Expert acceptance

How often catalogue experts consider the shortlist usable.

agreed in scopingmeasured in pilot
Long-tail coverage

Whether relevant older or low-exposure recordings surface.

agreed in scopingmeasured in pilot
Catalogue coverage

Share of the accepted sample searchable and represented in the index.

agreed in scopingmeasured in pilot
Zero-result rate

How often a valid reference fails to produce a useful shortlist.

agreed in scopingmeasured in pilot
Pre-indexed catalogue query latency

Median and P95 response times, measured after the sample catalogue has been indexed. These are never guaranteed.

agreed in scopingmeasured in pilot
Uploaded-reference processing

Measured separately, because the reference must first be processed before searching the partner catalogue.

agreed in scopingmeasured in pilot
Ingestion quality

Validation success, rejected files, and time from accepted batch to evaluation-ready.

agreed in scopingmeasured in pilot

pre-indexed queries and uploaded-reference processing are reported separately and never combined into one "search speed" figure

Preview-through rate

Do users play the results the system returns?

optionalpartner data
Save / shortlist-add

Do results enter real working shortlists?

optionalpartner data
Outbound click

Do results carry users onward in your product?

optionalpartner data
Repeat usage

Do your teams return with the next reference?

optionalpartner data
Conversion

Only where available and attributable in your analytics.

optionalpartner data

05 // The output

A decision pack, not a sales demo

The pilot ends with evidence your team can act on: what worked, what didn't, where the limits are, and what production would involve. Final deliverables are agreed during scoping.

Stop

The evidence does not justify expansion. A clean, documented end.

Extend

A second bounded evaluation for another catalogue area or question.

Plan production

Scope, ingestion cadence, API usage, service mode and terms, agreed together.

the pilot does not automatically convert into a contract · no public prices on this page

06 // Control

Your sample stays inside the agreed pilot boundary

  • Partner catalogues are logically isolated and restricted to authorised partner access.
  • You retain catalogue ownership and commercial control throughout.
  • Partner content is not used to train or fine-tune PYXIS-1. It is not a model, and it does not generate derivative audio.
  • Public exposure is not part of the pilot.
  • Your sample is processed within a partner-scoped catalogue boundary and restricted to authorised access. Detailed access, retention and deletion terms are agreed before ingestion. FINAL WORDING SUBJECT TO PILOT AGREEMENT

07 // Apply

Start with the question you want the pilot to answer

Submitting the form starts a qualification conversation. It does not create an account, a public sandbox or an automatic pilot.

Pilot inquiry
Enter a valid work email address.
Enter your name.
Enter your company.
Select your partner type.
Tell us the question the pilot should answer.
privacy & consent note · final legal wording pending · form data goes to the partner team only