180 · Music · Creative and media · live
Mix cue sheet
Eval results
Scored on a held-out or test splitRun 29 Sep 2026Eval write-up (decosa-api, access required)
- Song starts within 10 s, with your track files105/105 (92/105 within 5 s, 24/105 within 1 s)test splitn = 105105 starts predicted. Time per 5-minute mix: p50 4.46 s, p95 6.26 s.
- Song starts within 10 s, titles only (the hosted default)84/105 (51/105 within 5 s, 15/105 within 1 s)test splitn = 105The tracklist without times. Time per 5-minute mix: p50 0.85 s, p95 1.25 s.
- Song starts within 1 / 5 / 10 s, audio only3/105 / 10/105 / 19/105test splitn = 105Only 20 starts predicted: not useful on its own.
- By join, with your track files (within 5 s / 10 s, of 35 each)cuts 23 / 31, crossfades 31 / 35, blends 33 / 35test splitn = 105
- By join, titles only (within 5 s / 10 s, of 35 each)cuts 26 / 30, crossfades 11 / 30, blends 14 / 24test splitn = 105
- Learned detector on (self-host): within 10 s, titles only / with track files61/105 / 85/105test splitn = 105Not better on these short synthetic songs; it helps on real long mixes (dev set).
- Starts within 10 / 20 / 30 s, titles only, detector off (hosted setting)61 / 75 / 86 of 190dev (tuned on)n = 190Within 5 s: 40. No track files and no times: every start is placed from the audio.
- Starts within 10 / 20 / 30 s, titles only, detector on57 / 73 / 81 of 190dev (tuned on)n = 190
- Starts within 10 / 20 / 30 s, audio only, detector off / on59 / 70 / 81 vs 78 / 104 / 129 of 190dev (tuned on)n = 190With the detector on, 358 starts were predicted for 190 real ones.
- Starts within 10 / 20 / 30 s with a fingerprint service's identifications, titles and the detector99 / 123 / 144 of 190dev (tuned on)n = 190Within 1 s: 26; within 5 s: 74; 277 predicted starts. Detector off: 70 / 95 / 146. The identifications came from a fingerprint service that is not part of the product. This setting reproduces the original engine's numbers exactly.
Dataset
Held out: 20 synthetic mixes built from 19 of Decosa's own Make a song songs (60 s each, similarity check clear), 105 song starts, 99 minutes of audio; each song played at 0.96-1.04 speed and trimmed 0-6 s; joins are cuts, crossfades (4-12 s) and bass-swap blends (12-24 s), 35 of each. Development: 8 public DJ mixes with 190 song starts from their published timed tracklists (mixes and DJs not named).
Caveats
- The held-out mixes are synthetic, built from 60-second songs, not real DJ mixes.
- The same author wrote the mixer and the engine.
- Each test song appears in about 5 of the 20 mixes.
- Every threshold was frozen on a separate dev split before the test set was built; the test set was run once.
- The public-mix numbers are a development set, not held out: the original engine's settings were chosen while looking at them. Real DJ mixes with long blends are harder (61 of 190 within 10 s from titles alone).
- DJs' own timestamps disagree by about 9 s, so 10 s is the practical bar.
- The runs with identifications used cached results from a fingerprint service that is not part of the product.
Nightly smoke check
Loading the nightly status…
- Result
- pass
- Run
- 29 Sep 2026
- Latency, this run
- n/a
- p50 over passed runs
- 7.0 s
- Receipts
- 0
- Model calls
- n/a
- Tokens
- n/a
- Cost per run
- $0
Self-host verification
Not yet verified on a fresh self-host setup.
Rehearsal bundle: mix-cue-sheet.zip (1 KB, 12 checks). Mock inputs plus the expected results, so you can prove your own setup works before any real data touches it.
Known limits
- It names only songs you give a title or a file for; there is no catalogue lookup on the hosted tool.
- Titles without times or files are placed from the audio alone and marked estimated: 84 of 105 within 10 s on held-out synthetic mixes, but 61 of 190 on real DJ mixes with long blends.
- Audio alone, with no titles and no files, finds few starts (19 of 105 within 10 s); it is not offered as a mode on its own.
- The learned transition detector is off on the hosted tool (unlicensed training audio).
Models and licences
Standard tier. Licence posture: permissive (Apache, MIT or BSD).
- Song starts: spectral features and a novelty curve from the audio, a tracklist parser, and a resolver that turns your times, your track-file matches and the audio's change points into one start per song; writes the chapters (no model; CPU)decosa-cue engine (decosa_api/cue)Apache-2.0
- Finds each of your own track files in the mix from the audio (landmark pairs, searched across tempo changes of up to 6% and the pitch shift that comes with them) so its song gets an exact start (no model; CPU)Landmark matcher for your own track files (decosa_api/verticals/clearance fingerprinter)AGPL-3.0-or-later
All quality evidence
Every sourced number on the tool’s Stack tab, by tier. Some are proxies from another task; their labels say so.
Lite · titles and times only, any CPU (2)
- Song starts within 1 / 5 / 10 s, titles only (held-out synthetic mixes): 15/105 / 51/105 / 84/105decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (held out: 20 synthetic mixes of Decosa's own songs, 105 song starts, run once with thresholds frozen on a dev split)
- Song starts within 10 / 20 / 30 s, titles only, detector off, 8 real DJ mixes: 61 / 75 / 86 of 190 (5 s: 40)decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (8 public DJ mixes, 190 song starts; development numbers, not held out)
Standard · adds your own track files (hosted) (3)
- Song starts within 1 / 5 / 10 s, with your track files (held-out synthetic mixes): 24/105 / 92/105 / 105/105, with 105 starts predicteddecosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (held out: 20 synthetic mixes of Decosa's own songs, 105 song starts, run once with thresholds frozen on a dev split)
- By join (within 5 s / 10 s, of 35 each), with your track files: cuts 23 / 31, crossfades 31 / 35, blends 33 / 35decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (held out: 20 synthetic mixes of Decosa's own songs, 105 song starts, run once with thresholds frozen on a dev split)
- Time per 5-minute mix with track files (engine, held-out set): p50 4.46 s, p95 6.26 sdecosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (held out: 20 synthetic mixes of Decosa's own songs, 105 song starts, run once with thresholds frozen on a dev split)
Best · adds the learned transition detector (self-host only) (3)
- Held-out synthetic mixes, detector on: song starts within 10 s, titles only / with track files: 61/105 / 85/105 (not better on short synthetic songs)decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (held out: 20 synthetic mixes of Decosa's own songs, 105 song starts, run once with thresholds frozen on a dev split)
- Titles, the detector and a fingerprint service's identifications, 8 real DJ mixes (helps on real long mixes): 99 / 123 / 144 of 190 within 10 / 20 / 30 s (1 s: 26, 5 s: 74; 277 predicted starts); detector off: 70 / 95 / 146decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (8 public DJ mixes, 190 song starts; development numbers, not held out)
- Audio only (no titles), detector on, 8 real DJ mixes: 78 / 104 / 129 of 190 within 10 / 20 / 30 s (358 predicted starts)decosa-api docs/evals/mix-cue-sheet.md, 2026-09-29 (8 public DJ mixes, 190 song starts; development numbers, not held out)