Skip to content

Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

27.7 KB
Raw Blame

forge benchmark: v2r5

made: out/forge_v2; refs: /refsets.json; 2026-10-16 15:58

Medians per set. made = the made sounds vs the bench refs; real x = the forge refs (real, never in the bench) vs the bench refs; real loo = each bench ref vs the other bench refs. typ z, phrase z, margin, AS names: higher is better; tone dB, env oct (octaves off in attack / t40 / length), curve dB: lower is better; t40 x = tail length / bench median (1 = same). inside = checks (of n) a made sound lands inside the real 80% limit, median over the made sounds (real = the same count for the real rows). var cos = mean pairwise CLAP cosine within the set (made variants / forge refs / bench refs): high = the variants are near clones.

category set n typ z tone dB env oct curve dB t40 x phrase z margin AS names artifacts var cos inside
click made 5 0.21 8.79 0.23 8.83 1.44 3.03 0.24 0 0 0.723 7 / 7 (real 6)
real x 8 0.16 11.33 0.22 9.92 1.33 2.77 0.53 0.12 0 0.651
real loo 7 -0.1 9.85 0.46 13.19 0.86 2.67 0.27 0 0 0.576
downlifter made 6 3.23 0.92 0.33 0 0.749
note: empty: the licensed library has no downlifter, real or designed (no reversing or pitching of other sounds here: trim + fade only). Benchmark made downlifters on phrasings, AudioSet and artifacts only.
glitch made 6 2.03 -0.13 0 0 0.728
note: empty: no glitch material, real or designed, in the licensed library. Benchmark made glitches on phrasings, AudioSet and artifacts only.
hover_tick made 5 0.13 20.99 1.51 6.27 1.1 2.41 0.66 0 0 0.807 6 / 7 (real 5)
real x 6 0.09 21.2 1.64 9.88 0.9 2.51 0.9 0 0 0.799
real loo 6 0.47 15.46 1.16 19.39 1.2 2 0.58 0 4 0.626
impact made 6 4.38 2.39 30.05 0.58 3.25 0.9 1 0 0.849 6 / 6 (real 3)
real x 2 6.19 2.5 31.98 0.46 3.04 1.09 0.5 0 0.659
note: thin: the library has three cinematic hits (all three were the v1 impact forge refs); one is held out as bench, so v1 impact bench numbers are optimistic.
logo_sting made 5 13.08 1.68 13.93 1.04 1.38 -0.47 1 0 0.716 5 / 6 (real 5.5)
real x 2 15.52 1.46 21.27 1.7 1.4 -0.82 0.5 0 0.185
real loo 2 23.22 0.81 8.99 1.12 1.36 -0.58 1 0 0.507
note: no real logo stings exist in the library (they are composed); the refs are the struck metal / glass rings a sting ends on: a tail-shape and tone reference only.
notify made 6 0.15 15.63 0.66 13.09 0.86 1.54 -0.5 1 0 0.867 7 / 7 (real 5.5)
real x 5 -0.24 21.3 1.3 28.92 0.34 1.25 -0.24 1 0 0.593
real loo 5 3.84 16.7 0.81 17.41 1.19 1.76 -0.91 1 0 0.476
note: struck bells / glass / kalimba (forge) and celesta / glass / triangle (bench), rings capped at 2 s with a 0.25 s fade; no designed UI dings in the library.
pop made 5 -0.02 11.42 0.55 11.01 0.82 2.32 -0.2 0.4 0 0.735 7 / 7 (real 6)
real x 7 -0.09 16.06 1.51 20.54 0.91 2.46 -0.5 0.29 0 0.501
real loo 6 1.13 13.66 0.41 12.5 1.02 1.96 -1.06 0.67 0 0.522
pro_click made 5 15.43 1.28 13.47 0.8 3.91 2.28 0 0 0.786 5 / 6 (real 4)
real x 1 29.35 1.06 10.68 0.53 4.25 2.96 0 0
real loo 2 18.53 1.73 8.99 1.08 2.19 0.51 0 2 0.45
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md).
pro_glitch made 6 2.53 0.24 0 0 0.853
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only, one example.
pro_hover_tick made 5 -1.32 6.25 0.82 10.43 1 1.61 0.45 0 0 0.862 6 / 7 (real 6)
real x 3 -2.23 6.51 1.11 20.12 1 3.04 0.97 0 0 0.82
real loo 3 8.32 0.67 5.84 0.86 1.79 0.71 0 1 0.684
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md).
pro_impact made 5 2.17 -0.09 0.6 0 0.788
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only (one SFX-only film); designed, sub-heavy, gated tails.
pro_logo_sting made 5 15.62 2.15 22.33 0.24 1.02 -0.68 0.2 0 0.642 4 / 6 (real 6)
real x 1 15.49 2.84 24.51 0.06 0.99 -0.25 0 0
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge: falling chirp into a tonal hum; bench: a music end chord with a 4 s tail.
pro_notify made 5 2.16 0.38 1 0 0.936
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only.
pro_pop made 6 22.93 1.41 35.59 0.75 3.29 1.76 0 0 0.649 3 / 6 (real 3)
real x 2 18.43 2.78 42.94 0.06 3.54 2.33 0 0 0.488
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md).
pro_pop_in made 5 0.93 -3.13 0 0 0.75
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). not a forge category yet: element-in micro hits (thump + tick), forge only.
pro_riser made 5 17.88 1.54 36.57 0.05 2.71 0.47 0.2 0 0.712 4 / 6 (real 6)
real x 1 21.35 0.79 18.43 0.68 1.03 -0.72 0 0
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge: one designed stutter riser; bench: one noise riser at a film end.
pro_shimmer made 5 3.29 1 0.2 0 0.646
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only; one granular sparkle + one melodic chime run.
pro_sub_drop made 5 24.84 0.54 16.11 1.64 2.44 0.68 0 0 0.835
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). bench only, one example under music + voice.
pro_tap made 5 1.98 1.93 0.2 0 0.861
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only, one example.
pro_typing_key made 6 26.09 0.43 13.62 0.79 1.6 -0.96 0 0 0.815 4 / 6 (real 5.5)
real x 6 26.2 0.52 11.54 0.71 1.88 -0.42 0 0 0.849
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md).
pro_typing_run made 6 1.79 0.59 0 0 0.813
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). not a forge category yet: one whole designed typing run.
pro_whoosh_big made 6 3.71 1.56 0.83 0 0.882
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). forge only (one SFX-only film); the bench films bury their whooshes under music + voice.
pro_zip made 5 -2.41 11.89 0.71 20.81 0.84 2.34 -1.39 0 0 0.761 5 / 7 (real 5)
real loo 4 1.71 10.4 1 34.47 1.15 1.4 0.54 0 0 0.529
note: pro designed SFX from the reference launch films (bed under some trims; see docs/motion-sfx-study.md). not a forge category yet: tonal pitch sweeps, bench only (two films over music).
riser made 5 9.33 2.35 23.23 0.09 2.65 -0.3 0.6 0 0.801 3 / 6 (real 4)
real x 1 17.61 1.01 20.04 0.5 3.52 1.06 1 0
real loo 2 13.22 0.95 36.07 3.35 2.7 1.15 0.5 0 0.767
note: thin: one designed trailer riser (forge); the bench is two real cymbal swells, no synth risers.
shimmer made 6 1.07 10.68 0.35 4.06 0.97 3.46 0.91 0.67 0 0.845 7 / 7 (real 6)
real x 5 1.69 9.66 0.73 8.58 0.73 2.87 0.03 0.6 2 0.59
real loo 4 1.01 15.52 1.33 12.89 1.05 3.4 0.56 1 0 0.644
note: kit shimmer_01 (bar chimes sweep) is bench: its author also recorded the celesta notify bench.
sub_drop made 5 8.84 1.76 37.38 0.31 3.31 0.7 0 0 0.727
note: one designed source (a tom pitched down 24 semitones by its author), held out as bench; the forge has no sub-drop refs.
swipe made 5 -9.49 5.15 0.38 7.67 0.92 1.88 0.11 0.6 0 0.812 4 / 7 (real 6)
real x 4 -10.07 16.83 0.43 14.12 0.79 2.7 0.59 1 0 0.845
real loo 4 1.25 3.64 0.22 10.07 1.02 3.42 2.08 0.25 0 0.857
note: cloth only: the library has no paper slides.
swish made 5 0.62 6.69 0.23 11.69 1.02 2.94 1.62 0.8 0 0.796 5 / 7 (real 6)
real x 7 1.94 11.08 0.64 12.88 0.64 3.22 1.6 0.57 0 0.811
real loo 3 9.01 0.91 16.45 1.16 3.5 1.92 0.67 0 0.79
tap made 5 -2.31 5.81 1.4 11.65 1 1.12 0.77 0.2 0 0.782 4 / 7 (real 6)
real x 7 -1.17 9.35 1.59 13.67 1.64 1.85 0.92 0.14 0 0.713
real loo 6 1.66 16.78 1.19 11.59 1 1.62 0.35 0.17 0 0.716
toggle made 5 -3.4 7.82 0.42 10.11 0.74 1.72 -0.38 0 0 0.729 5 / 7 (real 6)
real x 4 -2.84 12.48 1.87 18.78 2.11 2.1 -0.02 0 0 0.477
real loo 4 1.54 6.25 0.28 4.92 1.02 1.94 -0.28 0 0 0.725
typing_key made 6 -0.32 7.44 1.04 9.08 1 3.74 1.45 0 0 0.713 4 / 7 (real 6)
real x 15 0.26 8.88 1.01 12.2 1.29 4.75 2.83 0.53 0 0.721
real loo 12 0.23 5.47 1.52 16.7 1 3.71 1.53 0.42 0 0.673
whoosh_big made 6 0.51 6.87 0.4 10.21 1.05 2.44 -0.02 0.83 0 0.76 7 / 7 (real 5)
real x 3 -0.27 8.8 1.13 19.46 3 2.92 0.04 1 0 0.7
real loo 3 4.25 0.43 6.67 0.97 1.88 0.19 0.33 0 0.495
note: forge = three designed Mixkit whooshes; bench = real air / cape swoops.
whoosh_fast made 6 -5.44 6.21 0.27 10.14 0.88 3.29 2.16 1 0 0.831 4 / 7 (real 6.5)
real x 5 0.57 10.31 1.22 20.2 0.6 4.14 2.78 0.4 0 0.826
real loo 5 1.52 4.58 0.4 8.21 1.08 4.14 2.62 0.8 0 0.772

Texture (medians; model-free, not in any forge objective): floor dB = 10th percentile 5 ms frame re the loudest (-120 = digital silence), stereo corr (1 = mono), darken = log2 centroid at half the tail / at the peak (< 0: the decay darkens).

category set floor dB stereo corr darken
click made -45.0 0.99 0.26
real x -42.85 0.99 -0.12
real loo -44.8 1.0 -0.07
downlifter made -54.45 0.67 -1.81
glitch made -44.95 0.09 0.04
hover_tick made -44.0 0.88 -0.09
real x -43.55 1.0 -0.09
real loo -24.9 0.52 -0.01
impact made -68.95 0.68 -0.96
real x -70.55 0.54 -1.3
logo_sting made -63.4 0.77 0.3
real x -52.1 0.59 -0.85
real loo -44.1 0.81 -1.43
notify made -43.7 0.98 -1.53
real x -41.2 0.99 -1.06
real loo -24.4 0.61 -0.53
pop made -62.8 1.0 0.25
real x -53.2 1.0 0.21
real loo -47.2 1.0 0.12
pro_click made -83.1 1.0
real x -108.5 0.0
real loo -30.6 0.95 0.26
pro_glitch made -44.85 0.04 0.04
pro_hover_tick made -37.8 0.26
real x -47.0 -0.0
real loo -37.4 0.16
pro_impact made -34.7 0.35 0.41
pro_logo_sting made -50.4 0.88 -0.62
real x -120.0 1.0 -0.38
pro_notify made -46.3 0.95 -0.37
pro_pop made -69.5 1.0 -0.31
real x -120.0 1.0
pro_pop_in made -61.5 0.58 -0.24
pro_riser made -32.5 0.82
real x -41.8 0.96 0.22
pro_shimmer made -49.0 0.33 -0.53
pro_sub_drop made -38.3 1.0 0.13
pro_tap made -83.3 0.42 0.07
pro_typing_key made -38.95 1.0 0.02
real x -53.55 1.0 -0.04
pro_typing_run made -57.95 1.0
pro_whoosh_big made -55.05 1.0 -1.31
pro_zip made -52.9 0.99 -1.67
real loo -21.95 0.93 0.24
riser made -37.6 0.61
real x -49.9 0.0
real loo -30.65 1.0 0.12
shimmer made -57.5 0.07 -0.64
real x -46.8 0.17 -0.29
real loo -36.1 0.68 -0.33
sub_drop made -67.0 1.0 -0.59
swipe made -61.9 0.64 0.19
real x -56.85 0.42 0.07
real loo -38.05 0.68 0.61
swish made -57.9 0.96 -0.02
real x -55.6 0.87 -0.16
real loo -44.6 1.0 -0.45
tap made -49.8 0.99 0.0
real x -43.6 1.0 1.31
real loo -38.4 1.0 0.94
toggle made -67.3 1.0 0.32
real x -48.4 1.0 -0.11
real loo -49.1 0.48 -0.18
typing_key made -51.8 0.96 -0.43
real x -43.7 0.76 0.04
real loo -39.65 1.0 0.09
whoosh_big made -59.3 0.94 -0.1
real x -43.2 0.66 -0.11
real loo -42.9 1.0 0.28
whoosh_fast made -63.35 0.97 -0.24
real x -65.4 0.81 -0.16
real loo -32.2 1.0 -0.2

Diversity among the made variants (CLAP cosine mean / max, tonal distance min dB, near duplicates):

  • click: cos 0.723 / 0.837, tone min 7.41 dB, 0 near duplicate pair(s) (bench refs: cos 0.576 / 0.792, tone min 6.13 dB)
  • downlifter: cos 0.749 / 0.955, tone min 3.12 dB, 0 near duplicate pair(s)
  • glitch: cos 0.728 / 0.871, tone min 1.8 dB, 0 near duplicate pair(s)
  • hover_tick: cos 0.807 / 0.923, tone min 3.74 dB, 0 near duplicate pair(s) (bench refs: cos 0.626 / 0.847, tone min 9.21 dB)
  • impact: cos 0.849 / 0.955, tone min 1.01 dB, 0 near duplicate pair(s)
  • logo_sting: cos 0.716 / 0.946, tone min 11.23 dB, 0 near duplicate pair(s) (bench refs: cos 0.507 / 0.507, tone min 23.22 dB)
  • notify: cos 0.867 / 0.959, tone min 5.35 dB, 0 near duplicate pair(s) (bench refs: cos 0.476 / 0.905, tone min 11.33 dB)
  • pop: cos 0.735 / 0.877, tone min 5.92 dB, 0 near duplicate pair(s) (bench refs: cos 0.522 / 0.832, tone min 7.62 dB)
  • pro_click: cos 0.786 / 0.902, tone min 6.93 dB, 0 near duplicate pair(s) (bench refs: cos 0.45 / 0.45, tone min 18.53 dB)
  • pro_glitch: cos 0.853 / 0.912, tone min 1.35 dB, 0 near duplicate pair(s)
  • pro_hover_tick: cos 0.862 / 0.942, tone min 1.79 dB, 0 near duplicate pair(s) (bench refs: cos 0.684 / 0.776, tone min 6.36 dB)
  • pro_impact: cos 0.788 / 0.898, tone min 5.23 dB, 0 near duplicate pair(s)
  • pro_logo_sting: cos 0.642 / 0.827, tone min 14.47 dB, 0 near duplicate pair(s)
  • pro_notify: cos 0.936 / 0.973, tone min 5.72 dB, 0 near duplicate pair(s)
  • pro_pop: cos 0.649 / 0.822, tone min 5.8 dB, 0 near duplicate pair(s)
  • pro_pop_in: cos 0.75 / 0.823, tone min 5.62 dB, 0 near duplicate pair(s)
  • pro_riser: cos 0.712 / 0.808, tone min 2.42 dB, 0 near duplicate pair(s)
  • pro_shimmer: cos 0.646 / 0.808, tone min 7.57 dB, 0 near duplicate pair(s)
  • pro_sub_drop: cos 0.835 / 0.885, tone min 4.46 dB, 0 near duplicate pair(s)
  • pro_tap: cos 0.861 / 0.939, tone min 7.57 dB, 0 near duplicate pair(s)
  • pro_typing_key: cos 0.815 / 0.952, tone min 1.1 dB, 0 near duplicate pair(s)
  • pro_typing_run: cos 0.813 / 0.951, tone min 1.36 dB, 0 near duplicate pair(s)
  • pro_whoosh_big: cos 0.882 / 0.966, tone min 3.24 dB, 0 near duplicate pair(s)
  • pro_zip: cos 0.761 / 0.922, tone min 3.83 dB, 0 near duplicate pair(s) (bench refs: cos 0.529 / 0.686, tone min 8.63 dB)
  • riser: cos 0.801 / 0.872, tone min 2.95 dB, 0 near duplicate pair(s) (bench refs: cos 0.767 / 0.767, tone min 13.22 dB)
  • shimmer: cos 0.845 / 0.938, tone min 6.82 dB, 0 near duplicate pair(s) (bench refs: cos 0.644 / 0.765, tone min 10.66 dB)
  • sub_drop: cos 0.727 / 0.889, tone min 4.89 dB, 0 near duplicate pair(s)
  • swipe: cos 0.812 / 0.897, tone min 2.37 dB, 0 near duplicate pair(s) (bench refs: cos 0.857 / 0.918, tone min 2.76 dB)
  • swish: cos 0.796 / 0.946, tone min 3.54 dB, 0 near duplicate pair(s) (bench refs: cos 0.79 / 0.908, tone min 9.83 dB)
  • tap: cos 0.782 / 0.892, tone min 3.68 dB, 0 near duplicate pair(s) (bench refs: cos 0.716 / 0.98, tone min 2.68 dB)
  • toggle: cos 0.729 / 0.782, tone min 4.99 dB, 0 near duplicate pair(s) (bench refs: cos 0.725 / 0.846, tone min 5.33 dB)
  • typing_key: cos 0.713 / 0.885, tone min 6.37 dB, 0 near duplicate pair(s) (bench refs: cos 0.673 / 0.919, tone min 4.64 dB)
  • whoosh_big: cos 0.76 / 0.902, tone min 3.3 dB, 0 near duplicate pair(s) (bench refs: cos 0.495 / 0.768, tone min 3.17 dB)
  • whoosh_fast: cos 0.831 / 0.921, tone min 3.0 dB, 0 near duplicate pair(s) (bench refs: cos 0.772 / 0.951, tone min 2.28 dB)

Judge notes (round 5, finalizer, 15:56-16:30)

Made = out/forge_v2/<category>/final/ after round 5 (183 sounds, 34 categories). Round 5 re-delivered 6 categories: whoosh_fast, tap, logo_sting (polish-ui) and pro_logo_sting, pro_pop, pro_notify (polish-pro). Their round-4 finals are in <category>/final_r4/. The other 28 categories are byte-identical to round 4 and give the same numbers. typing_key was replaced by a re-render from 14:21 to 14:44 and then restored from its original files; it measures exactly as in round 4. polish-ui ran the benchmark once (14:56) and polish-pro twice (14:47 on candidates, 15:05 on the final tree). This file is one full run at 15:58 on the delivered tree. Nothing was tuned on it. It only decided round 4 vs round 5 per category. Nobody has listened yet.

Rule for r4 vs r5: the same as round 4 and the progress file (blind_v2.verdict). A check counts as better or worse only when it moves relative to what real recordings score on it. The recording floor is left out. Model checks count as up or down. The areas' spectrogram sheets (out/forge_v2/_polish_ui/*_r4_r5.png, <category>/r4_vs_r5.png) break ties. Script: out/forge_v2/_final_r5/r4_vs_r5.py (local, not committed).

tap and pro_pop went back to round 4. Their rows in this file are the round-4 rows: same files, copied from results_v2r4.json, and the JSON says so under kept_r4. The round-5 deliveries are in <category>/final_r5/. Their as-run rows are in the table below and in out/forge_v2/_final_r5/results_v2r5_asrun.json (local).

Round 4 -> round 5 (made medians on the held-out bench; v2r4 vs v2r5 as run)

category var cos tone dB env oct curve dB t40 x phrase z margin AS names darken inside model-free better / worse models up / down kept
whoosh_fast 0.768 -> 0.831 6.28 -> 6.21 0.32 -> 0.27 10.32 -> 10.14 0.85 -> 0.88 3.23 -> 3.29 1.66 -> 2.16 0.5 -> 1.0 -0.05 -> -0.24 4 -> 4 1 / 0 3 / 1 r5
logo_sting 0.714 -> 0.716 13.06 -> 13.08 1.68 -> 1.68 14.29 -> 13.93 1.0 -> 1.04 1.25 -> 1.38 -0.48 -> -0.47 1 -> 1 0.41 -> 0.30 5 -> 5 1 / 0 1 / 0 r5
pro_logo_sting 0.908 -> 0.642 15.93 -> 15.62 2.50 -> 2.15 23.34 -> 22.33 0.12 -> 0.24 0.95 -> 1.02 -1.30 -> -0.68 0 -> 0.2 -0.65 -> -0.62 4 -> 4 1 / 1 3 / 0 r5
pro_notify 0.822 -> 0.936 - - - - 1.91 -> 2.16 0.15 -> 0.38 1 -> 1 0.39 -> -0.37 - 0 / 1 2 / 0 r5
tap 0.782 -> 0.813 5.81 -> 7.22 1.40 -> 1.19 11.65 -> 13.47 1.0 -> 1.36 1.12 -> 1.22 0.77 -> 0.38 0.2 -> 0.6 0.0 -> 0.04 4 -> 5 1 / 3 2 / 1 r4
pro_pop 0.649 -> 0.780 22.93 -> 22.61 1.41 -> 2.08 35.59 -> 37.19 0.75 -> 0.97 3.29 -> 2.75 1.76 -> 1.29 0 -> 0 -0.31 -> 0.03 3 -> 3 1 / 1 0 / 2 r4

The model-free counts leave out the floor. pro_logo_sting and pro_notify have no real variety row to judge against, so the rule leaves their variety out of the count. It is listed above, and it moves a lot in both.

Reasons:

  • whoosh_fast (r5).
    • Better: tail darkening -0.05 -> -0.24 (bench -0.2). The hiss band now sinks through the tail instead of hanging there as steam.
    • Model checks: AudioSet names it on all 6 (0.5 -> 1.0); margin 1.66 -> 2.16.
    • Costs: variety 0.768 -> 0.831 and CLAP typicality -4.25 -> -5.44. The variety stays inside the real rows (bench 0.772, forge refs 0.826), so it does not count.
  • logo_sting (r5).
    • Better: curve, darken and phrase z, slightly.
    • The area's model-free probes: decay roughness 0.46 -> 0.34 dB; reverse_bloom's pre-hit dip 14.6 -> 2.0 dB.
    • Unchanged: env oct 1.68. That comes from the lead-ins measured against bare rings, by construction.
  • pro_logo_sting (r5).
    • The clones are gone: variety 0.908 -> 0.642.
    • Tone, env, curve, t40, margin and AudioSet all move the right way.
    • The one worse check: stereo corr 1.00 -> 0.88, against a single mono music chord. The wide reverb tail is deliberate.
    • The area's diagnostic: CLAP 'gunshot' 2 of 5 -> 0, 'error buzz' 3 of 5 -> 1.
  • pro_notify (r5).
    • Variety is its only held-out model-free check, and it got worse: 0.822 -> 0.936 (the film dings score 0.868). The five members are one clean patch on a semitone ladder.
    • Kept on the spectrogram. Round 4 carries broadband hiss above 2 kHz through the whole ring; the film dings have that energy only from their music bed. Round 5 has the films' 2 kHz head -> 1 kHz body without the hiss.
    • Phrase z and margin went up. All five re-render exactly (round 4: 4 of 5).
  • tap (r4 kept).
    • Worse: variety 0.782 -> 0.813 (real 0.71), curve 11.65 -> 13.47 (best real 11.59), stereo corr 0.99 -> 0.93 (real 1.00).
    • Better: env oct only.
    • Tone 5.81 -> 7.22 and t40 x 1.00 -> 1.36 stay inside the real rows but move away from the bench median.
    • The model checks went up (AudioSet names 0.2 -> 0.6, inside 4 -> 5 of 7), which is what the area aimed for. By the trust order (model-free first) round 4 stays. The sheets show nearly the same sounds with slightly longer tails.
  • pro_pop (r4 kept).
    • Round 5 fixes the '8-bit' reading by the area's diagnostic: CLAP '8-bit / chiptune' in the top 3 on 3 of 6 -> 1 of 6.
    • On the held-out side, variety got worse (0.649 -> 0.780, forge refs 0.488) and both model checks fell (phrase z 3.29 -> 2.75, margin 1.76 -> 1.29). Tone got only slightly closer (22.93 -> 22.61).
    • On the sheet, four of the six round-5 members (02, 03, 05, 06) are near-steady tones at 0.5-1.5 kHz for 70-130 ms rather than pops. AudioSet puts 'Speech' first on 4 of 6.
    • Round 4's 01 and 02 still carry the stepped square gates that read '8-bit'. That fault stays open.

Reproducibility: the 4 round-5 deliveries that stay re-render from their report.json to max 2.5e-7 (the areas' checks). The restored round-4 tap and pro_pop finals re-render on today's code to max 1.6e-7 (pro_pop through pop.V2 with family.members[params.variant]).

v1 -> v2 (final), the five categories v1 had

category var cos v1 -> v2 (bench refs) t40 x v1 -> v2 (real x / loo) tone dB v1 -> v2 (real x / loo) curve dB v1 -> v2 env oct v1 -> v2 inside v1 -> v2 (real)
typing_key 0.965 -> 0.713 (0.673) 1.67 -> 1.00 (1.29 / 1.00) 8.20 -> 7.44 (8.88 / 5.47) 14.32 -> 9.08 1.07 -> 1.04 7 -> 4 of 7 (6)
click 0.886 -> 0.723 (0.576) 0.56 -> 1.44 (1.33 / 0.86) 7.60 -> 8.79 (11.33 / 9.85) 8.85 -> 8.83 0.56 -> 0.23 7 -> 7 of 7 (6)
pop 0.917 -> 0.735 (0.522) 1.00 -> 0.82 (0.91 / 1.02) 8.59 -> 11.42 (16.06 / 13.66) 6.29 -> 11.01 0.68 -> 0.55 7 -> 7 of 7 (6)
whoosh_fast 0.957 -> 0.831 (0.772) 0.51 -> 0.88 (0.60 / 1.08) 8.58 -> 6.21 (10.31 / 4.58) 15.93 -> 10.14 0.89 -> 0.27 7 -> 4 of 7 (6.5)
impact 0.931 -> 0.849 (forge refs 0.659) 0.50 -> 0.58 (0.46 / -) 6.70 -> 4.38 (6.19 / -) 24.86 -> 30.05 1.54 -> 2.39 5 -> 6 of 6 (3)

Only whoosh_fast changed since round 4: variety 0.768 -> 0.831, t40 x 0.85 -> 0.88, tone 6.28 -> 6.21. The progress file (out/showcase/progress/progress.md) counts model-free better / worse per check, v1 -> v2: key press 6 / 1, UI click 5 / 0, pop 3 / 1, fast whoosh 6 / 0, impact 3 / 0.

Breadth (the counts are the same as in round 4)

  • 34 categories, 183 finals, 0 artifact flags on the bench.
  • Tone. In 18 of 21 categories the made median is at least as close to the held-out balance as the real forge refs. The exceptions: pro_logo_sting 15.6 vs 15.5 dB, pro_pop 22.9 vs 18.4, shimmer 10.7 vs 9.7.
  • Inside the real limits. In 11 of 22 categories the made median is at or above a real recording's count: click, hover_tick, impact, notify, pop, pro_click, pro_hover_tick, pro_pop, pro_zip, shimmer, whoosh_big.
  • Variety. Made sets score 0.64-0.94. The most varied is now pro_logo_sting (0.642; it was the most clone-like at 0.908). The most clone-like are pro_notify 0.936 (a semitone ladder by design), pro_whoosh_big 0.882 and notify 0.867.

Verdicts after round 5

Showcase-ready, measured:

  • whoosh_big, swish, swipe, whoosh_fast
  • shimmer, click, pop (round-2 family), notify
  • impact, typing_key, pro_typing_key / run, pro_pop_in, pro_hover_tick, pro_click, pro_whoosh_big
  • logo_sting, downlifter, sub_drop, pro_glitch, pro_riser, pro_zip, toggle
  • pro_logo_sting, which leaves the weakest list

Weakest:

  • pro_pop: '8-bit' in two members. The round-5 fix was not kept.
  • tap: the model checks are low. The round-5 attempt traded model-free checks for them.
  • pro_notify: near clones by design. It is a clean ding now.
  • riser: AudioSet's nearest confusion is 'a jet engine starting'.
  • pro_impact: the model checks prefer round 3.
  • glitch, pro_tap.

Core: round 5 fixed the round-4 fill bug, where forge()'s final pass filled missing SPACE keys at mid-range. search.fill_start now fills from the start point, then the recipe's DEFAULTS, then the render module's DEFAULTS. It falls back to mid-range only with a MidRangeFill warning. An audit of all 34 finals found hidden mid-range values only in pro_impact. It is kept as delivered, because its swell member needs pre_shape 1.