From f11d5ce070eeb3857bc68a2cb13e1bee2a6e0f16 Mon Sep 17 00:00:00 2001 From: Meta Vens Date: Sun, 31 May 2026 20:44:23 +0100 Subject: [PATCH] Record corpus music curriculum run --- state/evidence.jsonl | 1 + state/scratch.md | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) diff --git a/state/evidence.jsonl b/state/evidence.jsonl index 10d502c..8079c32 100644 --- a/state/evidence.jsonl +++ b/state/evidence.jsonl @@ -260,3 +260,4 @@ {"date":"2026-05-31","area":"song-full-iteration-loop","lesson":"Song agents need a studio loop, not a one-shot submission. `song-prepare --duration-seconds 0` freezes full decoded songs; the swarm exposes `-FullSongs`; song challenges and candidate renders now include whitened spectral autocorrelation over band-whitened log-mel flux; and the prompt requires five local score/revise attempts per target before publishing a final patch. Candidate-side analysis artifacts let agents compare their Faust render against the target using the same feature vocabulary instead of guessing from the final verdict.","evidence":"tools/IpaTrialWorker/Program.cs; tools/run-song-snippet-trial-swarm.ps1; artifacts/parity/song-candidate-feature-smoke-2; artifacts/parity/song-snippet-swarms/20260531T120800752"} {"date":"2026-05-31","area":"cultcache-storage","summary":"Full-song song-trial stores can exceed 2 GB; single-file MessagePack snapshot flushing is the wrong owner for hot trial writes because it rewrites every cold record and can OOM. CultLib now has DirectoryMessagePackBackingStore: .cc is a small schema manifest, records live under .records/*.msgpack, and AquaSynth trial-result stores open with UseDirectoryStore=true.","verification":"dotnet test E:\\Projects\\CultLib\\tests\\GameCult.Caching.Tests\\GameCult.Caching.Tests.csproj --no-restore --filter BackingStoreTests: 14 passed; dotnet build E:\\Projects\\AquaSynth\\tools\\IpaTrialWorker\\IpaTrialWorker.csproj --no-restore: passed; dotnet test E:\\Projects\\AquaSynth\\tests\\AquaSynth.Dsl.Tests\\AquaSynth.Dsl.Tests.csproj --no-restore --filter CultCache: 7 passed"} {"date":"2026-05-31","area":"music-production-knowledge-cultcache","summary":"Fresh music curriculum stores should be distilled from official rendered evidence, not copied from hot trial stores. `music-distill` now writes paged `MusicProductionKnowledgeDocument` records: one master quality standard, reusable scene-role doctrine for syrinx voice, subtractive drums, additive/PAD beds, and shaped texture, quarantined render-failure pressure, ranked rendered candidate patterns, and abstraction-ledger syntax-sugar pressure. Explorer commands `music-search` and `music-show` make the new store inspectable by fresh agents before patch authoring.","verification":"dotnet build E:\\Projects\\AquaSynth\\tools\\IpaTrialWorker\\IpaTrialWorker.csproj --no-restore: passed; dotnet test E:\\Projects\\AquaSynth\\tests\\AquaSynth.Dsl.Tests\\AquaSynth.Dsl.Tests.csproj --no-restore --filter CultCache: 7 passed; music-distill over artifacts\\parity\\song-snippet-swarms\\20260531T121228337 wrote 37 records from 28 official rows; music-search syrinx/drums and music-show quality-standard succeeded","evidence":"src/AquaSynth.Core/IpaTrialResults.cs; tools/IpaTrialWorker/Program.cs; artifacts/parity/music-knowledge/20260531T121228337/music-production-knowledge.cc; artifacts/parity/music-knowledge/20260531T121228337/distillation-report.md; artifacts/parity/music-knowledge/20260531T121228337/show-quality-standard.md"} +{"date":"2026-05-31","area":"song-corpus-three-pass-curriculum","summary":"A three-pass 10-second corpus curriculum run across D:\\Music\\Reinier completed with 25 official assignments per pass. Pass 1 produced 25 official candidates, 23 rendered, 2 render failures, best cosine 0.299361, mean cosine 0.162788, mean score 0.198594, and 34 promoted music knowledge records. Pass 2 produced 25 official candidates, 20 rendered, 5 render failures, best cosine 0.351068, mean cosine 0.137059, mean score 0.170592, and 56 promoted music knowledge records. Pass 3 produced 25 official candidates, 15 rendered, 10 render failures, best cosine 0.304571, mean cosine 0.115347, mean score 0.128224, and 58 promoted music knowledge records. The learned signal is mixed: knowledge injection increased structured artifacts and reusable abstraction ledgers, but later-pass render failure and score degradation must be treated as quality pressure, not progress.","verification":"pass-001/pass-002/pass-003 each have 25 challenge.json files, 25 official candidates, 25 official summary.csv files, top-scoring-candidates.m3u, distillation-report.md, semantic-search-after.md, vector-index-after.md, music-production-knowledge.cc, music-production-knowledge-report.md, and music-production-quality-standard.md. Pass 3 was manually finished after external Codex jobs failed by promoting existing attempt-05 patches and running official scoring/promotion with IpaTrialWorker.exe.","evidence":"artifacts/parity/song-snippet-swarms/20260531T171802519/pass-001/music-production-knowledge.cc; artifacts/parity/song-snippet-swarms/20260531T171802519/pass-002/music-production-knowledge.cc; artifacts/parity/song-snippet-swarms/20260531T171802519/pass-003/music-production-knowledge.cc; artifacts/parity/song-snippet-swarms/20260531T171802519/pass-003/top-scoring-candidates.m3u; artifacts/parity/song-snippet-swarms/20260531T171802519/pass-003/distillation-report.md"} diff --git a/state/scratch.md b/state/scratch.md index 481b85d..8e72952 100644 --- a/state/scratch.md +++ b/state/scratch.md @@ -2,6 +2,23 @@ Current slice: +- Completed a three-pass corpus song curriculum run under + `artifacts/parity/song-snippet-swarms/20260531T171802519`: each pass prepared + 25 ten-second targets from `D:\Music\Reinier` for five agents with five + assignments each, then ran official scoring, playlist generation, semantic + search, trial distillation, and `music-distill` promotion. Pass 1 promoted 34 + music-production knowledge records, pass 2 promoted 56, and pass 3 promoted + 58. Final pass artifacts include `pass-003/top-scoring-candidates.m3u`, + `pass-003/distillation-report.md`, + `pass-003/music-production-knowledge.cc`, and + `pass-003/music-production-quality-standard.md`. The run exposed two harness + quality faults: spawned agents needed `E:\Projects\CultLib` as an added Codex + directory to run private scorers, and render-failed attempts must be handled + as negative evidence because candidate analysis files are absent. The pass-3 + outer swarm failed after agent jobs 2/3/4/5 exited nonzero, so the run was + finished by promoting existing attempt-05 patches from those agents into the + official patch tree and running official scoring/promotion manually. + - Built the first pruned music-production CultCache from the full-song iterative swarm artifacts instead of copying the old hot trial store. `music-distill` scans official pass summaries and abstraction ledgers, excludes iteration,