Skip to content

Releases: arnavd371/Project-Kaan

v3.1.1 — Comment cleanup

Choose a tag to compare

@arnavd371 arnavd371 released this 04 Aug 11:44

Strip decorative section banners and narrating comments from Python sources. Keep leakage warnings, Balingbing citations, and librosa parity notes. Web meta description no longer says “AI-Powered”.

Sole author: Arnav Dhiman.

v3.1.0 — Workshop-competitive research release

Choose a tag to compare

@arnavd371 arnavd371 released this 04 Aug 11:24

Summary

Workshop-facing research release on top of the v3 distilled production model.

  • Multi-seed advanced suite (42/43/44) with bootstrap 95% CIs — robustness, calibration, hierarchical heads, SSL
  • Hierarchical fine-tune (strict gate): 97.15% vs 96.84% baseline (seed 42)
  • CCAI @ NeurIPS 2026 Papers-track draft in workshop/
  • LIMITATIONS.md — IRRI ≠ phone-on-bag; soft 84.51% reference
  • Apache-2.0 — filled LICENSE appendix + detailed NOTICE; web/ aligned from MIT

Copyright © 2026 Arnav Dhiman (arnavd371@gmail.com). Sole GitHub contributor.

Key numbers

Metric Value
Baseline acc (3-seed mean) 96.73% ± 0.37%
SSL acc (3-seed mean) 96.62% ± 0.18%
Phone-band robustness 60.9% ± 8.4%
SNR ≤10 / hard combos ~7.6%
Hier fine-tune (seed 42) 97.15%

Paths

  • Aggregate: experiments/results/advanced_multiseed/
  • Hier FT: experiments/results/hier_finetune/
  • Paper: workshop/kaan_ccai_neurips2026.pdf
  • Changelog: CHANGELOG.md

v3.0.0 — Distilled production model

Choose a tag to compare

@arnavd371 arnavd371 released this 04 Aug 09:10

Summary

  • Distilled production CNN from gbdt + extratrees + cnn_deep soft labels (Kaggle T4)
  • Seed-42 val: 97.15% (macro F1 0.977) vs hard-only 95.57% and teacher ensemble 95.89%
  • Shipped INT8 TFLite (~333 KB) + ONNX for web/
  • Apache LICENSE / NOTICE filled with Arnav Dhiman contact details
  • Distill pipeline: model/distill.py, model/export_deploy.py, experiments/kaggle/push_distill.sh

Report

See experiments/results/distill/distill_report.md.

Not in this release

Field microphone corpus / phone-on-bag calibration (still desk-bound IRRI + ambient clean).

Kaan v2.0.0

Choose a tag to compare

@arnavd371 arnavd371 released this 04 Aug 06:46

Summary

Multi-approach bake-off (11 models), multi-seed stats, audits, and findings.
Production phone app path unchanged (INT8 / ONNX mel-CNN).

Approaches

cnn_shallow, cnn_deep, cnn1d, yamnet_probe, svm_rbf, mlp, gbdt, rf, extratrees, knn, logreg

Multi-seed accuracy (seeds 42/43/44 vs 84.51% ref)

Approach Acc mean ± std Seeds > ref
gbdt 95.36% ± 1.50 3/3
cnn_deep 95.15% ± 0.48 3/3
extratrees 94.94% ± 1.10 3/3
svm_rbf 94.73% ± 1.20 3/3
logreg 94.09% ± 1.59 3/3
rf 93.67% ± 0.95 3/3
cnn_shallow 93.57% ± 1.28 3/3
mlp 92.09% ± 0.32 3/3
knn 90.30% ± 0.37 3/3
yamnet_probe 85.65% ± 1.83 2/3
cnn1d 64.77% ± 20.7 1/3

Assets

  • stats.md / stats.json / aggregate_metrics.json / per_seed_metrics.json
  • findings_seed{42,43,44}.md
  • MODELS.md

Author: Arnav Dhiman. Apache-2.0.

CNN ablation summary table

Choose a tag to compare

@arnavd371 arnavd371 released this 29 Jul 15:27

Ablation comparison table. Author: Arnav Dhiman.

Ablation: baseline CNN

Choose a tag to compare

@arnavd371 arnavd371 released this 29 Jul 15:27

Ablation: baseline CNN

Author: Arnav Dhiman.

Ablation: without label smoothing

Choose a tag to compare

Ablation: without label smoothing

Author: Arnav Dhiman.

Ablation: without class weights

Choose a tag to compare

Ablation: without class weights

Author: Arnav Dhiman.

Ablation: without SpecAugment

Choose a tag to compare

Ablation: without SpecAugment

Author: Arnav Dhiman.

Ablation: full CNN recipe

Choose a tag to compare

@arnavd371 arnavd371 released this 29 Jul 15:27

Ablation: full CNN recipe

Author: Arnav Dhiman.