ADRs tagged tiny-ai¶
Auto-generated by scripts/docs/generate-adr-by-tag.sh. Edit ADR Tags: lines to update.
26 ADR(s) carry this tag.
| ID | Title |
|---|---|
| ADR-0109 | Nightly bisect-model-quality runs against a synthetic placeholder cache |
| ADR-0168 | Tiny-AI Wave 1 baselines C2 + C3 — KoNViD-1k training (T6-1) |
| ADR-0169 | ONNX op-allowlist — admit Loop + If with recursive subgraph scan (T6-5) |
| ADR-0170 | vmaf_pre extended to 10/12-bit and optional chroma (T6-4) |
| ADR-0171 | Bounded Loop.M trip-count guard (T6-5b) |
| ADR-0172 | MCP describe_worst_frames tool with VLM fallback (T6-6) |
| ADR-0173 | PTQ int8 audit implementation — registry schema + scripts + CI gate (T5-3) |
| ADR-0174 | First per-model PTQ — learned_filter_v1 dynamic int8 (T5-3b) |
| ADR-0207 | Tiny-AI Quantization-Aware Training (QAT) — design |
| ADR-0208 | First per-model QAT — learned_filter_v1 int8 (T5-4) |
| ADR-0235 | Codec-aware FR regressor (fr_regressor_v2) |
| ADR-0236 | 0236-dists-extractor.md |
| ADR-0244 | vmaf_tiny_v2 — canonical-6 + StandardScaler tiny VMAF MLP |
| ADR-0248 | nr_metric_v1 joins dynamic-PTQ family (T5-3d) |
| ADR-0249 | Tiny-AI Wave 1 baseline C1 — fr_regressor_v1 on Netflix Public |
| ADR-0258 | ONNX op-allowlist — admit Resize for saliency / segmentation models (T7-32) |
| ADR-0262 | bisect-model-quality cache check uses logical comparison for parquet |
| ADR-0272 | fr_regressor_v2 codec-aware scaffold (Phase B prereq) |
| ADR-0275 | vmaf_tiny_v3 and vmaf_tiny_v4 join dynamic-PTQ family (T5-3d follow-up) |
| ADR-0287 | vmaf_tiny_v5 — corpus expansion (4-corpus + YouTube UGC vp9 subset) |
| ADR-0389 | vmaf_tiny_v3 — wider/deeper mlp_medium tiny VMAF MLP |
| ADR-0390 | vmaf_tiny_v4 — mlp_large arch (opt-in only; arch ladder stops here) |
| ADR-0432 | High-Bit-Depth ROI-Score Mask Materialisation |
| ADR-0444 | Promote saliency_student_v2 to production default |
| ADR-0647 | Refresh fr_regressor_v1 from the 2026-05-20 Netflix feature table |
| ADR-0660 | Tiny-AI extractors check DNN availability before model paths |