mirror of
https://github.com/ruvnet/RuView.git
synced 2026-06-02 00:58:56 +02:00
ruv
a6808568a2
AetherArena ("AA") — the official, project-agnostic Spatial-Intelligence Benchmark
(ADR-149, Accepted). Iteration 1 of the long-horizon build:
- ADR-149 accepted: name locked (ruvnet/aether-arena), v0 metrics locked
(pose/presence/latency/determinism), dataset legality resolved (MM-Fi CC BY-NC
only; Wi-Pose excluded). Adds four-part framing, threat model, arena_score
formula, submission state machine, neutrality/governance, and the §7 acceptance test.
- aa_score_runner: deterministic scorer bin reusing the real ruview_metrics pose
harness on a fixed seed=42 fixture → RuViewTier-style verdict + cross-platform
SHA-256 proof hash. Builds --no-default-features (no torch/GPU). VERDICT: PASS.
- CI harness gate: .github/workflows/aether-arena-harness.yml runs the scorer on
every PR — the "PR that runs the harness as part of the build" requirement.
- Scaffold: aether-arena/{README,VERIFY,STATUS}.md + schema/aa-submission.toml.
- Horizon record persisted (.claude-flow/horizons/aether-arena-aa.json).
Infra = the deliverable; model SOTA (MM-Fi PCK@20) is a separate effort blocked on
ADR-079 data collection, tracked as a stretch goal, not an infra exit.
Co-Authored-By: claude-flow <ruv@ruv.net>
42 lines
1.7 KiB
TOML
42 lines
1.7 KiB
TOML
# AetherArena submission manifest (ADR-149 §2.2).
|
||
# Accompanies a model artifact pushed to the AA Hugging Face Space.
|
||
# This file is the contract the Space validates before quarantine + scoring.
|
||
|
||
[submission]
|
||
# Free-form display name shown on the leaderboard.
|
||
name = "my-spatial-model"
|
||
# Hugging Face repo or URL of the model artifact (.safetensors / .rvf / LoRA adapter).
|
||
model_ref = "hf://your-org/your-model"
|
||
# Submitter handle (HF username / org). Used to sign the ledger row.
|
||
submitter = "your-hf-username"
|
||
# SPDX license of the submitted model.
|
||
license = "Apache-2.0"
|
||
|
||
[category]
|
||
# One of: pose | presence | tracking | vitals | multi-task
|
||
# v0 ranks: pose, presence (tracking/vitals activate when ground truth lands).
|
||
primary = "pose"
|
||
|
||
[input]
|
||
# Which ADR-145 FeatureSet the model consumes. v0 input is RF/WiFi CSI.
|
||
# F0 = CSI amplitude/phase F1 = +CIR F2 = +Doppler F3 = +BFLD
|
||
feature_set = "F0"
|
||
# Tensor I/O contract so the scorer can feed the model correctly.
|
||
input_shape = [114, 2] # subcarriers × {amp, phase} (example)
|
||
output_shape = [17, 2] # 17 keypoints × {x, y} normalised [0,1]
|
||
# Normalisation expected on the input ("none" | "zscore" | "minmax").
|
||
normalization = "zscore"
|
||
|
||
[runtime]
|
||
# Inference entrypoint inside the artifact (framework-specific).
|
||
framework = "candle" # candle | onnx | torch
|
||
# Optional: target the edge-latency category with a declared device class.
|
||
device_class = "cpu" # cpu | pi5 | gpu
|
||
|
||
# Notes:
|
||
# - You submit a MODEL, never predictions on data you hold.
|
||
# - Scoring runs against a PRIVATE MM-Fi held-out split in a no-network,
|
||
# read-only sandbox. You cannot see the eval data.
|
||
# - The resulting score is a signed, append-only ledger row carrying a
|
||
# determinism proof hash and the pinned harness_version.
|