Question 1

How are detection models evaluated in GAS?

Accepted Answer

Discriminative miners submit models in safetensors format. Each model passes an entrance exam (80% accuracy threshold on a reduced dataset within 1 hour 25 minutes) before being benchmarked against the full dataset suite, which includes public benchmarks, private holdout datasets, and weekly-refreshed synthetic media from GAS-Station. Models are scored using `sn34_score`, a geometric mean of normalized MCC (classification accuracy) and Brier score (calibration quality), weighted across multiclass provenance labels (real, synthetic, semisynthetic, and rendered for video). One model per hotkey per modality; new models require new hotkeys.

Question 2

What hardware do discriminative miners need?

Accepted Answer

Discriminative miners do not need to host inference hardware. Models are submitted as files and evaluated on validator infrastructure. Generative miners, by contrast, run FastAPI servers on their own hardware and require GPUs (or external API access) to generate synthetic media on demand in response to validator prompts.

Question 3

How do generative miners earn rewards?

Accepted Answer

Generative miners earn base rewards proportional to their validation pass rate (content that passes C2PA signature checks and prompt alignment validation) and a multiplier based on fool rate—how often their synthetic media causes discriminators to misclassify. The multiplier also includes sample-size bonuses (logarithmic scaling up to 2× for high evaluation volume). Rewards are weighted by the cost of the generation model used; more expensive models earn higher per-sample rewards, incentivizing investment in quality infrastructure.

Question 4

What does C2PA verification mean for generative miners?

Accepted Answer

C2PA (Coalition for Content Provenance and Authenticity) is a metadata standard that digitally signs synthetic media to prove its origin. Validators reject unsigned content from generative miners to prevent gaming and wasted API costs. Supported generation services include OpenAI (DALL-E, Sora), OpenRouter (Google Veo, ByteDance Seedance), Stability AI, and Runway—all of which produce C2PA-signed output. Miners can verify local files with `gascli generator verify-c2pa <file>`.

Question 5

How is the reward split among detection and generation?

Accepted Answer

Total emissions are split: 40% image detection lane, 40% video detection lane, 4% audio detection lane, 16% generators. Within each detection lane, emissions follow a 'King of the Hill' model: 85% to the current best model, 10% to the previous best, 5% to the model ranked third. A challenger must score at least 0.01 higher than the reigning model to take the lane. When a new benchmark version releases, the defending king must re-evaluate to keep the crown (dethroning is frozen during defense).

Question 6

What modalities and classification classes are supported?

Accepted Answer

Image models classify into three classes: real, synthetic, and semisynthetic (original media with localized AI-generated edits). Video models classify into four: real, synthetic, semisynthetic, and rendered. Audio models classify into two: real and synthetic. Each modality is scored independently; miners may submit to multiple modalities by registering separate hotkeys.

Question 7

Can I run GAS locally or on a private network?

Accepted Answer

GAS runs on Bittensor Subnet 34 (mainnet). Installation requires Python 3.10+, uv, Git, and system dependencies (ffmpeg, build tools, Node.js/PM2 for process management). Validators require an NVIDIA GPU with 80 GB VRAM (A100 recommended) for generation services. Discriminative miners only need to submit model files; generative miners need access to generation APIs or local GPU resources. Docker Compose is provided for validator setup with shared volumes for caches and wallet data.

Question 8

What datasets does GAS use for benchmarking?

Accepted Answer

GAS evaluates against multiple sources: public benchmark datasets (image, video, audio) available in GASBench, private holdout datasets (not visible to miners), and continuously updated GAS-Station data from generative miners. Datasets are refreshed weekly. The round configuration assigns target weights to public, private, and GAS-Station samples. See GASBench's documentation for the full taxonomy and metric formulas.

BitMind

BitMind

Hardware Requirements

Hardware Requirements

Miner Setup

Validator Setup

Participate

Participate

Hardware Requirements

Hardware Requirements

Miner Setup

Validator Setup