Neuron registration trends
The alpha price in τ, day by day, and what moved it each way.
Log change over the last 30 days −3.08%: protocol buys 0.00%, root sells −6.43%, users net +9.81%, cross-subnet −6.46%, unattributed +0.0001%.
The chart follows the alpha price in τ. Each period starts at its opening price and steps through the mechanisms below, in a fixed order, to its closing price: a step that rises pushed the price up, one that falls pushed it down, and its height is how far it moved the price. A thin line carries each close into the next period’s open; it is dashed where the two differ. The faint candle behind each period is the market’s own open, high, low and close, for context.
With many periods on screen (90 days, or hours), the steps would be too thin to read, so the chart draws the price as a line instead and colours each period by the mechanism that moved it most. Hover a period for the full step-by-step breakdown.
Not here, because they do not move the spot price: the per-block TAO injection into the pool, and burns.
All figures are log changes, not simple percentage changes, so the parts add up exactly to the total; on big moves the two differ (a 10% log fall is a 9.5% price fall).
2026-11-07 UTC, as of ≈22:16 UTC (block 9,457,174)
The day isn’t over yet, so these figures keep changing. They are in no daily total, average or rank.
Online poker platforms struggle to reliably identify automated play. Bot detection cannot depend on a single action or known signature—bots and humans play by the same rules, and systems must generalize across diverse bot families and player styles while resisting shortcuts based on identity or source. Static evaluation benchmarks also suffer from overfitting and do not reflect live competitive conditions.
Poker44 addresses this by creating a decentralized network where independent miners compete to build better bot-detection models, each evaluated against the same private ground truth in real time. Validators retain labels and actor groups locally, so miners receive only behavioral features stripped of cards, exact amounts, timing, and identity—forcing models to learn genuine strategic patterns rather than exploitable shortcuts. Actor-balanced scoring ensures no single prolific player dominates the evaluation window.
Miners operate Bittensor Axons that receive ordered micro-sessions containing exactly four coarse poker decisions and return calibrated risk scores in [0,1] per session. Validators lease immutable tournament-derived windows, query all eligible miners, score responses locally using average-precision skill, low false-positive recall, and Brier skill, then settle weights deterministically—rewarding the highest-scoring model without EMA or arbitrary miner caps.
Auto-generated from the GitHub repository and may not reflect the latest changes.
Poker44 is a decentralized evaluation network for online-poker bot detection that rewards models assigning calibrated bot-risk probabilities to short sequences of poker decisions. Miners operate Axons serving detection models that classify tournament micro-sessions as human or bot-generated, while validators evaluate miners against private ground truth and settle weights deterministically based on quality metrics including average-precision skill, recall at low false-positive rates, and Brier skill.
Poker44 operates a three-layer evaluation pipeline: (1) Tournament Layer: humans and external agents play in tournaments on the Poker44 platform, generating consented gameplay and telemetry. Quality gates and schema-v4.1 micro-session construction remove raw telemetry, cards, exact amounts and identifiers. (2) Validator Layer: validators poll the platform for sealed evaluation windows containing immutable, ordered schema-v4.1 items. Each validator leases the same items, verifies dataset hash integrity, separates and retains labels locally, then queries every registered reachable miner Axon with MicroSessionDetectionSynapse requests. (3) Miner Layer: miners receive ordered lists of four-decision micro-sessions and return exactly one finite risk_score per item in [0,1], where 0=strongest human confidence and 1=strongest bot confidence.
Validators score responses locally using actor-balanced metrics, select the deterministic winner, and settle weights: 0% burn, 5% tournament funding, 95% winner by default. Labels and actor groups never reach miners; miner-visible payloads contain only decision features (decision_number, phase, position_group, pressure, action_type, size_bucket, is_all_in).
Invalid, missing, non-finite, out-of-range or wrong-length miner responses score zero. Actor-balanced sample weights ensure one prolific player cannot dominate the window by giving equal mass to each private actor within each class. Validators query every registered, reachable non-validator miner Axon (no 10/32-miner cap).
The highest-scoring hotkey wins the miner share for a round; multiple hotkeys under the same coldkey compete independently. Weights are support signals for Yuma Consensus and are refreshed every 720 blocks without re-querying miners when the target remains unchanged.
The sections above were auto-generated from the GitHub repository and may not reflect the latest changes. View repository (github.com, opens in a new tab, external site)
Decentralized Generative Video Platform
This information was auto-extracted from the GitHub repository and may be incomplete or out of date. Always refer to the subnet's GitHub repository (github.com, opens in a new tab, external site) for the latest instructions.
Hardware requirements: see the subnet's repository (github.com, opens in a new tab, external site)
Clone the Poker44 subnet repository
git clone <repo> && cd poker44
Install Python dependencies
pip install -r requirements.txt
Configure wallet, hotkey, subnet netuid and Axon port
export WALLET_NAME=<name> HOTKEY=<hotkey> NETUID=126 AXON_PORT=<port>
Set model factory import path (or use reference factory default)(optional)
export POKER44_MODEL_FACTORY=module:create_model
Configure model artifact path, device, and version string(optional)
export POKER44_MODEL_PATH=<path> POKER44_MODEL_DEVICE=<cpu|cuda> POKER44_MODEL_VERSION=<version>
Run code quality checks before deployment(optional)
ruff check poker44 neurons tests
Run unit tests before deployment(optional)
PYTHONPATH=. pytest -q
Start the miner with PM2 process manager
bash scripts/miner/run/run_miner.sh
Verify miner registration, Axon reachability, model version, and incentive on-chain(optional)
pm2 describe poker44-miner && pm2 logs poker44-miner
Clone the Poker44 subnet repository
git clone <repo> && cd poker44
Install Python dependencies
pip install -r requirements.txt
Configure wallet, hotkey and subnet netuid
export WALLET_NAME=<name> HOTKEY=<hotkey> NETUID=126
Set subnet data platform URL (default shown)(optional)
export POKER44_SUBNET_DATA_URL=https://api.poker44.net
Configure weight emission policy: burn fraction, funding fraction and funding hotkey(optional)
export POKER44_BURN_FRACTION=1.00 POKER44_FUNDING_FRACTION=0.00 POKER44_FUNDING_HOTKEY=<hotkey>
Configure validator polling, weight refresh cadence and round retry parameters(optional)
export POKER44_POLL_INTERVAL_SECONDS=300 POKER44_WEIGHT_REFRESH_BLOCKS=720 POKER44_ROUND_MAX_ATTEMPTS=3
Enable automatic validator updates from main branch(optional)
export AUTO_UPDATE_ENABLED=true TARGET_BRANCH=main
Run code quality checks before deployment(optional)
ruff check poker44 neurons tests
Run unit tests before deployment(optional)
PYTHONPATH=. pytest -q
Start the validator with PM2 process manager and auto-update watcher
bash scripts/validator/run/run_vali.sh
Verify validator and auto-update process status(optional)
pm2 describe poker44-validator && pm2 describe poker44-validator-auto-update
Monitor validator logs for window acquisition, miner queries, scoring and settlement(optional)
pm2 logs poker44-validator
| Day (UTC) | Share |
|---|---|
| 2026-11-06 | 0.00% |
| 2026-11-05 | 0.00% |
| 2026-11-04 | 0.00% |
| 2026-11-03 | 0.00% |
| 2026-11-02 | 0.00% |
| 2026-11-01 | 0.00% |
| 2026-10-31 | 0.00% |
| 2026-10-30 | 0.00% |
| 2026-10-29 | 0.00% |
| 2026-10-28 | 0.00% |
| 2026-10-27 | 0.00% |
| 2026-10-26 | 0.00% |
| 2026-10-25 | 0.00% |
| 2026-10-24 | 0.00% |
| 2026-10-23 | 0.00% |
| 2026-10-22 | 0.00% |
| 2026-10-21 | 0.00% |
| 2026-10-20 | 0.00% |
| 2026-10-19 | 0.00% |
| 2026-10-18 | 0.00% |
| 2026-10-17 | 0.00% |
| 2026-10-16 | 0.00% |
| 2026-10-15 | 0.00% |
| 2026-10-14 | 0.00% |
| 2026-10-13 | 0.00% |
| 2026-10-12 | 0.00% |
| 2026-10-11 | 0.00% |
| 2026-10-10 | 0.00% |
| 2026-10-09 | 0.00% |
| 2026-10-08 | 0.00% |
| 2026-10-07 | 0.00% |
| 2026-10-06 | 0.00% |
| 2026-10-05 | 0.00% |
| 2026-10-04 | 0.00% |
| 2026-10-03 | 0.00% |
| 2026-10-02 | 0.00% |
| 2026-10-01 | 0.00% |
| 2026-09-30 | 0.00% |
| 2026-09-29 | 0.00% |
| 2026-09-28 | 0.00% |
| 2026-09-27 | 0.00% |
| 2026-09-26 | 0.00% |
| 2026-09-25 | 0.00% |
| 2026-09-24 | 0.00% |
| 2026-09-23 | 0.00% |
| 2026-09-22 | 0.00% |
| 2026-09-21 | 0.00% |
| 2026-09-20 | 0.00% |
| 2026-09-19 | 0.00% |
| 2026-09-18 | 0.00% |
| 2026-09-17 | 0.00% |
| 2026-09-16 | 0.00% |
| 2026-09-15 | 0.00% |
| 2026-09-14 | 0.00% |
| 2026-09-13 | 0.00% |
| 2026-09-12 | 0.00% |
| 2026-09-11 | 0.00% |
| 2026-09-10 | 0.00% |
| 2026-09-09 | 0.00% |
| 2026-09-08 | 0.00% |
| 2026-09-07 | 0.00% |
| 2026-09-06 | 0.00% |
| 2026-09-05 | 0.00% |
| 2026-09-04 | 0.00% |
| 2026-09-03 | 0.00% |
| 2026-09-02 | 0.05% |
| 2026-09-01 | 0.07% |
| 2026-08-31 | 0.07% |
| 2026-08-30 | 0.07% |
| 2026-08-29 | 0.08% |
| 2026-08-28 | 0.08% |
| 2026-08-27 | 0.08% |
| 2026-08-26 | 0.08% |
| 2026-08-25 | 0.08% |
| 2026-08-24 | 0.08% |
| 2026-08-23 | 0.08% |
| 2026-08-22 | 0.09% |
| 2026-08-21 | 0.11% |
| 2026-08-20 | 0.11% |
| 2026-08-19 | 0.11% |
| 2026-08-18 | 0.06% |
| 2026-08-17 | 0.06% |
| 2026-08-16 | 0.06% |
| 2026-08-15 | 0.06% |
| 2026-08-14 | 0.07% |
| 2026-08-13 | 0.07% |
| 2026-08-12 | 0.05% |
| 2026-08-11 | 0.05% |
| 2026-08-10 | 0.06% |
| 2026-08-09 | 0.06% |
