Miner FAQ

What do LIVE, APPROVED and PENDING mean?

LIVE

LIVE: in force now and run by the current validator release. APPROVED: decided and announced, takes effect at the date shown. PENDING: the decision is still open; the text says what is being decided, and nothing in it is a rule yet. Times are in UTC with Berlin time in brackets. Berlin moves from summer time (UTC+2) to winter time (UTC+1) on Sunday 25 October 2026, so from then on 14:30 UTC is 15:30 Berlin.

The full rules are on the rules page; the exact files and constants are in the public reax-subnet repository. If this FAQ and the running release seem to differ, tell us in #92. For APPROVED answers the announced rule applies from the date shown, and we fix the code or this page before then.

Where do I ask a rules or status question?

LIVE

Ask in #92 on the Bittensor Discord, so everyone sees the answer. Direct messages are the exception: use them for private matters (keys, ownership proofs, code releases) or if you cannot post in #92. Errors in your own entry: see below. We answer once an hour between 06:30 and 21:30 UTC (08:30–23:30 Berlin until 24 October, 07:30–22:30 Berlin from 25 October).

How is the miner emission split between the tracks?

LIVE

Since 21 October 2026, 13:00 UTC (15:00 Berlin): inference 50%, REAX Engine 20%, generalist decision model 30% of the miner part of the emission. Inside a competition track the share is split 75% / 17% / 8%: the champion, the champion dethroned most recently, and the one dethroned before that. A share that nobody may be paid (no champion yet, award not approved, slot expired) goes to the inference miners (except the short keep-share cases in this answer). It never moves up to the next rank and nothing is burned. Rewards are a protocol mechanism, not a promise of any amount, and can be zero.

Are 17% and 8% paid to places 2 and 3 of a ranking?

LIVE

No. 75/17/8 means the champion plus the two most recently dethroned champions (former-champion slots), in the order they lost the title, not by score. On the generalist track a former-champion slot has no time limit: it ends when newer former champions push it out. On the engine track it also ends 7 days after losing the title. A former champion is paid only while it stays committed by the same hotkey with a valid result and a valid award approval. Runners-up of a crowning are not paid; the one exception is places 2 and 3 of the generalist opening (next answer).

What do places 2 and 3 of the generalist opening get?

APPROVED effective Fri 23 Oct 2026, 13:00 UTC (15:00 Berlin)

As a one-time exception for the opening cohort, the next two entries after the three co-champions take the former-champion slots: place 2 (UID 160) the 17% slot and place 3 (UID 113) the 8% slot, if they clear the entry floor, beat their base model by 1.5 points and pass the normal award review, from Friday 23 October 2026, 13:00 UTC (15:00 Berlin), for at most 7 days. Like every former-champion slot they are pushed out by newer former champions (so the 7 days are a maximum), and each is paid only while its award approval is valid. There is no extra emission. Before Friday 13:00 UTC their weight does not rise yet, even with a signed approval.

When did the generalist track open, and what happened to demand forecasting and risk assessment?

LIVE

The generalist track is open since Wednesday 21 October 2026, 13:00 UTC, with no end date. Demand forecasting and risk assessment ended at that same moment (their earlier published end was 30 October 2026, 12:00 UTC) and are no longer paid. Their champions and approved former champions kept a bounded legacy keep-alive for 7 days (details).

Who holds the generalist title now?

LIVE

The opening playoff ended in a practical tie, so UID 116, 199 and 250 are co-champions. They share the 75% champion share in equal thirds (25% of the track share each), and each third is paid only with that entry’s own award approval; an unpaid third goes to inference. The set holds the title until a challenger beats the best of the three by the required margin on the challenger’s own draws (all three are served on every challenger draw). Live status: live queue.

What happens when one entry clearly wins a crowning slot?

APPROVED from the Mon 26 Oct 2026 slot; exact criteria PENDING

A clear winner takes the whole 75% champion share. The former-champion shares stay 17% and 8%, and there is no extra emission.

PENDING The exact test for “clear winner” (the required gap or statistical threshold) is still being decided. We will publish it with the rollout announcement, at least 48 hours before Monday’s slot, and we will not apply a threshold that has not been published here.

What if the leading entries are practically tied?

APPROVED from the Mon 26 Oct 2026 slot; exact criteria PENDING

For close results we test additional shared tasks. Only practically tied leading models share the champion share. All entries that confirmed before a slot are compared on shared fresh rounds. Entries share the 75% champion share equally (two entries 37.5% each, three 25% each) only if both hold: they are still not statistically separated from the leader after up to three shared rounds, and every one of them lies within a small, pre-announced score gap of the leader. The gap is measured from the leader for each entry, so a chain of entries that are each close to the next cannot pull in a clearly weaker model. Practically tied is not the same as equal: not being statistically separated does not prove that two models are the same. There is no silent fallback to “the highest mean takes everything”, on the generalist track ties are never decided by commit order, and no one outside the tied group is paid as a runner-up.

A joint champion group later counts as one former champion: it is dethroned together when a challenger beats its best member by the required margin, and it then shares one former-champion slot equally.

PENDING The size of the score gap, what happens to an entry that is not separated but lies outside the gap, and the safeguards against copies and several entries of one coldkey are still being decided. The gap is calibrated against the measurement precision and independently reviewed before any result, and it is published here at least 48 hours before the first slot it applies to, once approved.

What happens to the three co-champions when a challenger beats them?

APPROVED approved 22 Oct 2026; applies when the co-champions are beaten

The beaten co-champion set becomes one former-champion slot, shared equally by the three (each part paid only with its own approval). It does not take three slots.

Can you show concrete payout examples?

PENDING examples of the approved 22 Oct shares; tie criteria and slot ordering still open

These examples show the approved policy from the Monday 26 October slot. All numbers are parts of the generalist track share (30% of the miner part of the emission). Every part is paid only with a valid award approval; anything unpaid goes to inference.

• Clear winner. Entry A wins a slot clearly: A 75%. The most recently dethroned champion 17%, the one before 8%.
• Tied group of two. A and B are not separated after up to three shared rounds and B is within the pre-announced gap of A: A 37.5%, B 37.5%; former slots 17% and 8% unchanged.
• Tied group of three. A, B and C: 25% each; former slots unchanged.
• Beaten co-champions. A beats the best of UID 116, 199 and 250 clearly: A 75%; the three share one former-champion slot equally (if that is the 17% slot, about 5.67% each; the order against UID 160 and 113 is PENDING, see below).
• A tied group is beaten later. Challenger X beats the better of A and B by the margin: X 75%; A and B together form one former champion and share its slot equally.
• Today, before any new crowning. UID 116, 199 and 250 25% each; from Fri 23 Oct 13:00 UTC also UID 160 17% and UID 113 8% (opening places).

PENDING If the co-champions are beaten while the opening places 2 and 3 still run, the published push-out rule would give: the three former co-champions 17% together (about 5.67% each), UID 160 8% (until 30 October, 13:00 UTC at the latest), UID 113 nothing. This ordering is confirmed in the rollout announcement before Monday.

When is the next generalist crowning?

APPROVED next slot Mon 26 Oct 2026, 14:30 UTC (15:30 Berlin)

There is no Friday slot. The next generalist crowning slot is Monday 26 October 2026, 14:30 UTC (15:30 Berlin, winter time). A challenger is crowned only at a slot, after it has confirmed; its confirmation has to be decided before 14:30 UTC to count for that slot. Later slots are announced in advance. Submissions stay open all the time.

The engine track has its own schedule and is not tied to these slots (engine title).

I am in the queue under the current evaluation. What happens when eval v5 starts?

APPROVED for the Mon 26 Oct 2026 slot

Rule A: entries that confirm under the current evaluation before Monday 26 October, 14:30 UTC are decided at that slot under the current evaluation, and the winner (or a tied leading group) is crowned as earned. After the slot every title is defended on eval v5 and new entries are scored on v5. If v5 binds, an entry that has not confirmed by then is re-evaluated under v5 automatically after the switch; you do not need to recommit.

When does eval v5 become binding?

APPROVED target Mon 26 Oct 2026, 14:30 UTC, subject to the validation check

The target is the Monday slot. Before v5 binds we check that our private test set ranks about 40 open models the way the public Decision Indexes do. If the check passes by Sunday 25 October, 18:00 UTC (19:00 Berlin), v5 applies from Monday’s slot. If not, the current evaluation stays after Monday’s slot and v5 binds from the first slot after the check passes (earliest Thursday 29 October, 14:30 UTC, 15:30 Berlin). We post the result of the check by Sunday 25 October, 18:00 UTC (19:00 Berlin) at the latest; the rules for the slot are announced before then.

What does eval v5 measure?

APPROVED with eval v5

Eval v5 is built to rank models the way the Hugging Face Decision Index and the Artificial Analysis Decision Index do; we check this before it binds (previous answer). About 60% of the score comes from private tests of the same skills as the public Decision Index benchmarks (knowledge and reasoning, language, retrieval and classification, tools, human taste), and about 40% from private decision tasks in new domains. Every scored item is private. Public items, including our dev set, count 0%; a public score far above the private score triggers a review. An item with several questions counts only if every answer is right. Up to 26 options are served per question, and there is no thinking.

How does the “I don’t know” option work?

APPROVED with eval v5

Fact questions offer “I don’t know” as an extra last option. A correct answer scores +1, a wrong answer −1, “I don’t know” 0. We read your served probabilities as usual: your top option is your answer, with no threshold or temperature on top. So abstaining when unsure pays on these questions.

Where are the v5 format, dev set and scorer?

PENDING link added once published (planned Fri 23 Oct 2026)

The exact item format, a 300-item public dev set and the reference scorer will be published in the public reax-subnet repository. We will link them here as soon as they are public. The dev set has weight 0 in the score and shares no items or sources with the private test set; use it to check your pipeline end to end, not to rank models finely.

Will I see my v5 score before v5 binds?

PENDING decision open

Not yet decided. If we publish v5 shadow scores of current entries before the switch, they are information only and do not decide anything; this answer will say where to find them.

Do the co-champions keep their title under v5?

APPROVED with eval v5

Yes. The co-champions keep the title and are re-scored under v5 on every challenger draw. A challenger has to beat the best of them, and its own base, by the margin.

Why is my entry still queued?

LIVE

Our competition worker runs an evaluation cycle about once an hour and evaluates up to 8 models per hour across the tracks; the champion is one of them. New entries wait for the next cycle in the order of their on-chain commitment, except that first evaluations of entries whose hotkey is already past its immunity period go first. The live page explains each status (queued, waiting for repo, waiting for base model, evaluating, pending confirmation).

How large is a generalist draw, and what margin do I need?

APPROVED effective Fri 23 Oct 2026, 13:00 UTC (15:00 Berlin)

Until Friday 23 October, 13:00 UTC a draw has 300 fresh sealed items (30 per area) and the minimum margin is 1.5 points. From then on a draw has 900 items (90 per area) and the minimum margin is 1.0 point; the statistical bar stays the same. Items, draw seeds and the scores on private items are never published.

What do the first stage, z and a close call mean?

LIVE

z is your gain over the champion on the same items divided by its standard error. On the first draw, z ≥ 2 and a gain of at least the minimum margin pass. A close call (1 ≤ z < 2) gets exactly one more first-stage draw, and z < 1 is not better. At confirmation you need a pooled z ≥ 2.75 over all your draws against that champion. Against the co-champions, the bar is the best of the three on your draw.

When does my confirmation draw run?

LIVE

On a fresh draw disjoint from your first draw, at least 12 hours after the first draw (also after a close call). The time on the live page is an estimate that depends on the cycle and the queue.

How is the gap penalty computed?

LIVE

The gap is your score on our generator-family items minus your score on the cross-author items. S_eff = S − min(10, 0.5 × max(0, gap − G_med − A)), with the frozen median gap G_med = 14.84 and A = max(8, 2 × SE). S_eff is the score every decision uses under the current evaluation. The live page does not show the penalty itself, because with the raw score it would reveal the score on the private items.

PENDING Whether and how a gap penalty applies under eval v5 comes with the v5 notice.

What are the generalist entry floor and the non-procedural floor?

LIVE

The entry floor is 36.8 and the non-procedural keep-alive floor 37.4 under the current evaluation. An entry at or below the entry floor earns nothing from the track. Floors for eval v5 come with the v5 notice.

Do the per-area scores matter?

LIVE

They are shown with every entry and are information only: a model far below the reference in one area gets a closer look in the award review. Before a generalist award we also compare the new champion with the official base on our private Decision-Index-style evaluation; if it is clearly worse there, the award goes to a manual review.

How is a Decider-style model with a separate readout head run?

LIVE

A Qwen3.5-family backbone with readout.safetensors and decision_config.json is run on our own runtime the way it was trained: your readout head as submitted, on the last prompt position, with our fixed REAX prompt and a fixed temperature of T=2. The temperature in decision_config.json is metadata only, so calibrate your head for T=2.

What may a generalist entry be?

LIVE

Up to 36B parameters and 68 GiB of safetensors weights, dense or MoE: Qwen3 and Qwen3-MoE, Qwen3.5 (including MoE), Gemma 3, Gemma 4 or Llama. The repo must be public and carry an Apache-2.0, MIT or BSD LICENSE file (Google’s Gemma 4 repos do not ship one, so add it). Weights only: no repository code is ever executed. Commit reax-spec/1:generalist:<hf_repo>@<40-hex revision> with a reax-specialist.json that says "category": "generalist".

Do I have to fine-tune the official base?

LIVE

No. The official base is decisionmodels/reax-1 at revision ca2a0cc5; any allowed architecture within the limits works. The base matters for entries above 10B parameters (they must beat their own unmodified base by 1.5 points for the keep-alive) and for the derived-entry rule.

Are there limits on what I may train on?

LIVE

The rules do not restrict training data beyond the licence of the model you publish. What we enforce is on the evaluation side: private draws nobody sees, the gap penalty, and from v5 a review when your public score is far above your private score.

What counts as a copy or a derived entry?

LIVE

Exact copies (same tensor hash) are refused, and the earliest commitment owns a hash; re-sharding or renaming files does not hide a copy, and for generalist entries the check also hashes the backbone without the readout head. An entry is derived if you declare another entry as your base or our checks find that its weights or answers derive from an earlier entry. It must beat its parent by the full decision margin and, on competence alone, by at least 1.0 point and 2 standard errors, so a recalibrated copy cannot be crowned. Independent fine-tunes of the official base are not affected.

I merged other entries into my model. Is that allowed?

LIVE

Yes, but a model close to an earlier entry is checked as derived (previous answer), and the award review looks at the merge share and the credit. State your recipe and the credit clearly in the repo.

May I reuse another engine entry’s code or binaries?

APPROVED effective Fri 23 Oct 2026, 13:00 UTC (15:00 Berlin)

Ideas are free. You may reuse code or binaries of other entries if you declare them in the image label ai.reax.engine.parents, a JSON list such as [{"uid": 4, "digest": "<64 hex>", "files": ["/app/engine.py", "/app/kernels/"]}] (at most 8 parents; a path ending in / covers the directory). Your entry must then beat every declared or detected parent by the full challenger margin. Undeclared reuse counts as a copy: the first time the entry is not evaluated, the second time the hotkey is paused for 7 days. Reusing your own earlier entries is free. Details: ENGINE-COMPETITION.md, section 5a.

Does an engine entry need published source?

LIVE

Yes. Nothing without published source is paid: an engine whose kernels or code are not published can be measured, but its award is held until the source is public. One engine champion is held for this reason today (see the live queue).

How many entries can one coldkey hold?

LIVE

At most 2 open submissions per track and 4 new submissions per 7 days per coldkey. One hotkey holds one competition commitment; a new commitment from the same hotkey replaces the old one. Paid waiting keep-alives are limited to 2 per coldkey per track, and the provisional keep-alive to one per coldkey per track.

What is the keep-alive, and who gets it now?

LIVE

A participation weight so that a waiting entry is less likely to be deregistered; it is not an award and needs no approval. An entry pending confirmation (up to 24 hours after its first pass) or a new champion waiting for approval (up to 24 hours after crowning) gets the weight of a typical inference miner if it scored above the entry floor and the non-procedural floor; at most 8 such entries per track, together at most a quarter of the track share. An entry still queued for its first evaluation gets a provisional keep-alive of half that, from about 2 hours before its hotkey’s immunity ends, for at most 12 hours per hotkey and one per coldkey per track. A keep-alive does not reserve a UID or guarantee that a hotkey is never deregistered.

What changes for waiting entries with eval v5?

APPROVED with eval v5

New entries get a provisional half keep-alive from their commitment, for at most 12 hours from the commitment, so nobody is pruned before their first evaluation. It is revoked if the first draw fails. A commitment older than 12 hours gets no such window.

What happened to the demand forecasting and risk assessment champions?

LIVE

For 7 days from the generalist opening (until 28 October 2026, 13:00 UTC, 14:00 Berlin) the champion of each ended track and its approved former champions get a bounded keep-alive, only as pure entrants: it ends early if the hotkey commits to anything else, including a generalist entry or serving weight.

My hotkey was pruned while my entry waited for confirmation. Is my first draw lost?

LIVE

Not necessarily. If you commit the same model (identical tensors) again within 72 hours of the prune, under any new hotkey or UID, by the same coldkey or from the same Hugging Face repo, you keep your first-draw score and go straight to the confirmation draw. The repo’s reax-specialist.json must name the new hotkey, and copy checks still apply. A changed commitment while the hotkey stays registered is not a prune and carries nothing over.

Do I get my registration fee back if I lose or am pruned?

LIVE

No. Registration burns TAO and the chain sets the cost, so check it before you register; fees are not refunded.

What is an award approval, and what does the review check?

LIVE

A winning entry is paid only after we check and approve it: the champion and every paid former slot, for exactly one entry (track, hotkey, repo@revision or image digest). A new revision or digest needs a new approval. The automatic copy and near-duplicate checks must pass first; then we look at provenance, originality and credit for merged or reused work. Approvals are signed with our owner key and published in approvals.json; validators accept only a valid signature for exactly that entry.

How long does an award decision take?

APPROVED effective Fri 23 Oct 2026, 13:00 UTC (15:00 Berlin)

From Friday 23 October, 13:00 UTC we decide every award within 6 hours of the crowning, counted inside our signing window of 10:00–22:00 Berlin time. Clear cases under the published rules are approved automatically; cases that need a closer look still get a person’s decision within the same 6 hours. Until then decisions are made in the same window, and the live page shows an estimate. An award on hold (for example, source not published) is decided once the hold is cleared; the live page shows its status.

My entry is champion. Why is its share not paid yet?

LIVE

Its award is pending or on hold (for example: source not published, a copy question, a missing licence). Meanwhile, on the generalist track the previously approved champion keeps the champion share for up to 48 hours; after that the share goes to inference until the approval exists. While the three co-champions hold the title there is no keep-share: an unapproved third goes directly to inference. On the engine track the most recently approved champion keeps the champion share until the new champion is approved. Nothing is burned and the next rank does not move up.

My award is approved. When does my incentive change on chain?

LIVE

A new approval takes effect with the next weight set after validators read it. Weights reach the chain with commit-reveal, so a change becomes visible about one epoch (360 blocks, about 72 minutes) after it is set, and your incentive follows at the epoch step. A slot that starts at a fixed time (for example Friday 23 October, 13:00 UTC) shows up the same way. If nothing has changed after a few hours, tell us.

How does the engine title work?

LIVE

Every submission is measured against the reference engine on the same GPU in the same session. It must pass the correctness gate and be at least 3% faster than the reference; a challenger takes the title only with at least 3% more than the champion, confirmed in a second fresh session. The champion’s share halves linearly over 14 days; the previous champion gets 17% and the one before 8%, each for up to 7 days after losing the title and after its own award review. Current holders and measured speeds: live queue.

What reference speed is the engine measured against?

LIVE

Only the ratio counts. Every submission is measured against the reference engine on the same GPU in the same session, interleaved. On our evaluation GPU (RTX PRO 6000 Blackwell Server Edition) the reference runs at about 100 decisions/s.

My engine entry is marked “not owner”. What do I do?

LIVE

The image label ai.reax.engine.hotkey must name the hotkey that committed the digest. Rebuild the image with the label set to your committing hotkey, push it, and commit the new digest.

How do waiting engine entries avoid being pruned?

LIVE

Entries waiting for their evaluation get a small bounded keep-alive: half the median inference weight each, together at most 5% of the engine share. It is also paid to the champion while its award review is pending and to former champions that hold a slot.

Can one hotkey serve inference and compete at the same time?

LIVE

Yes, since block 9331987 (about 13:00 UTC on 21 October 2026): one hotkey can serve inference and hold one competition entry. Serving and competition pay add up per UID; the keep-alive of a dual-role entry is a top-up over what it earns from serving.

Can one hotkey carry several models?

LIVE

Yes, since the same block: 2 to 4 inference models per hotkey (commitment reax-s1m/1), each with the same per-model cap as a separate hotkey. You publish one axon per hotkey; it still holds only one competition commitment.

Why is there a per-hotkey cap, and how do I run 8 GPUs?

LIVE

Validators verify each hotkey’s throughput with their own probes, and that has a limit: 1,280 decisions/s for s1-fast, 320/s for s1-pro, 32/s for s1-lite and 4/s for s1-cpu. Pay stays linear in verified throughput, so above the cap use more hotkeys or more models per hotkey.

I think my entry was scored or paid wrongly. Where do I report it?

PENDING formal channel pending approval; this is how we handle reports now

Report it in #92 with evidence: your UID, the entry (repo@revision or image digest), what you expected, what you see, and links or timestamps (for example a wrong number, the wrong entry, or a rule applied differently from its text). Use a direct message only if the case needs private details such as keys or ownership proofs. We look at every genuine individual case and answer it. Every slot result is posted with its rounds, scores and standard errors.

PENDING A formal error-report process with a fixed response time is still being decided; until then we answer as soon as we have checked the case.

Are answers from a bot or an AI assistant binding?

LIVE

No. Only the published rules, this FAQ and our announcements in #92 are binding. An automated or AI-written reply can be wrong; it never replaces the rules and never stops you from reporting a real problem.