MONARK

Quality 80 / 100good

4 tools, about 2,718 tokens to load them all · tool set 203b40a46d2e · tools last changed 2026-10-06 · checked 2026-10-20 02:01 UTC

Tool changes

• 2026-10-06calibratechangedoutput schema
• 2026-10-06gatechangeddescription, output schema
  before

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. The class 'btc-dir-15m' is retired and answers a named refusal. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; each band edge is yhat - qhat or yhat + qhat rounded to the nearest double, so it can differ from the exact edge by up to half a unit in the last place of that edge; the band is not widened for it; on that key it requires alpha = 0.1, nMin = 50; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) the served region is a conformal upper bound on the liquidable amount for the calibrated class; the lower edge is 0 by construction, not a calibrated bound; abstains (under_calib) outside it; this class requires alpha = 0.01, nMin = 100; calibrated on one recorded episode; no coverage is claimed on any other event; the H-3 exchangeability check is a report, a YES licenses nothing more; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. No served class has a committed attestation subject (the retired 'btc-dir-15m' held the only one), so any `attested` is refused. The gate only emits a decision; it never calls the named tool.

  after · 80% of words in common

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. The class 'btc-dir-15m' is retired and answers a named refusal. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; on that key it requires alpha = 0.1, nMin = 50; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) the served region is a conformal upper bound on the liquidable amount for the calibrated class; the lower edge is 0 by construction, not a calibrated bound; abstains (under_calib) outside it; this class requires alpha = 0.01, nMin = 100; calibrated on one recorded episode; no coverage is claimed on any other event; the H-3 exchangeability check is a report, a YES licenses nothing more; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. The 32 kata classes `{btc,eth,bnb,sol}-{dir,range,mae-down,mae-up}-{1h,4h}` are served from their policy tables, which hold no committed calibration row: every well-formed kata call abstains with no region (under_calib, or non_evaluable on a dir lean of exactly 0), and no kata class has an attestation subject. A kata call carries a `predictor_id` of the form `kata:<kataId>@<venue>/<SYMBOL>/<h>` (no bucket, <h> the class horizon), a `features_digest`, alpha = 0.45, nMin = 6 on dir classes and alpha = 0.01, nMin = 299 on the others, tau at most 1 on dir classes, and a `produced_at` on the class horizon grid, received at most 300 s after it; the full request rules are in section 9 of the contract 1.1.0 specification. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. No served class has a committed attestation subject (the retired 'btc-dir-15m' held the only one), so any `attested` is refused. The gate only emits a decision; it never calls the named tool.

• 2026-10-04gatechangeddescription
  before

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. For 'btc-dir-15m' it conformalizes against a committed synthetic calibration derived from the HIKAE S2a instrument (seed 101, n=300 draw), declared synthetic — a plumbing fixture, not a measured predictor. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) the served region is a conformal upper bound on the liquidable amount for the calibrated class; the lower edge is 0 by construction, not a calibrated bound; abstains (under_calib) outside it; this class requires alpha = 0.01, nMin = 100; calibrated on one recorded episode; no coverage is claimed on any other event; the H-3 exchangeability check is a report, a YES licenses nothing more; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. The gate only emits a decision; it never calls the named tool.

  after · 88% of words in common

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. The class 'btc-dir-15m' is retired and answers a named refusal. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; each band edge is yhat - qhat or yhat + qhat rounded to the nearest double, so it can differ from the exact edge by up to half a unit in the last place of that edge; the band is not widened for it; on that key it requires alpha = 0.1, nMin = 50; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) the served region is a conformal upper bound on the liquidable amount for the calibrated class; the lower edge is 0 by construction, not a calibrated bound; abstains (under_calib) outside it; this class requires alpha = 0.01, nMin = 100; calibrated on one recorded episode; no coverage is claimed on any other event; the H-3 exchangeability check is a report, a YES licenses nothing more; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. No served class has a committed attestation subject (the retired 'btc-dir-15m' held the only one), so any `attested` is refused. The gate only emits a decision; it never calls the named tool.

• 2026-09-25gatechangeddescription
  before

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. For 'btc-dir-15m' it conformalizes against a committed synthetic calibration derived from the HIKAE S2a instrument (seed 101, n=300 draw), declared synthetic — a plumbing fixture, not a measured predictor. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) no liquidation-eligible-coverage calibration is committed yet; the gate abstains (under_calib) by construction; this class requires alpha = 0.01, nMin = 100; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. The gate only emits a decision; it never calls the named tool.

  after · 93% of words in common

  Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. For 'btc-dir-15m' it conformalizes against a committed synthetic calibration derived from the HIKAE S2a instrument (seed 101, n=300 draw), declared synthetic — a plumbing fixture, not a measured predictor. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. For 'stable-run-velocity-24h' (Narabi: a redemption-flow velocity forecast) the gate holds a committed stable-run velocity calibration for the USDe synthetic-dollar-whitelisted-redeem population (key narabi:persistence-v2@eip155:1/erc20:0x4c9edd5852cd905f086c759e8383e09bff1e68b3) over calm-window redemption flow; coverage is stated under the split-conformal bound of Barber, Candes, Ramdas and Tibshirani 2023 (Thm 2, unit weights): at least 1 − α minus the average total-variation gap between calibration windows and the next one; that gap is not estimated here and the calibration is measured non-stationary across half-years, so 1 − α is the coverage only if that gap is zero (exchangeability), which is not assumed here; no coverage is measured; for any other population, no stable-run velocity calibration is committed for this population; the gate abstains (under_calib). For 'liquidation-eligible-coverage' (Ukemi: a per-account liquidable-amount class, class A only) the served region is a conformal upper bound on the liquidable amount for the calibrated class; the lower edge is 0 by construction, not a calibrated bound; abstains (under_calib) outside it; this class requires alpha = 0.01, nMin = 100; calibrated on one recorded episode; no coverage is claimed on any other event; the H-3 exchangeability check is a report, a YES licenses nothing more; the bound holds only if yhat was produced by the frozen close-factor rule on a mono-collateral WETH account at the first crossing, which the gate does not check. When the caller instead supplies a `calibration` (its own nonconformity scores plus a `mode`: `interval` ⇒ region [yhat - q̂, yhat + q̂], or `set` ⇒ a conformal set over caller `candidates`), the gate conformalizes against THOSE caller-supplied scores (BYO): split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right. A caller-carried `attested` price must declare a subject consistent with the committed task class (exact committed-URL membership; BYO classes do not accept `attested` in P1); the attestation is carried by the caller and is not re-verified at call time (the verifier is not executed here); `attest` only projects the committed witness — verify a caller-carried attestation offline with the Shōgen verifier; no temporal binding in P1. The gate only emits a decision; it never calls the named tool.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.