Skip to content
Tidebook

← Methodology

The classifier, explained

The Read’s state line comes from a single, versioned, deterministic classifier - regime.py’s classify() function. Given the same inputs, it always produces the same output: no wall-clock reads and no external calls.

The inputs themselves can change. Data providers correct recent days, and some inputs are ranked against all history up to that day, so the amount of history loaded matters. That is why a past day can be classified differently when the classifier is run again, and why the last section of this page exists.

Version

The currently pinned version is v1.1. v1 shipped first and its thresholds are frozen permanently once shipped - a rule change is never an edit to v1’s numbers, only a new version (v2, or a dotted follow-up like v1.1). v1.1 is exactly that: an additive follow-up, not a replacement. It changed exactly one thing - see “v1 versus v1.1” below - and everything else about the classifier’s scope, inputs, and vocabulary carries over from v1 unchanged.

Input set: core versus modifier versus adjacent

The classifier reads four input families, and only four: valuation (MVRV, confirmed by Puell Multiple), flows (net exchange flow, exchange reserve change), volatility (30-day realized volatility), and halving position (calendar, always available). These are the core inputs - the only things that can move state_id, the six-way valuation-band × flow-direction label the Read shows.

Two other kinds of input exist and are deliberately kept out of state_id:

Sentiment is adjacent, not core

Fear & Greed is computed and shown next to the state line as a divergence signal - useful context for whether the market’s mood agrees or disagrees with the fundamentals the classifier actually reads - but it never feeds state_id or the core inputs above, in any version. A market that turns euphoric or panicked purely on sentiment, with valuation and flows unchanged, reads as an unchanged state here. That’s the intended design: this classifier describes valuation, flows, volatility, and cycle position, not the full scope of market psychology, and sentiment is kept visibly separate rather than quietly blended in.

The hysteresis rule

A raw daily classification only becomes a confirmed state change after it holds for 3 consecutive days. If today’s raw reading differs from the currently confirmed state, that’s a candidate - not yet a transition. Only once the same differing reading has held for three days running does the classifier record a transition, backdated to the first of those three days. A candidate streak that breaks early - reverting to the already-confirmed state, or switching to a third state before reaching three days - never becomes a transition at all; those in-between days end up attributed to whichever state the streak eventually resolves to. This rule exists specifically to keep a single noisy day from flipping the headline state and flipping it back.

v1 versus v1.1: the neutral-band fix

v1’s flow-direction signal draws on a 30-day rolling sum of net exchange flow, recomputed daily. Because it’s a rolling sum, a single volatile day entering or leaving that 30-day window can cross zero on its own, flipping the coin-flow direction (coins leaving versus moving to exchanges) with no real change in the underlying trend - a flicker, not a real regime shift. v1.1 addresses this with one addition: a neutral dead-zone of ±5,000 BTC around zero on the 30-day flow signal specifically. A value inside that band abstains from casting a vote rather than forcing a fresh flow-direction reading off a borderline number; the 90-day exchange-reserve-change signal, a slower window and not the diagnosed source of the flicker, is left unbanded and can still decide the direction on its own. Nothing else changed - same six-state vocabulary, same core/modifier/adjacent split, same 3-day hysteresis rule, same institutional-era comparison window. v1 itself remains frozen and unedited; v1.1 is purely additive.

How our record works

Tidebook keeps two kinds of history, and each page says which one you are reading.

Published. Since 25 Sep 2026 the Read has been saved once a day, at the moment it was published. A saved Read is written once, and the database refuses to change or delete it. If a saved Read turns out to be wrong, a correction is added as a new row that points to the old one, and the old row stays. The first weeks of the record were copied from an earlier daily table that could be overwritten, so read those weeks with that in mind.

Reconstructed. Everything before that was worked out afterwards, in October 2026, by running the classifier over the stored data. Tidebook did not publish those reads at the time. They carry a “Reconstructed” label, and a reconstructed label can differ from what a live run would have shown on that day.

Why a past day can change. Data providers correct recent days, and the classifier ranks each day against all history up to that day. If the data or the amount of history changes, a re-run can give a different answer for an old day. A period also starts on the first of its three confirming days, so a live run only knows about it two days later.

When a re-run disagrees. A published period keeps its published label, dates and page address. The page adds a dated note that shows what was published and what today’s re-run says. A period that today’s re-run reports but Tidebook never published gets no page of its own. The history page lists it instead.

Versions. A change to the rules is a new classifier version. Saved Reads keep the version they were published under and are never relabelled with a newer one.