Root InsideROOT INSIDE
Daily boards · model predictions and their scoring record

Frozen, anchored, and scored — nothing else

방향 없음·권유 아님 — 모델 예측과 채점 기록만 싣는다No direction, no recommendation — only model predictions and their scoring record.

Updated 2026-09-29 18:30:47 +09:00Schema ri_public_boards/v1 · e583a54dlatest.json fd275deb · facts 6Built 2026-10-19 17:40:34 +09:00 (2026-10-19 08:40:34 Z)
Publication status 1 published · 3 withheld
BoardStatusReason categoryShown when published
① Index volatility bandsWithheldData terms of use under confirmationSymmetric 80%/95% bands (%) per market, freeze time, prediction hash and anchor, scoring (inside/outside, PIT, Winkler) and cumulative coverage
② Real-time volatility raceWithheldData terms of use under confirmationModel × horizon coverage table (vs nominal 80), out-of-band cell counts, trailing leaders, cumulative observations, roll-call time
③ RegimesWithheldData terms of use under confirmationRealised regime codes (A–F): base rates, transition matrix, run lengths, ablated regime-ML score (not a forecast)
④ Verification boardPublished—Pre-registered / scored / rejected counts (rows and unique), model registry, ML conclusion board, recent rejections by category
④-a Accuracy axisWithheldData terms of use under confirmationAccuracy items inside the verification board (value, n, verdict class)

Internal freezing and scoring continue; the record is published as is once the terms of use are confirmed.

The intermediate session — from freeze to score

The procedure below applies to the index volatility bands (①); once the bands are published, the actual freeze and scoring records appear on this page.

1

Freeze

After each close, the 80% and 95% intervals for the next session's index change are computed and frozen. The freeze time and the prediction hash (prediction_sha256) stay in the file.

2

Anchor

The manifest hash-chain row that first carries the sha256 of the frozen bytes becomes the anchor; the web-repository commit time is the second anchor. An anchor after the target session opened is flagged.

3

Score

Once the target session closes, the realised change is scored: inside/outside the band, the percentile on the predicted distribution (PIT) and the Winkler score (width plus breach penalty). Prediction fields never change; only outcome is added.

4

What is absent

No direction — bands are symmetric intervals only. No levels — no prices or index points. No symbols. No returns or hit rates. Not a recommendation.

The prediction hash is the sha256 of a key-sorted JSON (separators , and :, UTF-8) of six keys: market, session_date, target, estimator, prediction, spec_sha256. anchor, outcome, frozen_at and notice are not hashed. Hover a number to see its facts source and as_of. Every number sits next to its freeze time and hash.

④ Verification board

Pre-registered, scored, rejected, confirmed — counts and labels only

Counts from the experiment ledger (rows, duplicates included, timestamped rows only), model-registry status, the ML conclusion board, the accuracy axis and recent rejected labels are copied as they are. One classifier from the delusion-check layer does the classification; return-related items are never published even when the source has them. Verify a record →

Generated 2026-09-29 · 2026-09-29 18:30:47 +09:00
Delayed — last update 2026-09-29

Delusion check as_of 2026-09-29 16:43:06 +09:00 · ML board as_of 2026-09-21 16:46:38 +09:00

Experiment ledger — day 2026-09-29
rows
1
unique
1
registered
0
scored
1
rejected
0
passed some legs
0
Experiment ledger — cumulative · 31 days
rows
1,516
registered
695
scored
492
rejected
270
passed some legs
59
registered (unique)
436
rejected (unique)
75

Rejected unique total 75 · rejected labels withheld total 1

Model registry
models
110
promoted
11
observing
17
descriptive
69
rejected
13
ML conclusion board
targets
9
confirmed
1
insufficient
8
budget exhausted
4
Accuracy axis

Withheld Data terms of use under review — see the publication status panel

Recent rejections (counts by category — hypothesis IDs are not published) · latest 10
Categoryn
value3
venture3
rotation / ETF2
trading rules1
volatility1
as_of 2026-09-29 18:30:47 +09:00facts 31sha f95804c3
Sources and terms of use
  • Source: Korea Exchange statistical information (attribution under Article 10(3) of the Korea Exchange terms of use)
  • Only model-performance statistics are shown; no quotation values are published.
  • Index names such as KOSPI, KOSDAQ, S&P 500 and NASDAQ are trademarks of their respective owners; there is no affiliation with or endorsement of this site.
  • Data sources in summary: public data (filings and statistics), exchange statistical information, and the program's own prediction and scoring record. No price or index levels and no security identifiers are published.
Notice

방향 없음·권유 아님 — 모델 예측과 채점 기록만 싣는다No direction, no recommendation — only model predictions and their scoring record.

Descriptions of the research system on this site introduce an internal research program of Root Inside Co., Ltd. and are provided for research and educational purposes only. They are not a solicitation to buy or sell any financial instrument and do not substitute for your own judgment. All investment decisions, and their outcomes, are the sole responsibility of the user.