f62098bReset cache: discard draws made before auto-thinningJeremy Magland 1# Cached entropy estimates
3285002estimates: run 8 from efed18agithub-actions[bot] 3Machine-generated by [`.github/workflows/estimates.yml`][wf] on `main` — do not
4edit by hand. Every dispatch runs the whole grid again with fresh, independent
5pasts, appends one record per cell to `runs.jsonl`, and rebuilds
6`estimates.json` from the full log, so the means tighten run after run.
8- **`runs.jsonl`** — append-only, one JSON object per (cell, dispatch): the
9 cell's parameters, the per-past values with their sum and sum of squares,
10 the per-past resolved Gibbs thinning and probe autocorrelation times
11 (`thin='auto'` matches thinning to each chain's measured mixing), the
12 seed, and the code commit that produced them.
13- **`estimates.json`** — pooled `mean` and `se` per cell over every past ever
14 drawn for it, alongside the analytic `predicted` rate for comparison.
16The estimand is H(z_(M+1) | z_1..z_M) in bits/sample — an upper bound on the
17entropy rate of z that tightens as the conditioning window M grows.
19Fetch it from a browser or a script (raw.githubusercontent.com sends
20`access-control-allow-origin: *`):
22 https://raw.githubusercontent.com/concept-collection/timeseries-entropy/estimates/estimates.json
d76838aestimates: run 144 from efed18agithub-actions[bot] 24## Current state (131 runs, generated 2026-08-15T07:26:11Z)
26| cell | sigma | M | mean | se | pasts | predicted |
27| --- | --- | --- | --- | --- | --- | --- |
d76838aestimates: run 144 from efed18agithub-actions[bot] 28| bp300-6000_s1 | 1 | 512 | 0.9327 | 0.0039 | 1048 | 0.9513 |
29| bp300-6000_s16 | 16 | 512 | 2.5518 | 0.0085 | 1048 | 2.5680 |
30| bp300-6000_s2 | 2 | 512 | 1.3109 | 0.0035 | 1048 | 1.3319 |
31| bp300-6000_s32 | 32 | 512 | 2.9836 | 0.0190 | 1048 | 2.9938 |
32| bp300-6000_s4 | 4 | 512 | 1.7240 | 0.0043 | 1048 | 1.7342 |
33| bp300-6000_s8 | 8 | 512 | 2.1298 | 0.0060 | 1048 | 2.1476 |
34| lp3000_s1 | 1 | 512 | 0.4789 | 0.0073 | 1048 | 0.6166 |
35| lp3000_s16 | 16 | 512 | 1.4415 | 0.0060 | 1048 | 1.4888 |
36| lp3000_s2 | 2 | 512 | 0.7624 | 0.0082 | 1048 | 0.8251 |
37| lp3000_s32 | 32 | 512 | 1.6679 | 0.0066 | 1048 | 1.7179 |
38| lp3000_s4 | 4 | 512 | 0.9931 | 0.0058 | 1048 | 1.0415 |
39| lp3000_s8 | 8 | 512 | 1.2091 | 0.0067 | 1048 | 1.2632 |
40| ma8_s1 | 1 | 512 | 0.4817 | 0.0065 | 1048 | 0.6100 |
41| ma8_s16 | 16 | 512 | 3.1758 | 0.0077 | 1048 | 3.1777 |
42| ma8_s2 | 2 | 512 | 0.9757 | 0.0029 | 1048 | 0.9825 |
43| ma8_s32 | 32 | 512 | 4.0885 | 0.0076 | 1048 | 4.1125 |
44| ma8_s4 | 4 | 512 | 1.5562 | 0.0033 | 1048 | 1.5529 |
45| ma8_s8 | 8 | 512 | 2.3092 | 0.0051 | 1048 | 2.3064 |
46| none_s1 | 1 | 512 | 2.1054 | 0.0020 | 1048 | 2.1048 |
47| none_s16 | 16 | 512 | 6.0136 | 0.0152 | 1048 | 6.0473 |
48| none_s2 | 2 | 512 | 3.0670 | 0.0037 | 1048 | 3.0620 |
49| none_s32 | 32 | 512 | 7.0484 | 0.0327 | 1048 | 7.0472 |
50| none_s4 | 4 | 512 | 4.0386 | 0.0042 | 1048 | 4.0508 |
51| none_s8 | 8 | 512 | 5.0508 | 0.0090 | 1048 | 5.0480 |
53[wf]: https://github.com/concept-collection/timeseries-entropy/blob/main/.github/workflows/estimates.yml