-
7abbd24d34
docs: sentence-case the redacted node name
main

kartiandClaude Opus 5
2026-09-15 12:16:04 -07:00
-
ef01bde068
docs: redact the reference node's address and hostname

kartiandClaude Opus 5
2026-09-15 12:15:37 -07:00
-
3025c4cf85
Document the current public Arena boundary
karti
2026-08-25 14:59:00 -07:00
-
4836d3e644
Move maintained Tera evaluations to private source
karti
2026-08-25 13:08:23 -07:00
-
61939676a5
Pin Arena environments to stable Verifiers
karti
2026-08-25 10:33:35 -07:00
-
3305be4ff7
gates: give two of them a margin, and make the probe see components

kartiandClaude Opus 5
2026-08-21 23:14:05 -07:00
-
122a858b61
pin verifiers 0.3.1.dev59, and make every config say subprocess

kartiandClaude Opus 5
2026-08-21 23:14:05 -07:00
-
8048a61a1b
docs: run-20260821-1401 was sampled with thinking off, and four gates are dead

kartiandClaude Opus 5
2026-08-21 17:44:46 -07:00
-
4147de0282
tera-crow-nav: the first spatial taskset, and the hold sweep that sized its budget

kartiandClaude Opus 5
2026-08-21 17:44:46 -07:00
-
94ab513eda
probe: gate grand-exchange-live, the first interactive environment

kartiandClaude Opus 5
2026-08-21 17:44:20 -07:00
-
f953c03bd1
grand-exchange-live: protocol layer, taskset, config, widened reference gate

kartiandClaude Opus 5
2026-08-21 17:44:20 -07:00
-
e4cc2bf1c3
docs: the scope, the plan, the post-review execution plan, and the eval runbook

kartiandClaude Opus 5
2026-08-21 15:55:43 -07:00
-
162d67a83c
tera-spatial: an NDJSON replay bridge to the TypeScript spatial environments

kartiandClaude Opus 5
2026-08-21 15:55:12 -07:00
-
00d21025ff
grand-exchange-live: the stepped market engine, and the turn budget binds

kartiandClaude Opus 5
2026-08-21 15:55:12 -07:00
-
8fe348ca82
probe: discover environments from manifests, not a hardcoded list

kartiandClaude Opus 5
2026-08-21 15:54:56 -07:00
-
16f4ee21ae
Extend the merged CI and probe test to all seven environments

kartiandClaude Opus 5
2026-08-19 03:58:25 -07:00
-
7428e91415
Merge the redaction-pressure hardening with the three OSRS environments
karti
2026-08-19 03:57:10 -07:00
-
-
0defaed9c0
Three OSRS environments, and the first real model scores

kartiandClaude Opus 5
2026-08-19 03:56:50 -07:00
-
d691acf131
Harden redaction-pressure reward and provenance
karti
2026-08-19 00:52:56 -07:00
-
-
5a99eb86a5
Three more environments, and probe.py to gate all four

kartiandClaude Opus 5
2026-08-19 01:02:48 -07:00
-
9f8768acca
Harden redaction-pressure reward and provenance
archive/redaction-pressure-v2
karti
2026-08-19 00:52:56 -07:00
-
-
c28d864766
Arena: the environment repository, and redaction-pressure

kartiandClaude Opus 5
2026-08-19 00:09:31 -07:00