The Black is not dice: developer statements, evidence report, and a plan that looks for the rule
- planner/knowledge.yaml: what the game's developer has said (paraphrased, dated, graded), what the Atlas does with each statement, and the open questions with the experiment that tests each. - analysis/black/evidence.py -> analysis/reports/BLACK.md: counts from the runs. On the same recorded route the shadow shows on 21 of 79 first attempts and 1 of 80 later ones; no single route; Blue then Black after the shadow. - game.yaml: the shadow is a guard (not a roll); what follows it is the Blue, then the Black; on-screen text for the squad's direction screen. - planner/experiments.yaml v2: one exact path on every fresh account (fresh-replicate), then one choice changed at a time (fresh-ablate); shadow-again, second-attempt-same-path, veteran-repeat, veteran-variety; what the bot records about the account; the sequence to follow once the shadow shows. - solver.js: assign() takes account facts, account offsets and cycled arms; recommendOption() answers the squad screen (stay + direction) in one pick. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014jqCC2LZ4x1WHQ1V57nTsv
This commit is contained in:
co-authored by
Claude Fable 5.2
parent
51842e1aa9
commit
d01ec46fcc
@@ -19,6 +19,7 @@ import hashlib
|
||||
import itertools
|
||||
import json
|
||||
import random
|
||||
import re
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
@@ -47,10 +48,31 @@ def check_options(where, fixed):
|
||||
raise ValueError(f"{where}: '{k}' has no option '{o}' (game.yaml: {model.DECISIONS[k]})")
|
||||
|
||||
|
||||
def arms(exp):
|
||||
"""Every combination of the factors, each with the route held on every arm."""
|
||||
def arms(exp, routes=None):
|
||||
"""The arms of an experiment, each with the decisions it holds (`fix`): every combination of the factors, or
|
||||
the explicit `arms` (one `change` to the route each), or a single arm. A `cycle` arm also carries the decisions
|
||||
it varies from attempt to attempt."""
|
||||
route = exp.get("route") or {}
|
||||
if isinstance(route, str):
|
||||
if route not in (routes or {}):
|
||||
raise ValueError(f"{exp['id']}: unknown route '{route}'")
|
||||
route = routes[route]
|
||||
check_options(exp["id"] + " route", route)
|
||||
if exp.get("arms"):
|
||||
out = []
|
||||
for a in exp["arms"]:
|
||||
check_options(f"{exp['id']} arm {a['id']}", a.get("change"))
|
||||
out.append({"id": a["id"], "change": a.get("change") or {}, "fix": {**route, **(a.get("change") or {})}})
|
||||
if len({a["id"] for a in out}) != len(out):
|
||||
raise ValueError(f"{exp['id']}: arm ids must be unique")
|
||||
return out
|
||||
if exp.get("cycle"):
|
||||
for k, opts in exp["cycle"].items():
|
||||
if k in route:
|
||||
raise ValueError(f"{exp['id']}: '{k}' is both cycled and part of the route")
|
||||
for o in opts:
|
||||
check_options(exp["id"] + " cycle", {k: o})
|
||||
return [{"id": "all", "fix": dict(route), "cycle": exp["cycle"]}]
|
||||
factors = exp.get("factors") or {}
|
||||
for k, opts in factors.items():
|
||||
if k in route:
|
||||
@@ -71,6 +93,11 @@ def validate(d):
|
||||
if len(set(ids)) != len(ids):
|
||||
raise ValueError("experiment ids must be unique")
|
||||
for e in d["experiments"]:
|
||||
if e.get("starts_after") and e["starts_after"] not in ids:
|
||||
raise ValueError(f"{e['id']}: starts_after names no experiment")
|
||||
for k in (e.get("when") or {}):
|
||||
if k not in (d.get("record") or []):
|
||||
raise ValueError(f"{e['id']}: when.{k} is not something the bot records (`record`)")
|
||||
if e["target"] not in model.COLOURS:
|
||||
raise ValueError(f"{e['id']}: unknown target {e['target']}")
|
||||
if e.get("sampling", "best") not in SAMPLING:
|
||||
@@ -117,14 +144,16 @@ def build(d=None, log=None):
|
||||
d = d or design()
|
||||
validate(d)
|
||||
log = logged() if log is None else log
|
||||
exps = []
|
||||
exps, status_of = [], {}
|
||||
for e in d["experiments"]:
|
||||
m = e.get("measures")
|
||||
a = arms(e)
|
||||
a = arms(e, d.get("routes"))
|
||||
tally = {x["id"]: {"runs": 0, "observed": 0, "rare": 0} for x in a}
|
||||
for exp_id, arm, v in log:
|
||||
if exp_id != e["id"]:
|
||||
continue
|
||||
if a[0].get("cycle"): # a cycled arm is logged under the combination it played: all one arm here
|
||||
arm = a[0]["id"]
|
||||
t = tally.setdefault(arm or "?", {"runs": 0, "observed": 0, "rare": 0})
|
||||
t["runs"] += 1
|
||||
y = model.OBSERVE[m["roll"]](v) if m and v else None
|
||||
@@ -138,7 +167,9 @@ def build(d=None, log=None):
|
||||
total_rare = sum(t["rare"] for t in tally.values())
|
||||
status, note = "running", None
|
||||
se = e.get("stop_early")
|
||||
if not e.get("ongoing") and all(n >= planned for n in done.values()):
|
||||
if e.get("starts_after") and status_of.get(e["starts_after"]) != "complete":
|
||||
status, note = "waiting", f"starts when {e['starts_after']} is complete"
|
||||
elif not e.get("ongoing") and all(n >= planned for n in done.values()):
|
||||
status, note = "complete", f"every arm has its planned {planned}"
|
||||
elif se and total_obs >= se["after"] and total_rare <= se["rare_at_most"]:
|
||||
status = "paused"
|
||||
@@ -146,18 +177,25 @@ def build(d=None, log=None):
|
||||
for x in a:
|
||||
t = tally[x["id"]]
|
||||
x["progress"] = {**t, "planned": planned, **({"estimate": interval(t["rare"], t["observed"])} if m and t["observed"] else {})}
|
||||
status_of[e["id"]] = status
|
||||
exps.append({
|
||||
"id": e["id"], "status": status, **({"note": note} if note else {}),
|
||||
"question": e["question"], "attempts": {"from": e["attempts"]["from"], "to": e["attempts"].get("to")},
|
||||
"unit": e["unit"], "share": e["share"], **({"accounts": e["accounts"]} if e.get("accounts") else {}),
|
||||
**({"exclusive": True} if e.get("exclusive") else {}),
|
||||
**({"when": e["when"]} if e.get("when") else {}),
|
||||
"target": e["target"], "objective": e.get("objective", "eventually"), "sampling": e.get("sampling", "best"),
|
||||
"seed": d["seed"], "measures": m, "burn": e.get("burn"), "arms": a,
|
||||
"progress": {"runs": sum(t["runs"] for t in tally.values()), "observed": total_obs, "rare": total_rare,
|
||||
**({"estimate": interval(total_rare, total_obs)} if m and total_obs else {}),
|
||||
"unknownArms": sorted(k for k in tally if k not in {x["id"] for x in a})},
|
||||
})
|
||||
plan = {"schema": 1, "seed": d["seed"], "lifecycle": d["lifecycle"], "experiments": exps}
|
||||
for s in (d.get("scripts") or {}).values():
|
||||
for st in s:
|
||||
for k in ("take", "never"):
|
||||
re.compile(st.get(k) or "")
|
||||
plan = {"schema": 2, "seed": d["seed"], "lifecycle": d["lifecycle"], "record": d.get("record") or [],
|
||||
"scripts": d.get("scripts") or {}, "experiments": exps}
|
||||
plan["id"] = hashlib.sha1(json.dumps(plan, sort_keys=True, separators=(",", ":")).encode()).hexdigest()[:12]
|
||||
return plan
|
||||
|
||||
@@ -171,7 +209,7 @@ def summary(plan):
|
||||
for e in plan["experiments"]:
|
||||
p = e["progress"]
|
||||
est = p.get("estimate")
|
||||
L.append(f" {e['id']:<22} {e['status']:<9} {p['observed']} observed, {p['rare']} rare"
|
||||
L.append(f" {e['id']:<26} {e['status']:<9} {p['observed']} observed, {p['rare']} rare"
|
||||
+ (f" ({100 * est['rate']:.1f}%, 90% range {100 * est['lo']:.1f}-{100 * est['hi']:.1f})" if est else "")
|
||||
+ (f" [{e['note']}]" if e.get("note") else ""))
|
||||
return "\n".join(L)
|
||||
|
||||
Reference in New Issue
Block a user