Brummel/aura-quadriga
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

research: Arc 4 — breadth and beta controls; momentum candidate on FRA40

Browse Source 
Runs the two surviving threads (H1 breakout, vol-normalized H1 momentum)
across the 21-instrument gapless universe under the wide-stop regimes,
beside an always-long beta control on the same matrix. The breakout dies
everywhere (beta on trending assets, significantly negative on FX);
momentum shows a one-sided positive cross-sectional tail with five
double-regime flags, of which FRA40 (both regimes) and NatGas (k6) beat
the no-signal baseline outright — the only control-beating cells of the
whole program. Includes the engine performance envelope (single run 2.97 s
vs Arc-0 ~3 s; 11-13 s/cell; executor fan-out findings refs
Brummel/Aura#268, data-gap abort refs Brummel/Aura#264).
This commit is contained in:
Claude
2026-07-13 18:36:57 +02:00
parent de92b4283d
commit ee1c15885b
4 changed files with 371 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
research/campaign-arc4-breadth-bo-h1.json
+95
View File
@@ -0,0 +1,95 @@
{
"format_version": 1,
"kind": "campaign",
"name": "arc4-breadth-bo-h1",
"description": "Arc 4 breadth test of the H1 breakout: the arc2c survivor question asked across the whole archive universe with gapless 2018-2026 m1 coverage (21 instruments: indices, FX majors and crosses, metals, energy, crypto; Copper dropped \u2014 its archive is missing 2018-01..2018-10). Wide-stop regimes only (vol{60,k6}, vol{60,k12}) where the XAUUSD cell survived deflation and costs; vol slippage cost. If the XAUUSD result is signal rather than gold-specific luck, related instruments (XAGUSD, other trending assets) should lean the same way; if it is isolated, the generalize floor and sign-agreement will say so.",
"seed": 0,
"data": {
"instruments": [
"GER40",
"US500",
"EURUSD",
"XAUUSD",
"US30",
"NAS100",
"UK100",
"JPN225",
"HK50",
"FRA40",
"GBPUSD",
"USDJPY",
"AUDUSD",
"USDCAD",
"USDCHF",
"NZDUSD",
"EURAUD",
"XAGUSD",
"NatGas",
"BTCUSD",
"ETHUSD"
],
"windows": [
{
"from_ms": 1514764800000,
"to_ms": 1782863999999
}
]
},
"risk": [
{
"vol": {
"length": 60,
"k": 6.0
}
},
{
"vol": {
"length": 60,
"k": 12.0
}
}
],
"cost": [
{
"vol_slippage": {
"slip_vol_mult": 0.1
}
}
],
"strategies": [
{
"ref": {
"content_id": "82515a31bfe58ae087b4bd09eb4adb032cc2cabddd71a2761c543066bd237d3d"
},
"axes": {
"channel_hi.length": {
"kind": "I64",
"values": [
24,
48,
96
]
},
"channel_lo.length": {
"kind": "I64",
"values": [
24,
48,
96
]
}
}
}
],
"process": {
"ref": {
"content_id": "41863fcae9300b334056c6f2a899e8c2672ecb29387d294e9a6e58f159ef51b4"
}
},
"presentation": {
"persist_taps": [],
"emit": [
"selection_report"
]
}
}
research/campaign-arc4-breadth-mom-vnorm.json
+95
View File
@@ -0,0 +1,95 @@
{
"format_version": 1,
"kind": "campaign",
"name": "arc4-breadth-mom-vnorm",
"description": "Arc 4 breadth test of vol-normalized H1 momentum: the only family with a regime-robust WF-OOS positive (US500, P(E[R]<=0) < 0.05 in all three arc3 regimes) asked across the 21-instrument universe. Wide-stop regimes (vol{60,k6}, vol{60,k12}), vol slippage cost. If risk-adjusted momentum is a genuine cross-asset effect, the index family should lean positive together; a lone US500 flag with 0-sign-agreement elsewhere reads as selection luck across the arc3 program.",
"seed": 0,
"data": {
"instruments": [
"GER40",
"US500",
"EURUSD",
"XAUUSD",
"US30",
"NAS100",
"UK100",
"JPN225",
"HK50",
"FRA40",
"GBPUSD",
"USDJPY",
"AUDUSD",
"USDCAD",
"USDCHF",
"NZDUSD",
"EURAUD",
"XAGUSD",
"NatGas",
"BTCUSD",
"ETHUSD"
],
"windows": [
{
"from_ms": 1514764800000,
"to_ms": 1782863999999
}
]
},
"risk": [
{
"vol": {
"length": 60,
"k": 6.0
}
},
{
"vol": {
"length": 60,
"k": 12.0
}
}
],
"cost": [
{
"vol_slippage": {
"slip_vol_mult": 0.1
}
}
],
"strategies": [
{
"ref": {
"content_id": "05045dfaa1e399c12505e21dc87c36a61b7bbfda75c0bebc2e95a9be5bfd9e42"
},
"axes": {
"mom_lag.lag": {
"kind": "I64",
"values": [
24,
72,
120
]
},
"vol_avg.length": {
"kind": "I64",
"values": [
24,
72,
120
]
}
}
}
],
"process": {
"ref": {
"content_id": "41863fcae9300b334056c6f2a899e8c2672ecb29387d294e9a6e58f159ef51b4"
}
},
"presentation": {
"persist_taps": [],
"emit": [
"selection_report"
]
}
}
research/campaign-control-always-long-breadth.json
+85
View File
@@ -0,0 +1,85 @@
{
"format_version": 1,
"kind": "campaign",
"name": "control-always-long-breadth",
"description": "Beta control for the arc4 breadth tests: the constant bias=+1 strategy on the full 21-instrument universe under the arc4 regimes (vol{60,k6}, vol{60,k12}) and slippage cost. Every arc4 candidate cell is read against this baseline: a candidate whose pooled-OOS statistics do not clearly beat always-long on the same instrument and regime is long-beta, not signal.",
"seed": 0,
"data": {
"instruments": [
"GER40",
"US500",
"EURUSD",
"XAUUSD",
"US30",
"NAS100",
"UK100",
"JPN225",
"HK50",
"FRA40",
"GBPUSD",
"USDJPY",
"AUDUSD",
"USDCAD",
"USDCHF",
"NZDUSD",
"EURAUD",
"XAGUSD",
"NatGas",
"BTCUSD",
"ETHUSD"
],
"windows": [
{
"from_ms": 1514764800000,
"to_ms": 1782863999999
}
]
},
"risk": [
{
"vol": {
"length": 60,
"k": 6.0
}
},
{
"vol": {
"length": 60,
"k": 12.0
}
}
],
"cost": [
{
"vol_slippage": {
"slip_vol_mult": 0.1
}
}
],
"strategies": [
{
"ref": {
"content_id": "198ca420039925af330f120376836d9c49a167b26e81324cb4857f5c20f81a44"
},
"axes": {
"always_long.value": {
"kind": "F64",
"values": [
1.0
]
}
}
}
],
"process": {
"ref": {
"content_id": "41863fcae9300b334056c6f2a899e8c2672ecb29387d294e9a6e58f159ef51b4"
}
},
"presentation": {
"persist_taps": [],
"emit": [
"selection_report"
]
}
}