P03 · Paper portfolio
Billionaire Consensus
by AI Portfolios
This is the simple view. Nothing has been removed — the decision records, the refused proposals, the AI's own words, the cost model, the published limits and the hash chain are all in Advanced, which is the switch in the header. How to verify any of it →
Showing every layer. Pick Simple or Advanced in the header to choose one — nothing is removed either way, and the full record is always in this page.
Billionaire Consensus
Outside every declared rebalance window (next_window_opens=2026-11-14). This portfolio trades only in its filing windows; between them it is frozen by design. Exits for risk reasons remain permitted.
Hold the US-listed equities most widely and heavily owned across a fixed, publicly declared list of large institutional investment managers, as disclosed in their SEC Form 13F-HR filings.
| Slot | Last due | Answered | Status |
|---|---|---|---|
filing watch 0 9 12-20 2,5,8,11 * · America/New_York | — | n/a | does not decide This slot marks and reports; it never calls the model, so it leaves no decision record to check it against. |
rebalance run 0 17 15-21 2,5,8,11 * · America/New_York | 2026-08-21 21:00 | 2026-08-21 22:44 | ok due 2026-08-21T21:00:00+00:00, ran 2026-08-21T22:44:00.926749+00:00 |
monthly risk 0 12 1 * * · America/New_York | — | n/a | does not decide This slot marks and reports; it never calls the model, so it leaves no decision record to check it against. |
Catch-up policy. A decision instant that passes unanswered is run on the next pass, once, and the record stamps both instants — when it was due and when it actually ran. Past the catch-up window the gap stays open and is published as missed rather than backfilled.
Track record
Fewer than 60 daily observations. Annualised return, volatility, Sharpe, Sortino and Calmar are withheld: annualising a short sample produces numbers that look precise and are not.
Our own marks from our own fills (nothing here is vendor price data). Deliberately monochrome: colour that codes "good" and "bad" is an editorial thumb on the scale.
Index 100 is the starting capital ($100,000), so this line ends at the total return published above it. The comparison line is indexed to the same capital and starts at 100 at its own first close here: the record carries no priced instant at which capital was granted, so the comparison capital is uninvested until then rather than given a price nothing printed. Both cover the identical window.
Index values are derived percentage returns over IEX last-trade closes, which are licensed for publication; no raw vendor price is rendered.
| symbol | since entry | weight | opened |
|---|---|---|---|
| AMZN | -4.5% | +8.0% | 2026-08-14 |
| MOH | +2.2% | +7.2% | 2026-08-14 |
| V | +3.3% | +6.3% | 2026-08-14 |
| AAPL | +8.7% | +5.7% | 2026-08-14 |
| MA | +1.5% | +5.5% | 2026-08-14 |
| LULU | -15.3% | +5.3% | 2026-08-14 |
| MSFT | +3.1% | +5.3% | 2026-08-14 |
| MCO | -0.8% | +5.2% | 2026-08-14 |
| SPY | -2.0% | +5.1% | 2026-08-14 |
| TDG | -11.7% | +4.7% | 2026-08-14 |
| AXP | -3.8% | +4.6% | 2026-08-14 |
| SLM | -4.9% | +4.3% | 2026-08-14 |
| CME | +4.0% | +4.2% | 2026-08-14 |
| KO | +0.9% | +4.1% | 2026-08-17 |
| NVDA | -6.7% | +3.9% | 2026-08-14 |
| UBER | -5.9% | +3.9% | 2026-08-14 |
| FERG | -8.9% | +3.8% | 2026-08-14 |
| AVGO | -13.2% | +3.7% | 2026-08-14 |
| CRH | -8.2% | +3.7% | 2026-08-14 |
| STX | -18.8% | +3.6% | 2026-08-14 |
Return since the AI entered, measured from this book's own mark against what it actually paid — our own numbers over our own record, not vendor price data.
Weights are our own work product, computed at the newest audit-chain NAV mark — never re-derived later, never estimated from cost basis. Logos identify the holdings and imply no endorsement (operator decision, session 11); sector tints are structure, not judgement.
| Symbol | Quantity | Avg cost | Stop | Opened |
|---|---|---|---|---|
 AAPL5.7% | 16.3436 | 306.34 | — | 2026-08-14 committed 2026-08-17 |
 AMZN8.0% | 30.4588 | 265.55 | — | 2026-08-14 committed 2026-08-17 |
 AVGO3.7% | 10.4074 | 397.25 | — | 2026-08-14 committed 2026-08-17 |
 AXP4.6% | 13.4606 | 340.81 | — | 2026-08-14 committed 2026-08-17 |
 CME4.2% | 14.4552 | 269.61 | — | 2026-08-14 committed 2026-08-17 |
 CRH3.7% | 40.2470 | 96.91 | — | 2026-08-14 committed 2026-08-17 |
 FERG3.8% | 16.2489 | 243.92 | — | 2026-08-14 committed 2026-08-17 |
 KO4.1% | 44.1820 | 88.53 | — | 2026-08-17 committed 2026-08-18 |
 LULU5.3% | 51.3593 | 118.46 | — | 2026-08-14 committed 2026-08-17 |
 MA5.5% | 9.1869 | 565.85 | — | 2026-08-14 committed 2026-08-17 |
 MCO5.2% | 10.4338 | 481.70 | — | 2026-08-14 committed 2026-08-17 |
 MOH7.2% | 32.1988 | 209.59 | — | 2026-08-14 committed 2026-08-17 |
 MSFT5.3% | 10.1736 | 490.42 | — | 2026-08-14 committed 2026-08-17 |
 NVDA3.9% | 17.9872 | 226.07 | — | 2026-08-14 committed 2026-08-17 |
 SLM4.3% | 155.9044 | 27.75 | — | 2026-08-14 committed 2026-08-17 |
 SPY5.1% | 6.4534 | 776.22 | — | 2026-08-14 committed 2026-08-17 |
 STX3.6% | 4.2735 | 991.64 | — | 2026-08-14 committed 2026-08-17 |
 TDG4.7% | 4.0417 | 1258.39 | — | 2026-08-14 committed 2026-08-17 |
 UBER3.9% | 51.7446 | 77.17 | — | 2026-08-14 committed 2026-08-17 |
 V6.3% | 16.2845 | 363.23 | — | 2026-08-14 committed 2026-08-17 |
Why two dates? "Opened" is the market session the opening fill was priced on. The licensed data feed's T+1 rule means a cycle prices on the newest session already licensed for use, so the run that produced the fill can be committed to the audit chain on a later date — that commitment date is shown beneath. The commitment time is what makes history tamper-evident; the pricing session is what returns are computed from. Both are published on every fill.
Recent decisions
Every run, including the ones that traded nothing: the committed fact-pack hash (written to the audit chain before anything was proposed), the AI's published view, each proposal with the rule engine's verdict, and the fills that resulted. Rejected proposals stay up with their reason codes — a reader who can only see the trades that happened cannot judge the discipline that refused the ones that didn't.
Every card carries the instant it was decided at, because every card is a photograph. The facts in it were frozen when the run was committed and are never revised — a view that said "the platform has closed zero trades" was true at its timestamp and reads as a claim about today unless the card says otherwise. Consecutive runs that halted on identical codes are compressed into one card with a visible count and every run id listed; nothing is dropped.
AI-generated. All quantitative claims traced to the published fact pack. P03 is a near-zero-discretion "Billionaire Consensus" book whose 20 holdings are picked mechanically from SEC 13F overlap, ranked by a consensus score blending manager breadth, mean weight and QoQ momentum (p03:selection:summary: 20 of 103 scored candidates selected, 3-manager breadth floor, 38 consensus names outside eligible universe). My role is explain-and-flag only; I propose no trades. Current book is fully invested at the 20-slot cap (pf.position_count=20, pf.position_slots_free=0, pf.max_positions=20) with 1.94% cash (pf.cash_pct) and total return -2.36% (pf.total_return_pct), drawdown 2.48% from peak (pf.drawdown_pct). What the holdings represent: the largest positions by consensus score are AMZN (0.7625; 9/15 managers, mean weight 12.35% — p03:consensus:AMZN), MOH (0.5332; 4/15, mean weight 9.48% — p03:c…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| FLAG_DATA_ANOMALY STX | 3 | PROPOSED→GATES PASSED→NO ORDER FLAG_DATA_ANOMALY is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
AI-generated. All quantitative claims traced to the published fact pack. P03 is a near-zero-discretion 13F-consensus book; my role is explain-and-flag only, so I propose no trades. The 20 held names each carry a consensus_score derived from a fixed formula (0.50*manager-breadth + 0.35*mean-weight + 0.15*QoQ). The highest-conviction consensus holdings are AMZN (score 0.7625; 9/15 managers, mean weight 12.35% per p03:consensus:AMZN), MOH (0.5332; 4/15, mean weight 9.48% per p03:consensus:MOH), LULU (0.4786 per p03:consensus:LULU) and V (0.4620; 8/15 managers per p03:consensus:V). The book is fully invested: pf.position_count=20 of pf.max_positions=20, pf.position_slots_free=0, cash only 1.923% (pf.cash_pct), total return -1.3557% (pf.total_return_pct), drawdown 1.4677% (pf.drawdown_pct). Weights are broadly 3.6-8.2% (pos.AMZN.weight_pct=8.2084 highest, pos.STX.weight_pct=3.6068 lowest), c…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| FLAG_DATA_ANOMALY STX | 3 | PROPOSED→GATES PASSED→NO ORDER FLAG_DATA_ANOMALY is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
AI-generated. All quantitative claims traced to the published fact pack. This is a near-zero-discretion Billionaire Consensus (P03) book: holdings are set mechanically by 13F-overlap consensus scores, and my role is explain-and-flag only — I may not propose trades. The book holds 20/20 positions with pf.position_slots_free=0 (pf.position_count) and 3.93% cash (pf.cash_pct). Total return is -1.401% (pf.total_return_pct) with a modest 1.51% drawdown (pf.drawdown_pct). The 20 holdings map cleanly onto the published consensus scores: the highest-scoring names are held (AMZN 0.7625 with 9/15 managers, mean weight 12.35% per p03:consensus:AMZN; MOH 0.5332 per p03:consensus:MOH; LULU 0.4786 per p03:consensus:LULU; V 0.4620 with 8/15 managers per p03:consensus:V), consistent with the rulebook's overlap-weighted mechanic. Most positions were entered together (pos.*.days_held = 3, e.g. pos.AAPL.d…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| FLAG_DATA_ANOMALY STX | 3 | PROPOSED→GATES PASSED→NO ORDER FLAG_DATA_ANOMALY is a decision not to trade — no order is created | — |
| ADD KO @ 3.98% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
fills: BUY 22.2954 KO @ 88.63
AI-generated. All quantitative claims traced to the published fact pack. This is a near-zero-discretion, rules-first "Billionaire Consensus" book (P03) whose 20 holdings are picked mechanically from 13F-HR overlap. My role is explain-and-flag only; I may not propose trades. The book holds 20 of 20 slots (pf.position_slots_free=0, pf.max_positions=20), is ~1.93% cash (pf.cash_pct=1.9259), and total return is -1.1525% (pf.total_return_pct) with a 1.26% drawdown (pf.drawdown_pct). All positions were opened 2 days ago (e.g. pos.AAPL.days_held=2) and no round trips have closed yet. What the holdings represent: they are the highest consensus-scored names among the declared managers. AMZN carries the strongest consensus (p03:consensus:AMZN score 0.7625, 9/15 managers, mean weight 12.35%) and is the largest weight at 8.05% (pos.AMZN.weight_pct). MOH (0.5332, 4/15, mean 9.48%; pos.MOH.weight_pc…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| FLAG_DATA_ANOMALY MOH | 3 | PROPOSED→GATES PASSED→NO ORDER FLAG_DATA_ANOMALY is a decision not to trade — no order is created | — |
| BUY KO @ 3.98% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | CLAMP_CASH |
| SELL DHR mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
fills: SELL 19.1652 DHR @ 203.75 · BUY 21.8865 KO @ 88.44
AI-generated. All quantitative claims traced to the published fact pack. P03 is a near-zero-discretion, rules-first "Billionaire Consensus" mandate that mechanically holds the equities most widely and heavily owned across a fixed list of 13F filers. My role is strictly explain and flag — I may not propose trades. The portfolio is currently 100% cash (pf.cash_pct=100, pf.position_count=0, pf.nav=100,000), so no holdings exist yet to explain; the mechanical selection engine has not populated positions. The selection summary (p03:selection:summary) states 20 of 96 scored candidates were selected, 3497 names fell below the 3-manager breadth floor, and 45 consensus names sit outside the eligible universe. Only three consensus-score facts are exposed in this pack: MOH (p03:consensus:MOH, score 0.5332, 4/15 managers, mean weight 9.48%), NVDA (p03:consensus:NVDA, score 0.3153, 5/15 managers, me…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| FLAG_DATA_ANOMALY MOH | 3 | PROPOSED→GATES PASSED→NO ORDER FLAG_DATA_ANOMALY is a decision not to trade — no order is created | — |
| BUY AMZN @ 8% target mechanical | 4 | PROPOSED→GATES PASSED→QUEUED→FILLED | CLAMP_POSITION_CAP |
| BUY MOH @ 6.84% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY LULU @ 6.14% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY V @ 5.93% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY MA @ 5.23% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY TDG @ 5.08% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY MCO @ 5.06% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY MSFT @ 5.04% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY SPY @ 5.01% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY AAPL @ 5% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY AXP @ 4.61% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY SLM @ 4.37% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY STX @ 4.16% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY AVGO @ 4.09% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY NVDA @ 4.05% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY FERG @ 3.98% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY UBER @ 3.93% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY CRH @ 3.91% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY CME @ 3.9% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY DHR @ 3.88% target mechanical | 2 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
fills: BUY 30.4588 AMZN @ 265.55 · BUY 32.1988 MOH @ 209.59 · BUY 51.3593 LULU @ 118.46 · BUY 16.2845 V @ 363.23 · BUY 9.1869 MA @ 565.85 · BUY 4.0417 TDG @ 1258.39 · BUY 10.4338 MCO @ 481.70 · BUY 10.1736 MSFT @ 490.42 · BUY 6.4534 SPY @ 776.22 · BUY 16.3436 AAPL @ 306.34 · BUY 13.4606 AXP @ 340.81 · BUY 155.9044 SLM @ 27.75 · BUY 4.2735 STX @ 991.64 · BUY 10.4074 AVGO @ 397.25 · BUY 17.9872 NVDA @ 226.07 · BUY 16.2489 FERG @ 243.92 · BUY 51.7446 UBER @ 77.17 · BUY 40.2470 CRH @ 96.91 · BUY 14.4552 CME @ 269.61 · BUY 19.1652 DHR @ 200.23
AI-generated. All quantitative claims traced to the published fact pack. P03 is a rules-first "Billionaire Consensus" mandate: holdings are chosen mechanically from 13F overlap across a fixed manager list, and the AI's role is explicitly explain-and-flag-only (no trade proposals permitted). The portfolio is currently 100% cash — NAV 100,000 USD, 0 positions, 0 pct return, 0 drawdown (pf.nav, pf.cash_pct, pf.position_count, pf.total_return_pct, pf.drawdown_pct). The system is in risk state PAUSE_OUTSIDE_REBALANCE_WINDOW with the next window opening 2026-08-14, so the book is frozen by design until then; only risk exits are permitted, and there are no positions to exit. Consensus scores are present for only a handful of names (p03:consensus:MOH highest at 0.5332 with 4/15 managers and mean weight 9.48%; p03:consensus:LULU 0.4786; p03:consensus:MA 0.4075; p03:consensus:AXP 0.3588; p03:con…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN MOH | 2 | PROPOSED→GATES PASSED→NO ORDER EXPLAIN is a decision not to trade — no order is created | — |
Reading the lifecycle. PROPOSED and GATES PASSED are published facts. QUEUED is shown as reached only where a fill proves it — the payload publishes no order record. FILLED / EXPIRED stays undecided without a matching fill, because an accepted order can price on a later session under the T+1 rule, and calling that "expired" would be inventing the outcome. "Accepted" alone used to sit in this column and read as though the trade had happened.
What the AI is allowed to do
This portfolio's AI explains and flags. It makes no trade proposals at all — the maximum is zero, enforced by the mandate validator. Position selection is fully mechanical.
EXPLAIN · FLAG_DATA_ANOMALY
At most 1 proposal per run, each carrying a direction, a conviction from 1 to 5, a rationale, and references to the facts it used.
- set a price
- set a quantity or share count
- set a weight or position size
- set or move a risk limit
- execute anything
Model tier deep · prompt version P03-v1. Any change to the decider or the prompt is recorded as a MODEL_CHANGE event in the audit chain — without it the record would be a chimera of two systems presented as one.
Enforced limits
Every limit below names the code path that enforces it. This is not decoration: a limit that is published but never fires is worse than no limit, because a reader has no way to tell the difference. A test walks every mandate, drives the engine into the state each declared control claims to protect against, and fails the build if nothing stops it.
| Limit | Value | Enforced by |
|---|---|---|
| Maximum gross exposure | 100.0% | gate 2 — size_order |
| Maximum single sector | 35.0% | gate 2 — size_order |
| Limit | Value | Enforced by |
|---|---|---|
| Shorting | prohibited | gate 1 — proposal validation |
| Derivatives | prohibited | gate 1 — proposal validation |
| Margin | prohibited | gate 1 — proposal validation |
| Limit | Value | Enforced by |
|---|---|---|
| Maximum positions | 20 | gate 3 — BREACH_MAX_POSITIONS (portfolio limit check) |
| Minimum new position | 1.5% | gate 2 — size_order |
| Maximum order as % of ADV | 1.0% | gate 2 — size_order |
| Limit | Value | Enforced by |
|---|---|---|
| Stale-data halt | 48 hours | gate 3 — HALT_STALE_DATA |
| Limit | Value | Enforced by |
|---|---|---|
| At −20.0% drawdown | alert, publish_commentary | gate 3 — drawdown ladder |
| At −35.0% drawdown | alert, mandatory_deep_review | gate 3 — drawdown ladder |
| At −55.0% drawdown | graveyard_review | gate 3 — drawdown ladder |
| Limit | Value | Enforced by |
|---|---|---|
| Max trades per quarter | 30 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Min holding period days | 0 | entry block — PAUSE_TURNOVER_CAP_REACHED (never blocks an exit) |
| Limit | Value | Enforced by |
|---|---|---|
| Halt trading if price gap unexplained pct | 25 | gate 3 — circuit breaker |
| Halt trading if 13f parse error rate above pct | 5 | gate 3 — circuit breaker |
| Halt trading if unmapped figi rate above pct | 10 | gate 3 — circuit breaker |
| Halt trading if factpack hash mismatch | true | gate 3 — circuit breaker |
Disclosures specific to this portfolio
These render on the page itself rather than in a footer, because without them the numbers actively mislead.
- 13F filings are due 45 days after quarter end. Position data is between 45 and 136 days old, mean approximately 90 days.
- 13F discloses LONG US-listed positions only. Shorts, cash, foreign listings and most derivatives are invisible.
- Managers may omit positions under 10,000 shares AND under $200,000, and may request confidential treatment for others.
- This portfolio is not affiliated with, endorsed by, or connected to any manager named. Managers are identified by SEC CIK.
- Security identifiers are published as ticker and FIGI. CUSIP identifiers are never published.
Execution
Fills are struck on a VWAP window that begins strictly after the decision timestamp plus a latency delay. No fill can use information from the bar in which the decision was made, so look-ahead is arithmetically impossible rather than merely avoided.
Philosophy
A near-zero-discretion, rules-first portfolio. If many independent, well resourced managers independently arrive at the same position, that overlap is a signal worth mechanically expressing. The AI's role here is deliberately the smallest of any portfolio: it explains and it flags data anomalies. It does not pick.
Review schedule
| Job | Cron | Timezone | Makes a decision |
|---|---|---|---|
| filing watch | 0 9 12-20 2,5,8,11 * | America/New_York | no |
| rebalance run | 0 17 15-21 2,5,8,11 * | America/New_York | yes |
| monthly risk | 0 12 1 * * | America/New_York | no |
Published on a fixed, regular schedule. Never event-triggered — no "market is crashing, sell now" alerts, deliberately. This table is the promise; the cadence panel at the top of the page is whether it was kept, instant by instant.
Machine-readable mandate: config/portfolios/P03_billionaire_consensus.yaml · human rulebook: docs/portfolios/P03_billionaire_consensus.md · effective from 2026-08-06 (wall clock) · record starts 2026-08-13 (pricing session) · payload 540d30e63326…