P12 · Paper portfolio
Berkshire 13F Tracker
by AI Portfolios
This is the simple view. Nothing has been removed — the decision records, the refused proposals, the selector'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.
Berkshire 13F Tracker
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.
Mechanically copy the disclosed US-listed equity book of Berkshire Hathaway Inc (SEC CIK 0001067983) from its most recent Form 13F-HR filing: value-proportional weights across the top disclosed positions, rebalanced only when a new filing arrives, with every deviation from the disclosure (caps, universe exclusions, staleness) published rather than smoothed over.
| 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 |
|---|---|---|---|
| AAPL | +8.7% | +10.8% | 2026-08-14 |
| KO | +1.9% | +10.1% | 2026-08-14 |
| SGOV | -0.4% | +9.9% | 2026-08-14 |
| AXP | -3.8% | +9.5% | 2026-08-14 |
| BAC | -7.7% | +8.8% | 2026-08-14 |
| CVX | +5.7% | +7.1% | 2026-08-14 |
| OXY | +5.5% | +7.0% | 2026-08-14 |
| GOOGL | +0.5% | +6.0% | 2026-08-14 |
| CB | -1.3% | +4.2% | 2026-08-14 |
| MCO | -0.8% | +4.0% | 2026-08-14 |
| KHC | -3.9% | +2.7% | 2026-08-14 |
| DVA | +6.3% | +1.9% | 2026-08-14 |
| KR | +8.3% | +1.5% | 2026-08-14 |
| SIRI | +3.1% | +1.1% | 2026-08-14 |
| DAL | -10.4% | +0.9% | 2026-08-14 |
Return since this book's published arithmetic 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 |
|---|---|---|---|---|
 AAPL10.8% | 32.6872 | 306.34 | — | 2026-08-14 committed 2026-08-17 |
 AXP9.5% | 29.1988 | 340.81 | — | 2026-08-14 committed 2026-08-17 |
 BAC8.8% | 149.1704 | 64.43 | — | 2026-08-14 committed 2026-08-17 |
 CB4.2% | 12.4840 | 346.34 | — | 2026-08-14 committed 2026-08-17 |
 CVX7.1% | 33.5500 | 200.81 | — | 2026-08-14 committed 2026-08-17 |
 DAL0.9% | 11.4158 | 89.10 | — | 2026-08-14 committed 2026-08-17 |
 DVA1.9% | 9.8856 | 178.18 | — | 2026-08-14 committed 2026-08-17 |
 GOOGL6.0% | 17.3171 | 347.65 | — | 2026-08-14 committed 2026-08-17 |
 KHC2.7% | 110.1529 | 25.28 | — | 2026-08-14 committed 2026-08-17 |
 KO10.1% | 114.0121 | 87.65 | — | 2026-08-14 committed 2026-08-17 |
 KR1.5% | 24.5193 | 56.26 | — | 2026-08-14 committed 2026-08-17 |
 MCO4.0% | 8.5162 | 481.70 | — | 2026-08-14 committed 2026-08-17 |
 OXY7.0% | 113.4339 | 58.58 | — | 2026-08-14 committed 2026-08-17 |
 SGOV9.9% | 99.4431 | 100.97 | — | 2026-08-14 committed 2026-08-17 |
 SIRI1.1% | 39.0021 | 28.47 | — | 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 selector'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. This portfolio is a pure mechanical tracker of Berkshire Hathaway's disclosed equity holdings from its most recent 13F filing (period 2026-03-31, filed 2026-05-15). According to the mandate, the portfolio rebalances only when new filings arrive and uses value-proportional weights across the top disclosed positions. The current holdings precisely mirror the 13F copybook weights disclosed in the fact pack. The 15 positions held are: AAPL (10.16% vs 22.22% copybook, fact pos.AAPL.weight_pct, p12:copybook:AAPL), AXP (9.65% vs 17.62%, facts pos.AXP.weight_pct, p12:copybook:AXP), BAC (9.21% vs 9.62%, facts pos.BAC.weight_pct, p12:copybook:BAC), KO (10.30% vs 11.69%, facts pos.KO.weight_pct, p12:copybook:KO), SGOV (9.99% cash-equivalent, fact pos.SGOV.weight_pct), CVX (6.89% vs 6.71%, facts pos.CVX.weight_pct, p12:copybo…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN AAPL | 3 | PROPOSED→GATES PASSED→NO ORDER EXPLAIN is a decision not to trade — no order is created | — |
| BUY VRSN @ 0.86% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY COF @ 0.5% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY NYT @ 0.49% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY ALLY @ 0.44% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY GOOG @ 0.4% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY LEN @ 0.34% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
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 an experimental mechanical replication portfolio tracking Berkshire Hathaway's disclosed 13F holdings. According to the mandate, this portfolio value-weights the top disclosed US equity positions from Berkshire's most recent 13F-HR filing and rebalances only when new filings arrive. **Current Holdings Structure:** The portfolio holds 15 positions as of 2026-08-19 (pf.position_count). All holdings trace to Berkshire's 2026-Q1 13F filing dated 2026-05-15 (fact IDs p12:copybook:AAPL through p12:copybook:SIRI). The top positions by weight are: - AAPL: 10.28% (pos.AAPL.weight_pct) — copybook 22.22% (p12:copybook:AAPL) - KO: 10.23% (pos.KO.weight_pct) — copybook 11.69% (p12:copybook:KO) - SGOV: 9.93% (pos.SGOV.weight_pct) — a cash-equivalent ETF (meta.SGOV.asset_class) - AXP: 9.85% (pos.AXP.weight_pct) — copyboo…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN AAPL | 3 | PROPOSED→GATES PASSED→NO ORDER EXPLAIN is a decision not to trade — no order is created | — |
| BUY VRSN @ 0.86% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY COF @ 0.5% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY NYT @ 0.49% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY ALLY @ 0.44% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY GOOG @ 0.4% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY LEN @ 0.34% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
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 portfolio mechanically replicates Berkshire Hathaway's disclosed 13F holdings from their 2026-03-31 filing submitted 2026-05-15. The portfolio holds 15 positions representing the top disclosed stakes value-proportionally. Per the mandate, this is an EXPLAIN-ONLY role: I cannot propose trades, only explain what the holdings represent and flag data anomalies. Current holdings match the disclosed top-20 positions from the March 2026 13F: - AAPL (10.10% weight, fact pos.AAPL.weight_pct) maps to 22.22% of the 13F top-20 (fact p12:copybook:AAPL) - AXP (9.85%, fact pos.AXP.weight_pct) maps to 17.62% of the 13F top-20 (fact p12:copybook:AXP) - BAC (9.55%, fact pos.BAC.weight_pct) maps to 9.62% of the 13F top-20 (fact p12:copybook:BAC) - KO (10.10%, fact pos.KO.weight_pct) maps to 11.69% of the 13F top-20 (fact p12:co…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN AAPL | 3 | PROPOSED→GATES PASSED→NO ORDER EXPLAIN is a decision not to trade — no order is created | — |
| BUY VRSN @ 0.86% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY COF @ 0.5% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY NYT @ 0.49% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY ALLY @ 0.44% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY GOOG @ 0.4% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY LEN @ 0.34% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
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 portfolio mechanically replicates Berkshire Hathaway's disclosed equity holdings from their most recent 13F-HR filing dated 2026-03-31 (filed 2026-05-15). The fact pack shows 15 positions currently held, representing the top-20 disclosed positions from that filing, with weights proportional to the reported values. Current portfolio NAV is $99,520.38 (pf.nav), down -0.48% from the $100,000 starting capital (pf.total_return_pct), with a -0.48% drawdown from peak (pf.drawdown_pct). Cash stands at $14,509.63 or 14.58% of NAV (pf.cash_pct). The largest holdings align with the disclosed weights: • AAPL: 10.04% portfolio weight (pos.AAPL.weight_pct), based on $57.8B or 22.22% of copied top-20 (p12:copybook:AAPL) • SGOV: 10.05% (pos.SGOV.weight_pct) - cash equivalent position • KO: 9.96% (pos.KO.weight_pct), based o…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN AAPL | 3 | PROPOSED→GATES PASSED→NO ORDER EXPLAIN is a decision not to trade — no order is created | — |
| BUY VRSN @ 0.86% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY COF @ 0.5% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY NYT @ 0.49% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY ALLY @ 0.44% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY GOOG @ 0.4% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY LEN @ 0.34% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
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 portfolio is a mechanical replication system for Berkshire Hathaway's 13F-HR disclosed equity holdings (meta.P12: "Berkshire 13F Tracker"). The mandate specifies value-proportional weights across disclosed positions, rebalanced only when a new 13F filing arrives. The AI layer's role is strictly explain_and_flag_only—no trade proposals are permitted, only EXPLAIN and FLAG_DATA_ANOMALY actions. Current State (as of 2026-08-14): - Portfolio holds zero positions (pf.position_count: 0 count) - Cash is 100% (pf.cash_pct: 100%, pf.cash_usd: $100,000) - NAV equals starting capital (pf.nav: $100,000, pf.starting_capital: $100,000) - Total return is 0% (pf.total_return_pct: 0%) - No fees paid or dividends received (pf.fees_paid: $0, pf.dividends: $0) - Maximum positions allowed: 20 (pf.max_positions: 20) - All position…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN BRK.B | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_INVENTED_FACT_REF |
| BUY AAPL @ 10% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY AXP @ 10% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY KO @ 10% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY BAC @ 9.62% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY CVX @ 6.71% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY OXY @ 6.62% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY GOOGL @ 5.99% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY CB @ 4.29% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY MCO @ 4.13% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY KHC @ 2.81% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY DVA @ 1.78% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY KR @ 1.39% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY SIRI @ 1.11% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY DAL @ 1.02% target mechanical | 3 | PROPOSED→GATES PASSED→QUEUED→FILLED | — |
| BUY VRSN @ 0.86% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY COF @ 0.5% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY NYT @ 0.49% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY ALLY @ 0.44% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY GOOG @ 0.4% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY LEN @ 0.34% target mechanical | 3 | PROPOSED→REFUSED AT GATES no order was created | REJECT_BELOW_MIN_POSITION |
| BUY SGOV @ 10% target mechanical | 1 | 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 32.6872 AAPL @ 306.34 · BUY 29.1988 AXP @ 340.81 · BUY 114.0121 KO @ 87.65 · BUY 149.1704 BAC @ 64.43 · BUY 33.5500 CVX @ 200.81 · BUY 113.4339 OXY @ 58.58 · BUY 17.3171 GOOGL @ 347.65 · BUY 12.4840 CB @ 346.34 · BUY 8.5162 MCO @ 481.70 · BUY 110.1529 KHC @ 25.28 · BUY 9.8856 DVA @ 178.18 · BUY 24.5193 KR @ 56.26 · BUY 39.0021 SIRI @ 28.47 · BUY 11.4158 DAL @ 89.10 · BUY 99.4431 SGOV @ 100.97
AI-generated. All quantitative claims traced to the published fact pack. The Berkshire 13F Tracker portfolio (P12) is currently 100% cash (pf.cash_pct) with NAV of $100,000 USD (pf.nav), representing starting capital (pf.starting_capital_usd). The portfolio holds zero positions (pf.position_count) and has generated zero total return (pf.total_return_pct). This mandate is designed to mechanically replicate Berkshire Hathaway's disclosed US equity holdings from its most recent 13F-HR filing, rebalancing only when new filings arrive. The current risk state is PAUSE_OUTSIDE_REBALANCE_WINDOW, with the next rebalance window opening 2026-08-14. Between filing windows, the portfolio is frozen by design, trading only in declared rebalance windows (exits for risk reasons remain permitted). One copybook position exists: ALLY with a disclosed value of $1,137,670,000 representing 0.44% of Berkshir…
| Proposal | Conviction | Lifecycle | Codes |
|---|---|---|---|
| EXPLAIN ALLY | 3 | 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 this book's published arithmetic 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 standard · prompt version P12-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.
Top disclosed positions by reported value, weighted value-proportionally across the copied set, clamped to the entry cap, residual parked in the declared cash equivalent. An amendment (13F-HR/A) supersedes the original for the same period. Implemented in engine/selection.py (ManagerCopySelector); inputs committed to the fact pack before every run.
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 | 50.0% | 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 | 1.0% | 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 −25.0% drawdown | alert, publish_commentary | gate 3 — drawdown ladder |
| At −40.0% drawdown | alert, mandatory_deep_review | gate 3 — drawdown ladder |
| At −60.0% drawdown | graveyard_review | gate 3 — drawdown ladder |
| Limit | Value | Enforced by |
|---|---|---|
| Max trades per quarter | 60 | 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.
- This portfolio tracks the last disclosed quarterly filing — up to 45 days stale, long-only, shorts/hedges invisible.
- 13F filings are due 45 days after quarter end. Position data is between 45 and 136 days old, mean approximately 90 days.
- The copy is CAPPED, not exact: Berkshire's real book is far more concentrated than this mandate's per-position entry cap permits, so the largest disclosed positions are deliberately under-weighted here and the difference is visible in every rebalance fact pack.
- Disclosed positions outside this platform's licensed pricing universe are excluded, and the exclusion count is published in each cycle's fact pack.
- This portfolio is not affiliated with, endorsed by, or connected to Berkshire Hathaway. The manager is 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
The most famous portfolio in the world is public four times a year, 45 days late. This portfolio asks the cheapest possible question about it: what does the DISCLOSURE alone earn, copied mechanically, with no discretion, no timing, and honest costs? It is a measurement instrument, not a strategy — the AI explains and flags anomalies, and deterministic code does everything else.
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/P12_berkshire_tracker.yaml · human rulebook: docs/portfolios/P12_berkshire_tracker.md · effective from 2026-08-10 (wall clock) · record starts 2026-08-13 (pricing session) · payload 540d30e63326…