<b>Personal research mode.</b> This copy is for your own analysis, paper tracking, and manual trade research only. It does not pool money, onboard investors, custody funds, bypass eligibility rules, or place orders without your manual approval.
</div>
<divclass="live-build-banner"><b>Build 95 active:</b> The public paper agents run autonomously every 15 minutes while every user device is closed. Strategy 4's contract-safe rule failed its untouched chronological holdout, so it now collects zero-capital observations instead of opening new positions. Forty positive independent forward events can qualify 1% paper positions, eighty stronger events can raise size to 1.5%, and losing evidence keeps capital disabled. Existing positions still receive executable exits. Phones and computers display the same read-only autonomous state. Profits are not guaranteed.</div>
<divclass="live-build-banner"><b>Build 96 active:</b> The public paper agents run autonomously every 15 minutes while every user device is closed. Five aggressive agents can take tightly bounded, fixed-date 50–55% NO positions only in independently passing three-day or seven-day settlement windows. Entries use an executable ask plus slippage, one agent owns each event, positions hold to verified settlement, and each horizon can demote itself from losing forward evidence. Other unproven directional rules remain observation-only. Phones and computers display the same read-only autonomous state. Profits are not guaranteed.</div>
drivers:[`validated ${window.days}-day settlement window`,"NO midpoint is 50–55%","executable NO ask plus 0.25c slippage","one owner per event","hold to verified settlement"],
rationale:`Bounded current-regime pilot: NO is priced at ${pct(marketPrice)} for a fixed-date contract resolving in ${days.toFixed(1)} days, inside the independently passing ${window.days}-day window. The modeled entry is ${pct(modeledEntry)} using the executable NO ask plus 0.25-cent slippage, ${(executionCost*100).toFixed(2)} cents above midpoint. In the most recent 2,916 resolved-market replay at one-cent cost, the exact 50–55% NO rule covered ${audit.events} ${window.days}-day event clusters with a ${(audit.eventMean*100).toFixed(2)}% event mean and ${(audit.lower*100).toFixed(2)}% lower 90% bound; chronological train and holdout bounds were ${(audit.trainLower*100).toFixed(2)}% and ${(audit.holdoutLower*100).toFixed(2)}%. Historical liquidity at the decision point cannot be reconstructed, so this remains a 0.5% paper pilot with live liquidity gates, one owner per event, a 3% total cap, settlement-only exits, and automatic per-horizon forward demotion.`};
}
function sportsFavoriteLeadHours(item){return hoursUntil(item&&item.game_start);}
@@ -1578,7 +1623,7 @@ function marketWatchSuggestion(m,realWorldSignals={}){
rationale:`Market watchlist: included for coverage from the active-market scan. Signal margin is ${(Math.abs(netEdge)*100).toFixed(1)}c and evidence score is ${Math.round(evidence.score*100)}, so agents will not buy it unless confirmation improves.`};
}
function generateSuggestions(markets,total=SUGGESTION_TOTAL,perCategory=SUGGESTION_PER_CATEGORY,realWorldSignals={}){
rationale:`Forward evidence disabled the ${s.target_horizon_days||7}-day regime pilot after ${horizon&&horizon.events||profile&&profile.events||0} independent settled events. ${s.rationale||""}`});
@@ -3625,9 +3750,12 @@ function openPositions(p,cfg,rankedSugs,focus,decision,avoidMarketIds,peerStats=
?`${decision?decision.mode+" mode — ":""}Forward-promoted sports position bought ${shares} ${s.side} '${s.question.slice(0,40)}' @ modeled ${pct(entry)} for ${fmtUSD(cost)} (${pct(Number(s.market_price||entry))} midpoint + ${((entry-Number(s.market_price||entry))*100).toFixed(2)}c executable friction) · one position for event ${s.event_key||s.event||s.market_id} · learner state ${pilotProfile.state} · ${(Number(s.hours_to_start)||0).toFixed(1)}h before start`
:s.signal_type==="shock-fade-pilot"
?`${decision?decision.mode+" mode — ":""}${shockProfile.promoted?"Forward-promoted":"Forward-qualified"} ${SHOCK_FADE_EXIT_HOURS}-hour shock fade bought ${shares} ${s.side} '${s.question.slice(0,40)}' @ executable modeled ${pct(entry)} for ${fmtUSD(cost)} after a ${(Number(s.shock_move_3h||0)*100).toFixed(2)}-point move · learner state ${shockProfile.state} · fixed executable exit target in ${SHOCK_FADE_EXIT_HOURS}h`
:s.signal_type==="resolution-week-no-pilot"
?`${decision?decision.mode+" mode — ":""}${resolutionProfile.promoted?"Forward-promoted":"Bounded current-regime"} ${s.target_horizon_days||7}-day resolution pilot bought ${shares} NO '${s.question.slice(0,40)}' @ executable modeled ${pct(entry)} for ${fmtUSD(cost)} · one owner for event ${s.event_key||s.market_id} · hold to verified settlement · shared state ${resolutionProfile.state}`
:`${decision?decision.mode+" mode — ":""}Bought ${shares} ${s.side} '${s.question.slice(0,40)}' @ ${pct(entry)} for ${fmtUSD(cost)} · max binary loss budget ${(riskBudgetPct*100).toFixed(1)}% · signal margin ${((Math.abs(s.net_edge!=null?s.net_edge:s.edge))*100).toFixed(1)}c · learned weight ${Number(s.learning_multiplier||1).toFixed(2)}x (${s.learning_state||"observing"}/${s.market_learning_state||"observing"})${(s.historical_prior_features||[]).length?` · history prior ${(s.historical_prior_features||[]).join("+")}`:""} · evidence ${Math.round((s.evidence_score||0)*100)}${s.peer_note?` (${s.peer_note})`:""}`;
p.lastDecision.allocationStatus=`${p.lastDecision.allocationStatus||""} Resolution-window NO pilot: shared state ${sharedResolutionWeekProfile.state}, ${sharedResolutionWeekProfile.events} settled events, ${(sharedResolutionWeekProfile.position_pct*100).toFixed(2)}% position cap and ${RESOLUTION_WEEK_NO_TOTAL_CAPITAL_PCT*100}% total cap; only validated 3d/7d windows can trade, one agent owns each event, and positions hold to verified settlement.`.trim();
const learning=d.learning?` Learning: ${d.learning.samples} completed trades retained as historical context, ${(d.learning.global_score*100).toFixed(2)}% all-version shrunk expectancy; ${d.learning.current_samples||0} completed under adaptive strategy ${SUGGESTION_ENGINE_VERSION} with ${((d.learning.current_global_score||0)*100).toFixed(2)}% current-strategy shrunk expectancy. Only current-strategy closed trades can change sizing or personal cohort promotion${d.learning.best?`; historical strongest ${d.learning.best.feature.replace(":"," ")}`:""}${d.learning.worst?`; historical weakest ${d.learning.worst.feature.replace(":"," ")}`:""}.`:"";
@@ -4105,14 +4247,15 @@ function decisionSummary(p){
const maker=d.makerQuotes!=null?` Maker research: ${d.makerShadowActive||0} zero-capital lock-or-exit observations active; ${d.makerFills||0} verified touches and ${d.makerShadowCompleted||0} outcomes completed this cycle.${makerStats?` Event-clustered ledger: ${makerStats.attempts} attempts / ${makerStats.events} events, ${makerStats.locked} locked pairs, ${makerStats.adverse} immediate adverse exits, ${makerStats.unfilled} unfilled, and ${fmtUSD(makerStats.shadow_pnl)} simulated shadow net.`:""} Capital is disabled because neither the 6,048-rule chronological maker audit nor the reward stress test produced a validated holdout winner. Hypothetical rewards are excluded.`:"";
const sportsPilot=d.sportsFavoritePilot?` Sports forward learner: ${d.sportsFavoritePilot.state}, ${d.sportsFavoritePilot.active_shadows||0} zero-capital observations active and ${d.sportsFavoritePilot.events} independent closed events, ${d.sportsFavoritePilot.events?`${(d.sportsFavoritePilot.mean*100).toFixed(2)}% mean with ${d.sportsFavoritePilot.lower>=0?"+":""}${(d.sportsFavoritePilot.lower*100).toFixed(2)}% to ${d.sportsFavoritePilot.upper>=0?"+":""}${(d.sportsFavoritePilot.upper*100).toFixed(2)}% 90% interval; `:""}${fmtUSD(d.sportsFavoritePilot.shadow_pnl_per_100||0)} simulated per-$100 net and ${fmtUSD(d.sportsFavoritePilot.pnl)} realized capital P&L. Position cap ${(d.sportsFavoritePilot.position_pct*100).toFixed(2)}%; capital remains zero until ${SPORTS_FAVORITE_PROMOTION_EVENTS} new independent events establish a positive lower bound.`:"";
const shockPilot=d.shockFadePilot?` Shared shock strategy ${SHOCK_FADE_STRATEGY_VERSION}: ${d.shockFadePilot.state}, ${d.shockFadePilot.active_shadows||0} ${SHOCK_FADE_EXIT_HOURS}-hour observations active and ${d.shockFadePilot.events} deduplicated forward events complete across five adopters. Mean ${(d.shockFadePilot.mean*100).toFixed(2)}%; 90% interval ${(d.shockFadePilot.lower*100).toFixed(2)}% to ${(d.shockFadePilot.upper*100).toFixed(2)}%; ${d.shockFadePilot.expired_ungraded||0} missed windows were discarded. Position cap ${(d.shockFadePilot.position_pct*100).toFixed(2)}%, total cap ${SHOCK_FADE_TOTAL_CAPITAL_PCT*100}%; ${SHOCK_FADE_QUALIFICATION_EVENTS} positive events can qualify 1% capital and ${SHOCK_FADE_PROMOTION_EVENTS} stronger events can raise size to ${SHOCK_FADE_PROMOTED_POSITION_PCT*100}%.`:"";
return `${d.mode} mode: ${d.reason}${emotion} Limits now: ${d.maxNew} new trade${d.maxNew===1?"":"s"}, max ${(d.maxFrac*100).toFixed(1)}% per position${d.minConv?`, conviction ${d.minConv}+`:""}.${learning}${calibration}${maker}${sportsPilot}${shockPilot}${exposure}${allocation}${candidates}${blockers}`;
const resolutionWeek=d.resolutionWeekNoPilot?` Resolution-window NO pilot: ${d.resolutionWeekNoPilot.state}, ${d.resolutionWeekNoPilot.events} shared settled events, ${(d.resolutionWeekNoPilot.mean*100).toFixed(2)}% mean and ${(d.resolutionWeekNoPilot.lower*100).toFixed(2)}% lower 90% bound. Position cap ${(d.resolutionWeekNoPilot.position_pct*100).toFixed(2)}%, total cap ${RESOLUTION_WEEK_NO_TOTAL_CAPITAL_PCT*100}%; only validated 3d/7d windows can trade, each horizon adapts separately, one agent owns each event, and every position holds to verified settlement.`:"";
return `${d.mode} mode: ${d.reason}${emotion} Limits now: ${d.maxNew} new trade${d.maxNew===1?"":"s"}, max ${(d.maxFrac*100).toFixed(1)}% per position${d.minConv?`, conviction ${d.minConv}+`:""}.${learning}${calibration}${maker}${sportsPilot}${shockPilot}${resolutionWeek}${exposure}${allocation}${candidates}${blockers}`;
const cadence=cfg.id==="favorite"?"Zero-capital 12h sports observations until 30 forward events promote 1.25% positions":SHOCK_FADE_ADOPTER_IDS.has(cfg.id)?`Zero-capital 12h shock observations until ${SHOCK_FADE_QUALIFICATION_EVENTS} positive events qualify 1% positions; 1.5% requires ${SHOCK_FADE_PROMOTION_EVENTS}`:`${cfg.maxNew||0} new trades max per cycle`;
const exitRule=cfg.id==="favorite"?"Grade shadow observations only when Polymarket closes the market; after promotion, capital positions retain the 18% stop and profit locks":SHOCK_FADE_ADOPTER_IDS.has(cfg.id)?`Exit shock positions at the executable bid after ${SHOCK_FADE_EXIT_HOURS} hours; missed grading windows expire without using a later price`
const cadence=cfg.id==="favorite"?"Zero-capital 12h sports observations until 30 forward events promote 1.25% positions":RESOLUTION_WEEK_NO_ADOPTER_IDS.has(cfg.id)?`One bounded 3d/7d resolution-window NO entry per cycle; ${RESOLUTION_WEEK_NO_TOTAL_CAPITAL_PCT*100}% total cap plus zero-capital shock research`:`${cfg.maxNew||0} new trades max per cycle`;
const exitRule=cfg.id==="favorite"?"Grade shadow observations only when Polymarket closes the market; after promotion, capital positions retain the 18% stop and profit locks":RESOLUTION_WEEK_NO_ADOPTER_IDS.has(cfg.id)?`Hold 3d/7d resolution-window positions to verified settlement; exit shock positions at the executable bid after ${SHOCK_FADE_EXIT_HOURS} hours and discard missed grading windows`
:`Exit after a confirmed reversal, a 12h unconfirmed fade after 48h, a trailing-profit retrace, or ${EXIT_STALE_DAYS}d stale while losing; Politics trends get 72h before ordinary signal exits`;
const thesis=agentPlainBlurb(cfg,st);
const quoteSummary=(p.maker_quotes||[]).slice(0,3).map(quote=>`${quote.shadow_only?"Shadow":"Capital"} · ${quote.question.slice(0,34)}${quote.question.length>34?"...":""}: YES ${pct(quote.yes_quote)} + NO ${pct(quote.no_quote)}${quote.yes_filled_at||quote.no_filled_at?" (one leg touched)":""}`).join("; ");
historicalPrior:"No broad directional rule survived the adaptive holdouts at both 24h and 72h. Contract-safe Shock Strategy 4 fades an accelerating 8% three-hour move and grades an executable exit after 12 hours, while rejecting path barriers, exact numeric ranges, and insufficient runway. At a two-cent modeled cost, its primary event-clustered 90% lower bounds were +0.13% train, +3.56% validation, +0.99% chronological holdout, and +0.18% event holdout across 314 partition-events. On the untouched next 1,000 markets, the chronological lower bound was -9.35% and the event-holdout lower bound was -0.32%; no category or entry-price refinement survived every independent partition. Capital is therefore disabled. The five aggressive agents share disjoint zero-capital forward observations; 40 positive events can qualify 1% paper positions, 80 stronger events can raise size to 1.5%, and losing evidence keeps the lane disabled. Resolved archive coverage remains unavailable. Favorite-priced trend remains hard-blocked. Maker capital remains disabled"}),
historicalPrior:"No broad directional rule survived the adaptive holdouts at both 24h and 72h. Contract-safe Shock Strategy 4 remains zero-capital after its untouched expansion failed. A separate current-regime 50%-55% NO rule passed exact three-day and seven-day chronological audits at one-cent modeled cost; one-day, fourteen-day, thirty-day, and ninety-day windows failed or lacked evidence and remain disabled. Contemporaneous historical liquidity cannot be reconstructed, so only live, fixed-date, non-sports contracts in the passing windows that clear spread and liquidity gates receive 0.5% paper positions, one owner per event, a 3% cap, settlement-only exits, and automatic per-horizon demotion from forward losses. Favorite-priced trend remains hard-blocked. Maker capital remains disabled"}),
});
function runEngineSelfTest(){
const market=(overrides={})=>Object.assign({
@@ -5802,6 +5957,42 @@ function runEngineSelfTest(){
const pathBarrierContract=analyzeMarket(market({id:"barrier-test",question:"Will Bitcoin reach $66,000 August 17-23?",category:"Crypto"}),news);
const fixedDateLevelContract=analyzeMarket(market({id:"fixed-level-test",question:"Will Bitcoin be above $66,000 on 2026-08-23?",category:"Crypto"}),news);
const ordinaryDatedContract=analyzeMarket(market({id:"dated-test",question:"Will the policy pass on 2026-08-22?"}),news);
const resolutionWeekMarket=market({id:"resolution-week",question:"Will Bitcoin be above $82,000 on August 27?",event:"Bitcoin price on August 27",event_id:"btc-aug-27",
const pathDependentResolutionWeek=resolutionWeekNoSuggestion(market({id:"resolution-path",question:"Will Bitcoin reach $82,000 by August 27?",event_id:"resolution-path-event",
const sportsResolutionWeek=resolutionWeekNoSuggestion(market({id:"resolution-sports",question:"Will Harbor FC win?",event_id:"resolution-sports-event",
const sportsPilot=analyzeMarket(market({id:"sports-pilot",question:"Will Harbor FC win tomorrow?",event:"Harbor FC vs City FC",event_id:"sports-event-1",
note:"Current active-market selection and current category tags are a survivorship-biased proxy; signal inputs and future marks are time-ordered without lookahead. Confidence intervals cluster correlated markets by Polymarket event."},
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Theodore Song