Loading match analysis
Pulling the odds, probabilities and the full engine breakdown for this fixture.
Aluminij🌍Country pendingvs
Sheriff Tiraspol🌍Country pending
Score: 0-1
suspended
Suspended — no new pre-match decision.
This fixture is not eligible for a new public pre-match decision.
Key risks
- engine action is avoid
- calibration requires abstention
- engine actionability is blocked
Slip action lockedOnly a current, published value pick can be added.Discuss match
Probability comparison
The full bar is 100% of the model's 1X2 distribution. Evidence quality is shown separately so confidence is not confused with probability.
- Aluminij
- 31%
- Draw
- 27%
- Sheriff Tiraspol
- 42%
Evidence quality90%
Historical evidenceHistorical calibration range
Not availableNo statistical band is shown.
No selected runtime probability is available for an empirical calibration interval.
Model evidence
reviewHow the engine reached this view
This is the deterministic calculation path, not a generated explanation. Positive factors support the selected side; negative factors pull against it.
The engine did not produce a valid probability trace for this market.
Model and calibration provenance
- Historical evidence model
- football-poisson-v3
- Runtime parity
- exact runtime parity
- Engine version
- decision-engine-v1
- Learning profile
- shadow-only
- Calibration
- inactive
- Historical sample
- 4,135
- Held-out sample
- 1,241
- Normalized Brier
- 0.199
- Log loss
- 1.002
- Calibration error
- 0.043
- Player-form coverage
- 65% (1,871 fixtures)
- Training player form
- 65%
- Holdout player form
- 100%
Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion.
Live outcome calibration: Probability calibration remains inactive until a real-data backtest receives explicit live-guardrail promotion.
Player-form coverage uses only provider-capable fixtures and requires acceptable or strong chronology-safe history in both training and holdout windows. Normalized Brier averages squared probability error across the market outcomes; lower is better. Calibration error measures the weighted gap between forecast probability and observed frequency.
Value edge-11.0 pts
Data quality+8.0 pts
Expected value-6.0 pts
Confidence guardrail-5.0 pts
Outcome variance-3.0 pts
Case memory-2.0 pts
Data coverage uncertainty100/100
Context uncertainty84/100
Price execution uncertainty70/100
Robustness and review uncertainty80/100
Weighted evidence-risk index, not a statistical confidence level.
Data coverage uncertainty. Downgrade or block public trust until data coverage uncertainty is addressed. Confidence penalty -16.9%.
Market analysis
“Value edge” is our probability minus the bookmaker's fair probability (margin removed). Positive edge means the price is better than it should be. Current best edge: none found.
| Market | Selection | Odds | Bookmaker | Model | Raw implied | No-vig implied | Margin | No-vig edge | EV |
|---|
Odds movement and freshness
Decision generated7/17/2026, 11:28:53 AM
Price expiresAwaiting fresh odds
No stored match winner movement yet
No verified pre-match odds snapshots are stored for this fixture yet.
OddsPadi explanation
OddsPadi estimates Aluminij at 31%, the draw at 27%, and Sheriff Tiraspol at 42%. The current prices do not show a clear positive value edge, so the responsible call is to avoid forcing a pick.
- The model weighs ratings, recent form, attack and defensive strength.
- Recent H2H (2): Aluminij 0 wins, 1 draws, Sheriff Tiraspol 1 wins.
- Bookmaker margin is removed where possible before value edge is calculated.
- Confidence stays cautious when the edge is weak or data quality is limited.
Sports outcomes are uncertain. Predictions are model estimates, not guarantees.
Advanced engine audit
Audit-only detail cannot override the canonical public decision above. Candidate markets below show the engine's working, including blocked opportunities, but only the canonical status is publishable.
Decision engine
decision-engine-v1 - rules and model reasoning
Decision engine says avoid forcing a pick for Aluminij vs Sheriff Tiraspol; the available edges do not justify a recommendation.
Research brief
Statusblocked
Decision clockBelief expires at 11:28 UTC; next review is 11:28 UTC.
Aluminij vs Sheriff Tiraspol is blocked from a public recommendation.
Decision engine says avoid forcing a pick for Aluminij vs Sheriff Tiraspol; the available edges do not justify a recommendation. The research brief says block public recommendation until failed gates, missing data, or invalid memory conditions are repaired.
Model thesisNo market is currently a thesis worth recommending for Aluminij vs Sheriff Tiraspol.
Market thesisMarket thesis is neutral: no selection clears positive edge and expected-value guardrails.
Risk thesisRisk thesis blocks the recommendation: Value edge and EV: No selection passed positive-edge and expected-value filters..
Research checks: Refresh bookmaker odds: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value. Injury and suspension news: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates. Confirmed lineups: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates. Positive edge and EV required: Do not promote the decision until this abstention gate is cleared by fresh model, market, or provider evidence. Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
Decision notebook
Statusblocked
Assumptions5
Falsifiers5
Next review11:28 AM
Notebook is blocked: 3 falsifier or abstention condition(s) prevent public trust.
assumption - medium - blockedModel probability remains valid
No modeled candidate clears the value guardrail.
Action: Rerun the sport model after any lineup, injury, weather, odds, or live-state update.
assumption - critical - blockedMarket price still supports the thesis
Market prices do not create positive expected value.
Action: Refresh bookmaker odds and recompute raw implied probability, no-vig probability, edge, and EV.
assumption - high - openMissing context does not overturn the thesis
Open context gaps: Injury and suspension news, Confirmed lineups, Weather check.
Action: Fetch the highest-priority missing provider signals before keeping the same action.
falsifier - critical - blockedOdds shorten enough to erase value
No value thesis exists to falsify.
Action: Downgrade to avoid when no-vig edge or EV falls to zero or below.
falsifier - high - openAdverse injury, lineup, weather, or live event appears
Stress applies unresolved context gaps: Injury and suspension news, Confirmed lineups, Weather check.
Action: Apply the provider context update and rerun actionability before showing the pick.
falsifier - high - openBelief expires before refresh
Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes.
Action: Hide or downgrade the recommendation if the belief expires without a fresh decision run.
Operator checklist: Refresh bookmaker odds: Complete this check, then rerun the decision engine before trusting the current posture. Injury and suspension news: Complete this check, then rerun the decision engine before trusting the current posture. Confirmed lineups: Complete this check, then rerun the decision engine before trusting the current posture. Positive edge and EV required: Complete this check, then rerun the decision engine before trusting the current posture. Wait for fresh odds or a stronger model-market disagreement before showing a candidate.: Complete this check, then rerun the decision engine before trusting the current posture.
Agent calibration
Healthreview
Reliability51/100
Calibration actionabstain
Contradictions0
Decision should abstain or avoid until the blocking condition changes.
Data coverage
Statusinsufficient
Score28/100
Provider-backed1
Mock0
Missing8
Stale0
Data coverage is 28/100; too many required provider signals are missing for production trust.
provider backed - pre match - api-footballFixture for the day
Aluminij vs Sheriff Tiraspol is loaded from api-football.
computed - historical - api-football-recent-fixtures-form-rating-v1 + league-strength-baseline-v1 + missing-player-historyTeam/player historical results
Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
missing - missing - missing-providerLeague standings
Standings snapshots exist in the training schema but are not yet connected to live decisions.
computed - pre match - deterministic-provider-proxyHome/away performance
Home/away strength uses deterministic form proxies, team rating, and league strength; data quality 89%.
computed - pre match - deterministic-provider-proxyRecent form
Recent form is currently estimated from provider fixtures and deterministic team proxies until a form feed is connected.
missing - missing - missing-providerInjuries
No provider-backed injury feed is connected.
missing - missing - missing-providerSuspensions
No suspension provider is connected.
missing - missing - missing-providerLineups
Confirmed lineups/starters are not connected.
Required before trust: Injuries: No provider-backed injury feed is connected. Suspensions: No suspension provider is connected. Lineups: Confirmed lineups/starters are not connected. News signals: No news provider is connected. Weather: No weather provider is connected for outdoor totals/tempo markets. League standings: Standings snapshots exist in the training schema but are not yet connected to live decisions. Bookmaker odds: No odds market snapshot is available. Team/player historical results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
Odds intelligence
Statusno value
Markets0
Positive EV0
Actionable0
Avg marginN/A
Best actionableNone
Watch leaderNone
Odds intelligence found no positive expected-value candidate after bookmaker-margin removal.
Market movement intelligence
Statusno market
Current oddsN/A
Fair oddsN/A
Shortening roomN/A
Market movement cannot be evaluated because no positive-value candidate is selected.
No priced candidate - action avoidN/A
Edge N/A; EV N/A. Wait for a priced candidate before evaluating odds movement.
Movement alerts: No priced candidate is available; do not manufacture market movement intelligence.
Belief state
Gradefragile
Believed probabilityNo trusted pick
Probability edgeNo edge
Uncertainty60/100
Empirical bandNo data
Expires0 min
Supports0
Opposes3
No selected runtime probability is available for an empirical calibration interval.
Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes.
opposes - low confidence - model-and-marketNo value belief
Impact -4.0%. No selection passed positive-edge and confidence filters.
opposes - medium confidence - calibrationCalibration belief
Impact -5.0%. Decision should abstain or avoid until the blocking condition changes.
opposes - medium confidence - decision-memoryCase memory belief
Impact -3.0%. Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
uncertain - low confidence - team-newsInjury and suspension news
Impact 0.0%. No live injury/suspension provider is connected yet.
Invalidates when: Invalidate if fresh odds create a positive no-vig edge with acceptable confidence. Invalidate if confirmed lineups, injuries, suspensions, weather, or live events materially oppose the current thesis. Invalidate if bookmaker prices move before the next refresh window. Invalidate or downgrade because case memory says discount. Blocking gate: Positive edge and EV required.
Probability trace
Statusblocked
Market priorN/A
Model probabilityN/A
PosteriorN/A
Posterior edgeN/A
Posterior EVN/A
Probability trace is blocked because no priced selection passed the value guardrail.
posterior - skipped - weight 0%No priced candidate
No probability update. The engine cannot expose a runtime probability path until a selection has model probability, no-vig market probability, and odds.
Trace conflicts: No selection passed the value, EV, and confidence guardrails.
Trace safeguards: Do not infer a probability path without a priced candidate. Rerun after fresh odds create a positive no-vig edge and positive expected value.
Decision attribution
Statusblocked
Decisive factorData coverage
Value score0/100
Risk score100/100
Net movementN/A
Model-market gapN/A
Attribution is blocked: Data coverage prevents a trusted public recommendation.
negative - data - impact 100/100Data coverage
Data coverage is 28/100; too many required provider signals are missing for production trust.
negative - risk - impact 88/100Review loop
Review loop blocks the recommendation until failed gates or abstention rules clear.
negative - risk - impact 82/100Positive edge and EV required
The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds.
Missing-data drag: Injuries, Suspensions, Lineups, News signals, Weather.
The final action is constrained by a blocker; do not treat the selected side as public value until the negative driver clears.
Decision-risk decomposition
Statushigh risk
Diagnostic index63/100
PrimaryData coverage uncertainty
Penalty-16.9%
Diagnostic uncertainty risk is high at 63/100; primary uncertainty is Data coverage uncertainty.
Weighted evidence-risk index, not a statistical confidence level.
high - data - contribution 20.0Data coverage uncertainty: 100/100
Data coverage is 28/100; too many required provider signals are missing for production trust.
Mitigation: Injuries: No provider-backed injury feed is connected.
high - context - contribution 11.8Context uncertainty: 84/100
Missing context: Injury and suspension news, Confirmed lineups, Weather check.
Mitigation: Fetch or verify Injury and suspension news before raising confidence.
high - price - contribution 8.4Price execution uncertainty: 70/100
Market movement cannot be evaluated because no positive-value candidate is selected.
Mitigation: No priced candidate is available; do not manufacture market movement intelligence.
high - robustness - contribution 7.2Robustness and review uncertainty: 80/100
Robustness is 0/100: only 0/6 stress tests survive, so the recommendation is fragile. Review loop blocks the recommendation until failed gates or abstention rules clear.
Mitigation: Bookmaker price shortens: Refresh bookmaker odds and remove the pick if edge or EV is no longer positive.
high - timing - contribution 6.6Timing and freshness uncertainty: 82/100
Monitoring is expired; rerun the engine with a fresh fixture and market snapshot.
Mitigation: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value.
medium - memory - contribution 4.6Memory and calibration uncertainty: 58/100
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
Mitigation: Use settled comparable decisions to discount or confirm this pattern.
Decision impact: Downgrade or block public trust until data coverage uncertainty is addressed.
Decision boundary
Statusblocked
Nearest flipProbability floor: no measurable margin past the boundary.
Flip marginN/A
Next actionDo not show as public value; clear Probability floor and rerun.
Decision boundary is blocked; nearest flip is Probability floor: no measurable margin past the boundary.
probability floor - breachedProbability floor
Current N/A; threshold N/A; margin N/A. No priced candidate exists, so the probability floor is breached.
odds floor - breachedOdds floor
Current N/A; threshold N/A; margin N/A. No offered odds or posterior probability exists for a fair-odds floor.
edge floor - breachedNo-vig edge floor
Current N/A; threshold 0.0%; margin N/A. No priced candidate exists, so no-vig edge cannot clear the floor.
ev floor - breachedExpected-value floor
Current N/A; threshold 0.0%; margin N/A. No priced candidate exists, so expected value cannot clear the floor.
score floor - breachedDecision-score floor
Current -20/100; threshold 24/100; margin -44 pts. Decision score is -20/100; lean-value consideration starts at 24, while strong value starts at 42 with high confidence.
data quality floor - safeData-quality floor
Current 89/100; threshold 62/100; margin +27 pts. Model data quality is 89% and coverage audit score is 28/100; below 62/100 hard-blocks trust.
uncertainty ceiling - nearUncertainty ceiling
Current 63/100; threshold 66/100; margin +3 pts. Uncertainty score is 63/100; 66/100 or higher is high-risk unless mitigated.
context shock - breachedContext-shock tolerance
Current N/A; threshold 0.0%; margin N/A. No selected side exists, so context-shock tolerance is unavailable.
price shortening - breachedPrice-shortening room
Current N/A; threshold 3%; margin N/A. No market movement buffer exists without a priced candidate.
Must stay true: Load a priced candidate that clears positive no-vig edge and positive expected value. Raise decision score to at least 24 without triggering data-quality, live-model, learned-edge, or case-memory abstention gates. Connect enough provider data to keep model data quality at or above 62/100.
Flip triggers: Probability floor breached: No priced candidate exists, so the probability floor is breached. Odds floor breached: No offered odds or posterior probability exists for a fair-odds floor. No-vig edge floor breached: No priced candidate exists, so no-vig edge cannot clear the floor. Expected-value floor breached: No priced candidate exists, so expected value cannot clear the floor. Decision-score floor breached: Decision score is -20/100; lean-value consideration starts at 24, while strong value starts at 42 with high confidence. Context-shock tolerance breached: No selected side exists, so context-shock tolerance is unavailable. Price-shortening room breached: No market movement buffer exists without a priced candidate. Uncertainty ceiling is near the boundary: Uncertainty score is 63/100; 66/100 or higher is high-risk unless mitigated. Positive edge and EV required: The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds.
AI protocol
Statusblocked
Modedeterministic public audit
Questions answered2/7
Tool gaps3
AI protocol is blocked: 6 failed check(s), 1 triggered abstention gate(s), and current action avoid.
blocked - evidence probability-trace-summary, odds-intelligence-summaryIs there a measurable model-vs-market value edge?
No selection cleared positive edge and positive expected value.
Follow-up: Wait for a better price or stronger model-market disagreement.
blocked - evidence market-movement-summary, decision-boundary-summaryCan the current price survive normal market movement?
Market movement cannot be evaluated because no positive-value candidate is selected.
Follow-up: Refresh bookmaker markets and rerun value-edge ranking.
blocked - evidence decision-boundary-summaryWhat would flip this action?
Probability floor: no measurable margin past the boundary.
Follow-up: Do not show as public value; clear Probability floor and rerun.
needs data - evidence data-coverage-summary, uncertainty-summaryWhich data gaps could change the thesis?
Injuries: No provider-backed injury feed is connected.
Follow-up: Injuries: No provider-backed injury feed is connected.
blocked - evidence attribution-summary, uncertainty-summary, review-loop-summaryDo risk, actionability, or review checks block the decision?
Actionability is 31/100: block a public recommendation until failed gates are fixed. Review loop blocks the recommendation until failed gates or abstention rules clear.
Follow-up: Fresh odds must keep no-vig edge and expected value positive.
answered - evidence historical-discipline-summaryDoes historical backtest discipline allow this decision to be promoted?
No 10-year public historical evidence is attached to this decision run. Run the public historical evidence proof before using history to discipline raw model edges.
Follow-up: Keep historical discipline attached to the audit trail.
high priority - missing - Bookmaker odds providerRefresh bookmaker odds
Refresh bookmaker markets and rerun value-edge ranking.
Unlocks: Recalculates implied probability, no-vig edge, EV, boundary margins, and closing-line-value target.
high priority - missing - Sport-specific context providersFetch lineups, injuries, suspensions, and news
Injuries: No provider-backed injury feed is connected.
Unlocks: Reduces data/context uncertainty and reruns the actionability and review-loop gates.
medium priority - ready - Live score and event providerFetch live score and match events
Keep ready for in-play rechecks.
Unlocks: Updates live-state model inputs and hard in-play abstention gates.
medium priority - missing - Supabase training corpusLoad historical training profile
Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion.
Unlocks: Tunes learned minimum edge, data-quality weight, market-adjustment weight, and calibration thresholds.
medium priority - ready - Historical backtest corpusRun historical discipline retest
Attach public historical evidence or a persisted provider-backed learning profile.
Unlocks: Confirms whether provider-enriched historical results beat market consensus before any raw edge can be promoted.
Reviewer guardrails: Use only supplied evidence IDs and model artifacts. Do not invent injuries, lineups, weather, news, odds, scores, or private facts. Do not expose hidden chain-of-thought; return public audit notes only. Do not upgrade a local avoid or monitor action into a stronger recommendation. Downgrade or abstain when safety gates, boundary breaches, or unsupported material claims remain.
Reasoning graph
Statusblocked
Nodes13
Edges11
Watch nodes2
Reasoning graph is blocked: 9 blocker node(s), 2 watch node(s), and final action avoid.
objective - neutral - strength 100/100Decision objective
Decide whether Aluminij vs Sheriff Tiraspol can show No clear value found as a responsible value candidate.
model - blocking - strength 0/100Model probability
Probability trace is blocked because no priced selection passed the value guardrail.
Evidence: probability-trace-summary
market - blocking - strength 0/100Market value
Odds intelligence found no positive expected-value candidate after bookmaker-margin removal.
Evidence: odds-intelligence-summary, market-movement-summary
data - blocking - strength 28/100Data coverage
Data coverage is 28/100; too many required provider signals are missing for production trust.
Evidence: data-coverage-summary
uncertainty - blocking - strength 37/100Uncertainty budget
Diagnostic uncertainty risk is high at 63/100; primary uncertainty is Data coverage uncertainty.
Evidence: uncertainty-summary
boundary - blocking - strength 8/100Decision boundary
Decision boundary is blocked; nearest flip is Probability floor: no measurable margin past the boundary.
Evidence: decision-boundary-summary
review - blocking - strength 10/100Decision attribution
Attribution is blocked: Data coverage prevents a trusted public recommendation.
Evidence: attribution-summary
risk - blocking - strength 31/100Actionability guardrail
Actionability is 31/100: block a public recommendation until failed gates are fixed.
Evidence: review-loop-summary, attribution-summary
Strongest path: objective -> historical-discipline -> final-action.
Blocking path: objective -> model-probability -> market-value -> data-coverage -> uncertainty -> boundary -> final-action.
Tool orchestration
Statusneeds tools
Readiness49/100
Next taskhistorical-results
Stale after1 min
Tool orchestration needs tools: 4/12 task(s) ready, 4 high-priority config gap(s), next task Load team/player historical results, readiness 49/100.
critical priority - ready - fixturesLoad today's fixture
Provider: api-football. Depends on: none.
Aluminij vs Sheriff Tiraspol is loaded from api-football.
Decision impact: Without the fixture, the decision stays avoid and every downstream task is blocked.
high priority - missing config - historical resultsLoad team/player historical results
Provider: api-football-recent-fixtures-form-rating-v1 + league-strength-baseline-v1 + missing-player-history. Depends on: fixtures-today.
Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
Decision impact: Weak history keeps model strength, form weighting, and learned thresholds conservative.
high priority - missing config - standingsLoad league standings
Provider: missing-provider. Depends on: fixtures-today, historical-results.
Standings snapshots exist in the training schema but are not yet connected to live decisions.
Decision impact: Missing standings lower data quality and increase context uncertainty.
high priority - ready - recent formCompute recent form and home/away profile
Provider: deterministic-provider-proxy + deterministic-provider-proxy. Depends on: fixtures-today, historical-results.
Recent form and home/away features are ready for this model run.
Decision impact: If form or home/away inputs change, the model probability and value edge are recalculated.
high priority - missing config - injuriesFetch injuries, suspensions, lineups, and news
Provider: Sport-specific context providers. Depends on: fixtures-today.
Injuries: No provider-backed injury feed is connected.
Decision impact: Material team news can downgrade or flip the action before kickoff.
high priority - missing config - oddsRefresh bookmaker odds and no-vig probabilities
Provider: Bookmaker odds provider. Depends on: fixtures-today.
Refresh bookmaker markets and rerun value-edge ranking.
Decision impact: A price move can erase the edge, change the safer alternative, or move the pick to avoid.
medium priority - waiting - live scoresFetch live score and match events
Provider: Live score and event provider. Depends on: fixtures-today, odds-refresh.
Wait until kickoff or in-play mode before live score and event polling becomes active.
Decision impact: Live goals, cards, retirements, or tempo shocks can invalidate pre-match value.
medium priority - missing config - weatherFetch weather where relevant
Provider: missing-provider. Depends on: fixtures-today.
No weather provider is connected for outdoor totals/tempo markets.
Decision impact: Severe weather can move totals, BTTS, fatigue, or model uncertainty.
Blocking tasks: historical-results, standings-table, context-availability, odds-refresh.
Execution order: fixtures-today -> historical-results -> standings-table -> recent-form-home-away -> context-availability -> odds-refresh -> live-state-events -> weather-context -> historical-training -> historical-discipline -> decision-memory -> openai-review.
Tool execution audit
Statusblocked
Executed3/12
Blocked6
Skipped1
Tool execution audit is blocked: Load team/player historical results, Load league standings, Fetch injuries, suspensions, lineups, and news, Refresh bookmaker odds and no-vig probabilities must run before the current decision can be trusted.
critical priority - executed - api-footballLoad today's fixture - 1 record(s)
Load today's fixture executed from api-football with 1 observed record(s).
Outputs: fixture, kickoff, teams, league
high priority - blocked - api-football-recent-fixtures-form-rating-v1 + league-strength-baseline-v1 + missing-player-historyLoad team/player historical results - 9 record(s)
Load team/player historical results is blocked: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
Outputs: team-history, player-history, long-form
high priority - blocked - missing-providerLoad league standings - 0 record(s)
Load league standings is blocked: Standings snapshots exist in the training schema but are not yet connected to live decisions.
Outputs: league-standings, motivation-context
high priority - executed - deterministic-provider-proxy + deterministic-provider-proxyCompute recent form and home/away profile - 11 record(s)
Compute recent form and home/away profile executed from deterministic-provider-proxy + deterministic-provider-proxy with 11 observed record(s).
Outputs: recent-form, home-away-profile, team-strength
high priority - blocked - Sport-specific context providersFetch injuries, suspensions, lineups, and news - 0 record(s)
Fetch injuries, suspensions, lineups, and news is blocked: Injuries: No provider-backed injury feed is connected.
Outputs: injuries, suspensions, lineups, news
high priority - blocked - Bookmaker odds providerRefresh bookmaker odds and no-vig probabilities - 0 record(s)
Refresh bookmaker odds and no-vig probabilities is blocked: Refresh bookmaker markets and rerun value-edge ranking.
Outputs: raw-implied-probability, no-vig-probability, expected-value, value-edge
medium priority - waiting - Live score and event providerFetch live score and match events - 1 record(s)
Fetch live score and match events is waiting: Wait until kickoff or in-play mode before live score and event polling becomes active.
Outputs: live-score, match-events, in-play-state
medium priority - blocked - missing-providerFetch weather where relevant - 0 record(s)
Fetch weather where relevant is blocked: No weather provider is connected for outdoor totals/tempo markets.
Outputs: weather, wind-rain-temperature
Next run: Load team/player historical results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
Control policy
Statusblocked
Visibilityinternal only
Modeblocked
Primary blockervalue-selection
Control policy blocks public display: 10 blocker gate(s), primary blocker Value selection.
Directive: Block public display and collect the required evidence first.
Next best action: Wait for a stronger model-market edge before publishing a candidate.
model - blockValue selection
No selection cleared the value and expected-value filters.
Required: Wait for a stronger model-market edge before publishing a candidate.
market - blockMarket state
Market movement cannot be evaluated because no positive-value candidate is selected.
Required: Refresh bookmaker markets and rerun value-edge ranking.
data - blockData coverage
Data coverage is 28/100; too many required provider signals are missing for production trust.
Required: Injuries: No provider-backed injury feed is connected.
tools - blockTool execution
Tool execution audit is blocked: Load team/player historical results, Load league standings, Fetch injuries, suspensions, lineups, and news, Refresh bookmaker odds and no-vig probabilities must run before the current decision can be trusted. Tool orchestration needs tools: 4/12 task(s) ready, 4 high-priority config gap(s), next task Load team/player historical results, readiness 49/100.
Required: Load team/player historical results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
risk - blockDecision boundary
Decision boundary is blocked; nearest flip is Probability floor: no measurable margin past the boundary.
Required: Do not show as public value; clear Probability floor and rerun.
risk - passHistorical discipline
No 10-year public historical evidence is attached to this decision run. Run the public historical evidence proof before using history to discipline raw model edges.
ai-review - blockAI review
AI protocol is blocked: 6 failed check(s), 1 triggered abstention gate(s), and current action avoid.
Required: Refresh bookmaker markets and rerun value-edge ranking.
operator - blockReasoning graph
Reasoning graph is blocked: 9 blocker node(s), 2 watch node(s), and final action avoid.
Required: learning-memory
Allowed: persist blocked audit only; collect required data; rerun the decision engine
Forbidden: publish as value candidate; show as actionable; upgrade by AI review; invent missing data
Monitoring plan
Statusexpired
Prioritycritical
Cadence0 min
Next review11:28 AM
Monitoring is expired; rerun the engine with a fresh fixture and market snapshot.
critical priority - odds - due 11:28 AMRefresh bookmaker odds
No selection currently has positive expected value, so fresh prices may be the only path to a recommendation.
Action: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value.
critical priority - team news - due 11:28 AMInjury and suspension news
This missing signal can move the probability estimate or downgrade confidence before kickoff.
Action: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
critical priority - lineups - due 11:28 AMConfirmed lineups
This missing signal can move the probability estimate or downgrade confidence before kickoff.
Action: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
critical priority - calibration - due 11:28 AMPositive edge and EV required
The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds.
Action: Do not promote the decision until this abstention gate is cleared by fresh model, market, or provider evidence.
Stop when: Stop any recommendation until a selection shows positive no-vig edge and positive expected value. Invalidate if fresh odds create a positive no-vig edge with acceptable confidence. Invalidate if confirmed lineups, injuries, suspensions, weather, or live events materially oppose the current thesis. Invalidate if bookmaker prices move before the next refresh window. Invalidate or downgrade because case memory says discount. Stop while abstention gate remains active: Positive edge and EV required. Stop while calibration says abstain.
Escalate when: If two high-priority monitoring tasks remain unresolved at the next review, downgrade the action to monitor or avoid. If bookmaker movement removes the value edge, remove the recommendation and rerun the committee. If confirmed team news, weather, surface, or live-event data opposes the thesis, rerun the model before showing the pick. If committee disagreement remains after the next data refresh, keep the lower-risk action. Do not raise confidence from historical learning until the real-data profile is active.
Actionability audit
Statusblocked
Postureavoid recommendation
Score31/100
Failed gates5
Actionability is 31/100: block a public recommendation until failed gates are fixed.
fail - weight 18%Value edge and EV: 0/100
No selection passed positive-edge and expected-value filters.
Required: Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
fail - weight 14%Confidence and risk: 0/100
No candidate exists, so confidence and risk cannot support action.
Required: Keep as analysis-only watchlist unless confidence improves or risk falls.
pass - weight 12%Data quality: 89/100
Data quality is 89%.
warn - weight 10%Context coverage: 52/100
Missing signals: Injury and suspension news, Confirmed lineups, Weather check.
Required: Fetch the highest-priority missing context signals and rerun the decision.
fail - weight 12%Belief freshness: 24/100
Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes.
Required: Refresh odds, context, and model state before trusting this belief.
Blockers: Value edge and EV: No selection passed positive-edge and expected-value filters. Confidence and risk: No candidate exists, so confidence and risk cannot support action. Belief freshness: Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes. Committee arbitration: Decision committee recommends avoid with blocked consensus: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk. Monitoring state: Monitoring is expired; rerun the engine with a fresh fixture and market snapshot. Positive edge and EV required: The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds. Calibration: Decision should abstain or avoid until the blocking condition changes.
Before action: Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Keep as analysis-only watchlist unless confidence improves or risk falls. Fetch the highest-priority missing context signals and rerun the decision. Refresh odds, context, and model state before trusting this belief. Resolve committee disagreement and keep the lower-risk action. Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value. Keep memory neutral or discounted until stored outcomes support this pattern. Do not raise confidence from training until real historical data is active.
Treat the output as statistical analysis, not certainty. Do not use this audit as staking, bankroll, or financial advice. Refresh odds and context before relying on any displayed edge. Avoid acting when the monitoring plan is blocked, expired, or unresolved.
Review loop
Statusblocked
Recommended actionavoid
Score delta-28
Shiftslower/raise
Review loop blocks the recommendation until failed gates or abstention rules clear.
thesis builder - challenge - low confidenceNo value thesis survived the market guardrail.
Evidence: No market is currently a thesis worth recommending for Aluminij vs Sheriff Tiraspol. Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes.
Required: Wait for a positive-EV selection before forming a recommendation thesis.
red team - block - high confidenceRed team found 4 blocking issue(s).
Evidence: Value edge and EV: No selection passed positive-edge and expected-value filters. Confidence and risk: No candidate exists, so confidence and risk cannot support action. Belief freshness: Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes. Committee arbitration: Decision committee recommends avoid with blocked consensus: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk. Context coverage: Missing signals: Injury and suspension news, Confirmed lineups, Weather check.
Required: Value edge and EV: No selection passed positive-edge and expected-value filters.
data gap checker - repair - medium confidence3 missing signal(s) remain: Injury and suspension news, Confirmed lineups, Weather check.
Evidence: Monitoring is expired; rerun the engine with a fresh fixture and market snapshot. Refresh bookmaker odds: No selection currently has positive expected value, so fresh prices may be the only path to a recommendation. Injury and suspension news: This missing signal can move the probability estimate or downgrade confidence before kickoff. Confirmed lineups: This missing signal can move the probability estimate or downgrade confidence before kickoff.
Required: Fetch missing context, refresh probabilities, and rerun actionability.
repair planner - repair - medium confidenceRepair plan has 6 required check(s).
Evidence: Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Keep as analysis-only watchlist unless confidence improves or risk falls. Fetch the highest-priority missing context signals and rerun the decision. Refresh odds, context, and model state before trusting this belief. Refresh bookmaker odds: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value. Injury and suspension news: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
Required: Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
final reviewer - block - low confidenceFinal reviewer recommends avoid; review loop status is blocked.
Evidence: Actionability is 31/100: block a public recommendation until failed gates are fixed. Decision should abstain or avoid until the blocking condition changes. Risk shift: raise; confidence shift: lower.
Repairs: Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Keep as analysis-only watchlist unless confidence improves or risk falls. Fetch the highest-priority missing context signals and rerun the decision. Refresh odds, context, and model state before trusting this belief. Refresh bookmaker odds: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value. Injury and suspension news: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
Unresolved: Value edge and EV: No selection passed positive-edge and expected-value filters. Confidence and risk: No candidate exists, so confidence and risk cannot support action. Belief freshness: Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes. Committee arbitration: Decision committee recommends avoid with blocked consensus: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk. Context coverage: Missing signals: Injury and suspension news, Confirmed lineups, Weather check. Case memory: Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted. Historical learning profile: Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion. Missing signal: Injury and suspension news.
Release criteria: Fresh odds must keep no-vig edge and expected value positive. Belief state must be unexpired before the decision remains visible. Monitoring plan must be active or explicitly cleared. Actionability must stay actionable or the product should downgrade to watch/avoid. Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Keep as analysis-only watchlist unless confidence improves or risk falls. Fetch the highest-priority missing context signals and rerun the decision.
Robustness stress test
Statusfragile
Score0/100
Survival rate0%
Worst caseBookmaker price shortens
Robustness is 0/100: only 0/6 stress tests survive, so the recommendation is fragile.
breaks - shift -8.0%Bookmaker price shortens: avoid
Edge N/A; EV N/A. No candidate exists, so odds movement cannot rescue the decision without a fresh market.
Repair: Refresh bookmaker odds and remove the pick if edge or EV is no longer positive.
breaks - shift -5.4%Adverse team news or weather: avoid
Edge N/A; EV N/A. Stress applies unresolved context gaps: Injury and suspension news, Confirmed lineups, Weather check.
Repair: Fetch lineups, injuries, suspensions, weather, and news before keeping the same action.
breaks - shift -1.5%Data quality decays: avoid
Edge N/A; EV N/A. Data-quality stress reflects current data score 89% and provider uncertainty.
Repair: Improve provider coverage or downgrade confidence until real data fills the gap.
breaks - shift -7.0%Belief expires before refresh: avoid
Edge N/A; EV N/A. Monitoring state is expired; stale belief should reduce trust in the edge.
Repair: Rerun the belief state and monitoring plan before showing the candidate again.
breaks - shift -9.0%Review-loop repair pressure: avoid
Edge N/A; EV N/A. Review loop status is blocked; unresolved repairs should be priced into the decision.
Repair: Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
breaks - shift -16.0%Actionability downgrade: avoid
Edge N/A; EV N/A. Actionability status is blocked with score 31/100.
Repair: Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
Hedges: Both Teams To Score: BTTS Yes at model 56%. Goals: Over 2.5 Goals at model 51%. Goals: Under 2.5 Goals at model 49%.
Required rechecks: Bookmaker price shortens: Refresh bookmaker odds and remove the pick if edge or EV is no longer positive. Adverse team news or weather: Fetch lineups, injuries, suspensions, weather, and news before keeping the same action. Data quality decays: Improve provider coverage or downgrade confidence until real data fills the gap. Belief expires before refresh: Rerun the belief state and monitoring plan before showing the candidate again. Review-loop repair pressure: Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Actionability downgrade: Wait for fresh odds or a stronger model-market disagreement before showing a candidate. Refresh bookmaker odds: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value. Injury and suspension news: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
Evaluation plan
Statusno action
SettlementNo public pick
Model prob.N/A
Break-evenN/A
Quoted oddsN/A
Target CLVN/A
Evaluation plan records the abstention so future calibration can learn whether avoiding the market was correct.
pending - resultSettled match and market result
Store the final match result so no-pick decisions can still be audited.
optional - closing-oddsClosing odds snapshot
Closing odds are optional when the engine abstained.
pending - contextLate context resolution
Record whether monitoring tasks changed the thesis before kickoff: Refresh bookmaker odds, Injury and suspension news, Confirmed lineups.
required - calibrationCalibration outcome row
Link the settled outcome to this decision run so confidence, health, Brier score, ROI, and CLV can be measured.
Success: The abstention remains justified after final odds and context are known. No avoided market closes with a clear positive edge that the current model should have captured.
Failure: Final market data shows a positive expected-value pick that the agent missed. The abstention was caused by provider gaps that should be fixed before similar matches.
Learning questions: Did the no-action decision avoid a false positive? Which missing provider signal most limited the model? Would real historical thresholds have changed the abstention?
Post-match actions: Store the settled outcome through the decision outcome endpoint with the linked decision_run_id. Recompute calibration by confidence and decision health after settlement. Compare quoted odds with closing odds for closing-line value. Keep learned thresholds inactive until enough real historical fixtures and odds are imported.
Case memory
Statusready
Similar cases5
Adjustmentdiscount
Avg similarity96%
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
similarity 100% - avoid - stableNo clear value found
api-football:1557367; score 71; reliability 89/100; same value/no-value state, quality and reliability proximity
similarity 100% - avoid - fragileNo clear value found
api-football:1557367; score 71; reliability 89/100; same value/no-value state, quality and reliability proximity
similarity 93% - avoid - reviewNo clear value found
api-football:1581037; score -20; reliability 52/100; same value/no-value state, quality and reliability proximity
Learning profile
Training statusshadow only
Real fixtures6086/1000
Learned edge+3.5%
Backtest yield-5.3%
Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion.
Decision score
Score-20
Actionavoid
Confidencelow
Riskmedium
Agent stages
Fixture and market intake - warning68/100
Aluminij vs Sheriff Tiraspol; data quality 89%; missing signals 3.
Model integrity check - passed100/100
Model produced 1.24-1.48 expected goals and winner total 1.000.
Market edge search - failed24/100
No selection survived the value-edge search.
Risk and variance gate - failed35/100
No pick means the risk gate remains defensive.
Contradiction and abstention review - passed73/100
0 watch/conflict checks and 1 triggered abstention gates.
Final arbitration - failed30/100
Weighted decision score -20; the agent will abstain rather than invent a pick.
Decision committee
Consensusblocked
Final actionavoid
Consider votes0
Avoid votes4
Decision committee recommends avoid with blocked consensus: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk.
model advocate - abstain - votes avoidModel advocate
The model cannot advocate for a selection because no market cleared the positive-edge filter.
Challenge: Injury and suspension news: No live injury/suspension provider is connected yet. Confirmed lineups: Lineups are not available in the MVP mock provider.
Checks: Recompute probabilities after fresh odds and context updates.
market skeptic - abstain - votes avoidMarket skeptic
Market prices are currently stronger than the model edge.
Checks: Refresh bookmaker odds before surfacing a final edge.
context scout - neutral - votes monitorContext scout
Context is incomplete for Aluminij vs Sheriff Tiraspol; 3 missing signals remain.
Challenge: Injury and suspension news Confirmed lineups Weather check A moderate adverse injury, suspension, or lineup shock is applied to the selected side.
Checks: Check lineup, injury, suspension, weather, live-state, and news signals near start time.
risk manager - abstain - votes avoidRisk manager
Reliability is 51/100 with review health and abstain calibration action.
Challenge: Positive edge and EV required: The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds.
Checks: Honor triggered abstention gates before any public recommendation.
memory analyst - neutral - votes monitorMemory analyst
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
Challenge: Compared against 40 stored football decisions. Average similar-case reliability is 66/100.
Checks: Store this decision and settle outcomes so memory can learn from real results.
final arbiter - abstain - votes avoidFinal arbiter
review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk.
Challenge: Injury and suspension news Confirmed lineups Weather check
Checks: Remain avoid unless new evidence removes the active guardrail. Keep avoiding until a new market price creates a positive no-vig edge and positive EV.
Open disagreements: Context scout voted monitor: Context is incomplete for Aluminij vs Sheriff Tiraspol; 3 missing signals remain. Memory analyst voted monitor: Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
Agent deliberation
Primary thesisNo market is currently a thesis worth recommending for Aluminij vs Sheriff Tiraspol.
Dissenting thesisThe dissenting view is that better odds or provider-backed context may create value later, so the engine should keep monitoring.
Synthesisreview decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk.
rejected - low confidenceValue thesis
The engine found no positive-EV selection with acceptable confidence.
Impact: Does not survive guardrails as a public recommendation.
needs data - medium confidenceCounter-thesis: market may know more
Without a positive edge, market prices are currently stronger than the model signal.
Impact: Requires odds refresh before the recommendation can be trusted.
needs data - high confidenceContext-risk thesis
3 missing context signals remain, led by Injury and suspension news, Confirmed lineups, Weather check.
Impact: Controls whether the engine considers, monitors, or abstains after late provider data arrives.
rejected - medium confidenceFinal arbitration
Base case decision score is -20; calibration says abstain with 51/100 reliability.
Impact: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk.
contested - high confidenceCase-memory thesis
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
Impact: Memory discounts confidence.
What would change the decision
high priority - team newsInjury and suspension news
This missing signal can move the probability estimate or downgrade confidence before kickoff.
If confirmed: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
high priority - lineupsConfirmed lineups
This missing signal can move the probability estimate or downgrade confidence before kickoff.
If confirmed: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
medium priority - weatherWeather check
This missing signal can move the probability estimate or downgrade confidence before kickoff.
If confirmed: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
high priority - oddsFresh bookmaker price
A better price is required before any selection can become positive EV.
If confirmed: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and EV.
medium priority - trainingHistorical learning profile
Without enough real historical fixtures and odds, thresholds stay conservative defaults.
If confirmed: Import real fixtures and odds, run backtests, then activate learned thresholds only after the corpus is large enough.
high priority - trainingSimilar stored decisions
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
If confirmed: Discount confidence and require stronger fresh odds/context confirmation.
Bad-data path: Remain avoid unless new evidence removes the active guardrail. Market-move path: Keep avoiding until a new market price creates a positive no-vig edge and positive EV.
Context adjustment
Home shift0.0%
Away shift0.0%
Total shift0.0%
Signals0
Context layer reviewed 0 structured signals without moving probabilities.
Weighted factors
Value edge - score -35 - weight 0.32-11
No selection cleared the positive-edge guardrail.
Expected value - score -35 - weight 0.16-6
No selection cleared the positive-EV guardrail.
Confidence guardrail - score -25 - weight 0.2-5
No viable pick means confidence stays low.
Data quality - score 44 - weight 0.188
Data quality is 89%.
Outcome variance - score -20 - weight 0.14-3
No clear value creates no acceptable variance profile.
Missing context - score -8 - weight 0.1-1
Lineups, injury/suspension news, and weather are not connected yet.
Live state - score 0 - weight 0.060
Pre-match state avoids in-play recalibration risk.
Historical learning - score 0 - weight 00
Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion.
Case memory - score -24 - weight 0.07-2
Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
Historical discipline - score 0 - weight 00
Run the public historical evidence proof before using history to discipline raw model edges.
Self-critique checks
Probability normalization - clear
Home/draw/away probabilities sum to 1.000.
Confidence versus data quality - clear
Confidence is low with 89% data quality.
Recommendation versus missing context - clear
Missing context does not contradict the current action.
Risk versus action - clear
No selected pick; risk/action contradiction is not present.
Live state versus model - clear
Fixture is not live, so pre-match modeling is coherent.
Public reasoning trace
- Read fixture context, team strength, recent form, odds, and data quality.
- Audited data coverage: Data coverage is 28/100; too many required provider signals are missing for production trust.
- Simulated scorelines from expected goals: 1.24-1.48.
- Applied Dixon-Coles low-score correction with rho -0.0570 before deriving football winner, totals, BTTS, and scoreline probabilities.
- Context layer reviewed 0 structured signals without moving probabilities. Missing context still tracked: Confirmed lineups, Injury and suspension news, Weather check.
- Core model context signal: Provider football context xG: Poisson expected goals used deterministic team strength, form, and xG proxies because provider-backed football context was not attached..
- Market prior was not applied because no priced bookmaker market matched the model output.
- Compared model probabilities with no-vig market probabilities and EV; no positive edges were available.
- Ran odds intelligence: Odds intelligence found no positive expected-value candidate after bookmaker-margin removal.
- Audited market movement: Market movement cannot be evaluated because no positive-value candidate is selected.
- No pick selected because the guardrail rejected the market prices.
- Ran self-critique: 0 conflicts, 0 watch items, 1 triggered abstention gates.
- Calibrated reliability at 51/100 with review health and abstain action.
- Updated belief state: Belief is fragile: no selection is trusted yet; uncertainty 60/100, expires in 0 minutes.
- Fused probability evidence: Probability trace is blocked because no priced selection passed the value guardrail.
- Attributed decision drivers: Attribution is blocked: Data coverage prevents a trusted public recommendation.
- Decomposed uncertainty: Diagnostic uncertainty risk is high at 63/100; primary uncertainty is Data coverage uncertainty.
- Mapped decision boundaries: Decision boundary is blocked; nearest flip is Probability floor: no measurable margin past the boundary.
- Prepared AI protocol: AI protocol is blocked: 6 failed check(s), 1 triggered abstention gate(s), and current action avoid.
- Linked reasoning graph: Reasoning graph is blocked: 9 blocker node(s), 2 watch node(s), and final action avoid.
- Planned tool orchestration: Tool orchestration needs tools: 4/12 task(s) ready, 4 high-priority config gap(s), next task Load team/player historical results, readiness 49/100.
- Audited tool execution: Tool execution audit is blocked: Load team/player historical results, Load league standings, Fetch injuries, suspensions, lineups, and news, Refresh bookmaker odds and no-vig probabilities must run before the current decision can be trusted.
- Applied control policy: Control policy blocks public display: 10 blocker gate(s), primary blocker Value selection.
- Synthesized deliberation: review decision: abstain now; the guardrails or missing data make a public recommendation weaker than the risk.
- Ran decision committee: 0 consider, 2 monitor, 4 avoid; final action avoid with blocked consensus.
- Built monitoring plan: Monitoring is expired; rerun the engine with a fresh fixture and market snapshot.
- Audited actionability: Actionability is 31/100: block a public recommendation until failed gates are fixed.
- Ran review loop: Review loop blocks the recommendation until failed gates or abstention rules clear.
- Compiled research brief: Aluminij vs Sheriff Tiraspol is blocked from a public recommendation. Block public recommendation until failed gates, missing data, or invalid memory conditions are repaired.
- Opened decision notebook: Notebook is blocked: 3 falsifier or abstention condition(s) prevent public trust.
- Stress-tested robustness: Robustness is 0/100: only 0/6 stress tests survive, so the recommendation is fragile.
- Registered evaluation plan: Evaluation plan records the abstention so future calibration can learn whether avoiding the market was correct.
- Compared with stored case memory: Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
- Historical learning profile: shadow-only; Latest real-data backtest is available for shadow comparison only; live guardrails require an active model-bound calibration promotion.
- Applied historical discipline: No 10-year public historical evidence is attached to this decision run. Instruction: Run the public historical evidence proof before using history to discipline raw model edges.
- Checked missing context such as confirmed lineups, injuries, weather, and live events before final verdict.
Evidence reviewed
model - acceptable - neutralPoisson expected-goals model
Aluminij expected goals 1.24, Sheriff Tiraspol expected goals 1.48; top scoreline 1-1.
market - thin - neutralNo-vig market probability comparison
No market selection passed the positive-edge and confidence threshold.
form - acceptable - neutralRecent form signal
Aluminij: L-L-L-D; Sheriff Tiraspol: W-L-W-L-W.
data quality - strong - neutralData quality guardrail
Data quality is 89%; low quality downgrades confidence.
team news - missing - unknownInjury and suspension news
No live injury/suspension provider is connected yet.
lineups - missing - unknownConfirmed lineups
Lineups are not available in the MVP mock provider.
weather - missing - unknownWeather check
Weather is not connected yet; relevant for outdoor football totals and tempo.
model - thin - neutralCore model context adjustment
Provider football context xG: Poisson expected goals used deterministic team strength, form, and xG proxies because provider-backed football context was not attached.
Why to avoid forcing it
- No selection passed the positive value-edge and confidence threshold.
- Abstention gate triggered: Positive edge and EV required.
Safer alternatives to review
Both Teams To Score - medium riskBTTS Yes
Model 56% - fair odds 1.80
Goals - medium riskOver 2.5 Goals
Model 51% - fair odds 1.96
Goals - medium riskUnder 2.5 Goals
Model 49% - fair odds 2.05
Both Teams To Score - high riskBTTS No
Model 44% - fair odds 2.25
Risks and next checks
- Sports outcomes are uncertain; the decision engine is an analysis layer, not a guarantee.
- Bookmaker prices can move quickly, so stale odds can erase a calculated edge.
- Refresh bookmaker odds and recalculate no-vig market probabilities before showing a final value edge.
- Check injuries, suspensions, and confirmed lineups close to kickoff.
- Add weather for outdoor football totals and tempo-sensitive markets.
- Re-check after 11:28 AM; this belief expires in 0 minutes.
- Refresh bookmaker odds by 11:28 AM; No selection currently has positive expected value, so fresh prices may be the only path to a recommendation.
- Wait for fresh odds or a stronger model-market disagreement before showing a candidate.
- Keep as analysis-only watchlist unless confidence improves or risk falls.
- Refresh bookmaker odds: Recalculate implied probability, bookmaker margin, no-vig probability, value edge, and expected value.
- Injury and suspension news: Refresh the model, rerun the no-vig EV calculation, and re-check abstention gates.
- Refresh bookmaker odds: Complete this check, then rerun the decision engine before trusting the current posture.
- Injury and suspension news: Complete this check, then rerun the decision engine before trusting the current posture.
- No selection passed the value, EV, and confidence guardrails.
- Data coverage: Data coverage is 28/100; too many required provider signals are missing for production trust.
- Review loop: Review loop blocks the recommendation until failed gates or abstention rules clear.
- Injuries: No provider-backed injury feed is connected.
- Fetch or verify Injury and suspension news before raising confidence.
- Probability floor breached: No priced candidate exists, so the probability floor is breached.
- Odds floor breached: No offered odds or posterior probability exists for a fair-odds floor.
- Refresh bookmaker odds: Refresh bookmaker markets and rerun value-edge ranking.
- Fetch lineups, injuries, suspensions, and news: Injuries: No provider-backed injury feed is connected.
- Next tool task historical-results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
- Load team/player historical results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
- Control policy: Wait for a stronger model-market edge before publishing a candidate.
- Load team/player historical results: Historical evidence is incomplete. Aluminij: provider-backed via api-football-recent-fixtures-form-rating-v1 (4 matches); Sheriff Tiraspol: computed via league-strength-baseline-v1 (0 matches). Player history: missing; no leakage-safe player-performance form was attached.
- Load league standings: Standings snapshots exist in the training schema but are not yet connected to live decisions.
- Learning and memory: Case memory found 5 similar stored decisions with weak reliability or avoid pressure, so confidence is discounted.
- Tool and data requests: 3 missing tool/data request(s): Refresh bookmaker odds, Fetch lineups, injuries, suspensions, and news, Load historical training profile.
- No priced candidate is available; do not manufacture market movement intelligence.
- Fresh odds must keep no-vig edge and expected value positive.
- Belief state must be unexpired before the decision remains visible.
- Bookmaker price shortens: Refresh bookmaker odds and remove the pick if edge or EV is no longer positive.
- Adverse team news or weather: Fetch lineups, injuries, suspensions, weather, and news before keeping the same action.
- Injuries: No provider-backed injury feed is connected.
- Suspensions: No suspension provider is connected.
- Calibration outcome row: Link the settled outcome to this decision run so confidence, health, Brier score, ROI, and CLV can be measured.
- Import enough real historical fixtures and odds before learned thresholds tune live decisions.
- Attach public historical evidence or a persisted provider-backed learning profile.
- Keep learned thresholds and public picks locked until provider-enriched backtests pass.
- Backtest this market against historical closing odds before raising confidence in production.
Sensitivity checks
- Odds movement: requires review. A materially better price could create value, but the current market does not pass the guardrail.
- Team news: requires review. Confirmed absences, player fitness, or lineup surprises could change the projection enough to rerun the decision.
- Data quality: keeps verdict. More complete provider data is needed before raising confidence.
Scenario matrix
Base case - avoid-20 (+0)
Current model, odds, data-quality, and missing-context state.
Odds shorten by 5% - avoid-24 (-4)
A shorter price would remove or further weaken the edge.
Adverse team news - avoid-38 (-18)
A moderate adverse injury, suspension, or lineup shock is applied to the selected side.
Confirmed context supports model - avoid-17 (+3)
Lineups, injury/suspension news, and weather arrive and support the existing model signal.
Abstention gates
Positive edge and EV required - triggered
The agent refuses to force a pick when no market selection clears both the edge and positive-EV thresholds.
Data quality floor - clear
Data quality is 89%; below 62% the agent abstains.
High-variance edge - clear
No selection is available for variance review.
Live model requirement - clear
Pre-match fixture; in-play event model is not required yet.
Thin context around edge - clear
Missing context is noted but does not force abstention at the current edge/data-quality level.
Future fixture synthetic market - clear
Fixture has no future-season seed or synthetic market flag.
Learned minimum edge - clear
No real-data training profile is active; default minimum-edge guardrail is used.
Case memory abstention - clear
Case memory did not find enough similar stored pressure to force abstention.
Historical market-prior discipline - clear
No public historical discipline evidence is attached, so this gate stays neutral.
Prediction agent report
Verdict: no clear value
The agent does not see enough separation between OddsPadi probabilities and no-vig market probabilities for Aluminij vs Sheriff Tiraspol.
Reasons
- The strongest available edges do not meet the confidence threshold.
- Expected goals are 1.24 for Aluminij and 1.48 for Sheriff Tiraspol.
- Top scoreline estimate: 1-1.
Cautions
- Sports outcomes remain uncertain; this is statistical analysis only.
- Do not treat positive edge as a requirement to place a bet.
Model football-poisson-v3; data quality 89%.
Model mathematics
Home expected goals1.24
Away expected goals1.48
Total expected goals2.72
Winner probability sum1.000
Top projected scores
1-113%
0-19%
1-29%
2-18%
1-08%
Signals
- Home rating edge: -0.07 Positive values favor the home side before market comparison. Aluminij: api-football-recent-fixtures-form-rating-v1, 4 match sample; Sheriff Tiraspol: league-strength-baseline-v1, 0 match sample.
- Recent form edge: -0.526 Computed from W/D/L form with exponential recency weighting; the latest result carries the most weight.
- Expected goals total: 2.72 Derived from attack, defense, rating, registry home advantage (1.09), and league goal-rate assumptions.
- xG blend adjustment: 0 No provider xG inputs were available, so expected goals used rating, form, attack, defense, league rate, and home advantage only.
- Provider football context xG: 0 Poisson expected goals used deterministic team strength, form, and xG proxies because provider-backed football context was not attached.
- Data quality: 0.9 Lower data quality reduces confidence even when the edge is positive.
- Dixon-Coles rho: -0.057 Low-score dependence correction applied to 0-0, 1-0, 0-1, and 1-1 score cells before market probabilities are derived.
- Context side shift: 0 Context layer reviewed 0 structured signals without moving probabilities.
- Context total shift: 0 Positive values raise over/tempo markets; negative values lower them.
- Market prior weight: 0 No market prior was applied because no priced market matched the model output.
- Average bookmaker margin: 0 Bookmaker margin is removed before edge calculation and also discounts the market-prior blend.