{"resourceId":"nrcd-xc-schedule-ml-null-2026","versions":[{"version":"external-81b9e26520512027f8a298102de9500aa989c2f3031b5f8b3980fbd07620670b","resource":{"id":"nrcd-xc-schedule-ml-null-2026","title":"NRCD study: collegiate XC ML fails individual improvement forecasts; team race volume still associates with placement","organization":"University of Notre Dame / University of Virginia / National Running Club Database","sector":"College athletics / cross country scheduling analytics","geography":"United States (collegiate club / NIRCA; transfer caution to NCAA varsity)","publishedAt":"September 15, 2026 (arXiv v6); analysis of 2023–2025 seasons","publicationDate":"2026-09-15","eventDate":null,"sourceName":"arXiv (cs.CY / cs.LG)","sourceLabel":"Academic research — leakage-controlled collegiate running analytics","sourceUrl":"https://arxiv.org/abs/2509.10600","evidenceClass":"academic-research","outcomeClass":"cautionary","topics":["knowledge-work","operating-model","infrastructure","data-security"],"finding":"Using 23,360 comprehensive-era NRCD club cross-country results (7,056 athletes, 2023–2025), leakage-controlled temporal validation shows race-result features do not support out-of-year forecasting of individual improvement (best men’s R²=0.044; women’s −0.018), near a low reliability ceiling (~0.23–0.28). Converted Only times overstate mean first-to-last gains by 15–21 seconds versus weather/elevation Standardized times. Separately, team race frequency associates with nationals placement (pooled RR=2.09; OR=2.56 per SD), but within-team year-to-year schedule changes do not predict placement change and depth signals entangle with club size. Authors advise cautious transfer to NCAA/NAIA/NJCAA varsity contexts.","sledRelevance":"Newly relevant for fall 2026 XC scheduling and for athletic departments buying “athlete progression AI” pitched on results history alone: a large public collegiate dataset with honest null individual prediction—contrasts vendor accuracy headlines and complements archived injury-AUC papers that warn overall accuracy can hide weak classes.","evidence":"arXiv abs and HTML v6 (2509.10600): abstract metrics, Table 4 held-out R², weather-inflation 15–21 s, pooled RR/OR team results, discussion on varsity transfer limits, IRB non-human-subjects note.","architectureImplications":"Interpretation: if building XC analytics, standardize environmentally adjusted times before modeling; evaluate with temporal holdout and leakage audits; do not ship athlete-level improvement scores from finish history alone.","governanceImplications":"Interpretation: present team-level schedule associations as observational hypotheses for coaches, not causal mandates to maximize race count; require health oversight before changing athlete race loads.","securityPrivacyImplications":"Interpretation: NRCD export is de-identified public data—campus deployments using identifiable student-athlete results need ordinary FERPA/athletics access controls even when methods transfer.","caveats":"Club not varsity sample; observational team findings; no training logs/wearables; finish times omit injury/tactics; reliability ceiling approximates ≥4-race subgroup.","streamIds":["college-athletics"],"roles":{"sales":"Open with coaches who want AI to pick which runners will improve—this paper’s leakage-controlled answer is essentially no from race results alone. Sell environmental standardization and schedule-experiment design, not individual prophecy. Stakeholders are XC coaches, sports science, and compliance/health. Bound value to better questions about team race opportunity and weather-adjusted comparisons. Unsupported: guaranteeing nationals placement by adding meets, or treating club NIRCA coefficients as NCAA gospel.","engineering":"Fit is research-grade evaluation of collegiate endurance analytics pipelines. Integrate Standardized (weather/elevation) time transforms, temporal train/test by season, and explicit leakage exclusions (no last_time in features). Prerequisites: multi-season results with course/weather metadata. Constraints: club population; weak individual R². Security: identifiable campus athlete results need role-based access even if methods mirror public NRCD. Proof: held-out R²/SER, calibration, and documented leakage audits before any athlete-facing score.","delivery":"Delivery work is a methods review with the XC staff: replicate Standardized vs Converted Only gaps on local data, forbid athlete-level improvement scores without positive temporal skill, and design prospective schedule pilots with sports medicine. Ownership: head XC coach for schedule; sports science for metrics. Skills: coaches learn weather inflation; analysts learn leakage control. Governance: health sign-off on race-load changes; written “no individual forecast” rule. Risks: over-racing from team RR headlines; mis-transfer from club to varsity."},"roleDetails":{"sales":{"customerProblem":"XC staff want predictive tools for who will improve and how to schedule meets, but results-only models may look smart while failing true forecasts.","stakeholders":["Head XC coach","Sports performance/science","Athletics analytics","Sports medicine","FAR/compliance"],"discoveryQuestions":["Do current dashboards use weather-adjusted or raw/converted times?","Have any vendor models been tested with next-season holdout?","Who approves changes to athlete race frequency?","Is the population varsity NCAA, club, or mixed?"],"valueHypothesis":"If local pipelines adopt Standardized times and leakage-controlled evaluation, departments can avoid false confidence in individual progression scores while still studying team schedule structure carefully.","potentialEngagement":"Three-week methods workshop: replicate weather-inflation checks on two seasons of campus XC results and document whether any athlete-level model beats a null baseline out of year.","unsupportedClaims":["That increasing every athlete to 4+ races causes better nationals placement","That club NRCD coefficients apply unchanged to NCAA varsity","Positive individual forecasting skill from finish times alone"]},"engineering":{"fit":"Evaluation harness and time-standardization layer for collegiate endurance analytics—not a turnkey improvement predictor.","architectureIntegration":"Ingest results with course/weather fields; compute Standardized times; train/test by season year; block endpoint leakage features; report R², SER, and reliability ceilings.","prerequisites":["Multi-season results with high weather/course coverage","Clear athlete–season unit definition","Agreement that null results are publishable internally"],"constraints":["Source population is collegiate club XC","Individual held-out R² near zero","Team associations are between-program and size-entangled"],"security":"Tokenize or restrict identifiable student-athlete performance exports; no public redistribution of campus PII.","proofOfValue":["Temporal held-out R² with confidence intervals","Leakage add-back audit table","Documented Converted vs Standardized inflation on local data"]},"delivery":{"work":"Local replication notebook, coach-facing brief on null individual forecasts, and optional prospective schedule pilot design with medical oversight.","dependencies":["Results warehouse access","Sports medicine review for load changes","Coach willingness to treat nulls as findings"],"ownership":"Sports science owns metrics validation; head coach owns schedule decisions.","skillsAdoption":"Analysts practice leakage-controlled CV; coaches interpret weather-adjusted times.","governanceCheckpoints":["No athlete-facing improvement score without positive temporal skill","Medical sign-off before race-frequency experiments","Written varsity-transfer caveats"],"acceptanceCriteria":["Replication memo with held-out metrics","Coach briefing delivered","Pilot protocol filed if schedule changes proceed"],"risks":["Misreading team RR as causal within-team advice","Over-racing injury risk","Vendor models that skip leakage audits"]}},"retrievedAt":"2026-09-22T03:10:50Z","enrichedAt":"2026-09-22T03:15:28Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Interpretation: publish null results internally so less-resourced programs are not shamed into buying weak individual-forecast tools.","procurementImplications":"Interpretation: require temporal holdout and leakage audits in XC/analytics RFPs; reject results-only improvement guarantees.","operatingModelImplications":"Interpretation: separate research evaluation from coach decision rights; schedule changes remain human-owned with health constraints.","sourceVerification":{"openedUrl":"https://arxiv.org/abs/2509.10600","referenceExcerpt":"race-result features do not support out-of-year forecasting of individual improvement","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}