{"uid":"cap_8jDp_qO30ALKx5FR2EZo1","slug":"prediction-result-imports-column-statistics-4717a703","name":"Prediction Result Imports — Column Statistics","description":"Prediction result imports — Column statistics: Column statistics for Prediction result imports. Validate a declared CSV table contract, up to 1000 rows. Quoted cells supported; no external enrichment. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one CSV column statistics report.","url":"https://market.datapackvibe.com/x402/assistant-bx-csv-predictions-column-stats?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"csv":{"type":"string","default":"prediction_id,predicted_on,model_id,probability,latency_ms\nrecord-a,2026-01-01,group-a,10,2\nrecord-b,2026-01-02,group-b,20,3","maxLength":100000,"minLength":1},"maximum":{"type":"number","default":1000000000000,"maximum":1000000000000,"minimum":-1000000000000},"minimum":{"type":"number","default":-1000000000000,"maximum":1000000000000,"minimum":-1000000000000},"delimiter":{"enum":[",",";","\t"],"type":"string","default":","},"max_cell_length":{"type":"integer","default":1000,"maximum":5000,"minimum":1},"allowed_categories":{"type":"array","items":{"type":"string","default":"","maxLength":100,"minLength":1},"default":["group-a","group-b"],"maxItems":100,"minItems":0}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_cYdiPA0nh_pyNSBcadz_v","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Computes per-column statistics for a CSV of prediction result records, validating up to 1000 rows against a declared schema contract.","exampleAgentPrompt":"Can you run column statistics on this predictions CSV — it has columns prediction_id, predicted_on, model_id, probability, and latency_ms — and validate that probability values are between 0 and 100, latency_ms between 0 and 50000, and that model_id only contains 'group-a' or 'group-b'?","exampleUseCases":[{"title":"Validate ML model output before ingestion","prompt":"I've got a CSV of predictions from our classifier with columns prediction_id, predicted_on, model_id, probability, and latency_ms. Can you compute column statistics and check that probability stays between 0 and 1, latency_ms is between 0 and 10000, and model_id is only ever 'model-v1' or 'model-v2'?"},{"title":"Audit prediction import for data quality","prompt":"Before I import this batch of 800 prediction records into our data warehouse, can you run a column stats report on the CSV to see if any cells are malformed, out of range, or contain unexpected categories? The delimiter is a semicolon and max cell length should be 500."},{"title":"Spot-check new model predictions distribution","prompt":"We just got a fresh export of predictions from a new model — tab-delimited CSV with probability scores and latency values. Can you summarize the column statistics and flag anything where probability is outside 0 to 1 or latency_ms exceeds 5000?"}],"resultDescription":"Returns a per-column statistics report for the submitted CSV, including data type inference, value distribution metrics (min, max, mean, etc.), category conformance against the allowed list, and validation flags for cells that violate declared bounds or exceed max cell length.","failureModes":["CSV exceeds 100,000 character limit — request rejected","More than 1000 rows submitted — only first 1000 may be processed","Delimiter mismatch causes single-column parse — statistics meaningless","Allowed categories list exceeds 100 items — schema validation error","Cell length exceeds max_cell_length — flagged as violation","Malformed CSV (unclosed quotes, inconsistent columns) — parse error returned"],"whenToPreferThis":"Use this endpoint when you need fast, structured per-column statistical analysis and schema validation for prediction result CSVs specifically — especially when you need to enforce value bounds and category allowlists on model output imports before downstream ingestion. Prefer it over generic CSV tools when working within the x402 micropayment ecosystem at low cost ($0.01/call) and when your dataset fits within 1000 rows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T18:47:59.692Z","isFirstParty":false,"canonicalSlug":"prediction-result-imports-column-statistics-4717a703"}