{"slug":"hubvibe-io-com-work-data-anomalies-3a6c9d","title":"Detect anomalies in a target table's time series against a history table, using ","host":"hubvibe-io.com","method":"POST","resource":"https://hubvibe-io.com/work/data/anomalies","category":"other","description":"Detect anomalies in a target table's time series against a history table, using AI.DETECT_ANOMALIES (TimesFM). Both tables share the same timestamp and value column names.","price_listed":10.0,"price_asked":10.0,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":857,"reported_calls_30d":2,"reported_payers_30d":1,"networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"data_col":"example","history_table":"example","target_table":"example","timestamp_col":"example"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"anomaly_prob_threshold":{"description":"0.5-0.999, default 0.95.","type":"number"},"data_col":{"type":"string"},"history_table":{"description":"project.dataset.table","type":"string"},"id_cols":{"description":"Optional: one series per value of these columns.","items":{"type":"string"},"type":"array"},"max_scan_gib":{"type":"number"},"target_table":{"description":"project.dataset.table","type":"string"},"timestamp_col":{"type":"string"}},"required":["history_table","target_table","timestamp_col","data_col"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"$schema":"https://json-schema.org/draft/2020-12/schema","description":"The 200 body of every paid /work call. `result` is the worker's own output (its schema is per route); everything else is the same on all 38 routes. A receipt for the job is at `receipt_url`.","properties":{"billing_warning":{"description":"Present only when the charge was recorded with a caveat.","examples":["settlement pending"],"type":"string"},"price_usd":{"description":"What this call cost, in USD.","examples":[0.02],"type":"number"},"provenance":{"description":"How the result was produced: which providers ran and how long each took.","properties":{"attempts":{"description":"Provider attempts made, including retries and failovers.","examples":[1],"type":"integer"},"elapsed_ms":{"description":"Wall-clock milliseconds for the whole job.","examples":[340],"type":"integer"},"providers_used":{"description":"Providers that served the job.","examples":[["coinbase-advanced-trade-public"]],"items":{"description":"Provider name.","examples":["coinbase-advanced-trade-public"],"type":"string"},"type":"array"},"steps":{"description":"Every step the job ran, in order.","items":{"description":"One step of the job.","properties":{"ms":{"description":"Milliseconds the step took.","examples":[312],"type":"integer"},"ok":{"description":"Whether the step succeeded.","examples":[true],"type":"boolean"},"provider":{"description":"Provider that served the step.","examples":["coinbase-advanced-trade-public"],"type":"string"},"reason":{"description":"Failure reason, on a failed step.","examples":["provider_timeout"],"type":"string"},"step":{"description":"Step name inside the worker.","examples":["quote"],"type":"string"}},"required":["step","ok","ms"],"type":"object"},"type":"array"}},"required":["steps","providers_used","attempts","elapsed_ms"],"type":"object"},"receipt_id":{"description":"Receipt id for this job.","examples":["rcpt_9f1c2b3a4d5e6f70"],"type":"string"},"receipt_url":{"description":"Where to fetch the machine-readable receipt (free, no payment).","examples":["/work/receipts/rcpt_9f1c2b3a4d5e6f70"],"type":"string"},"result":{"properties":{"anomaly_prob_threshold":{"description":"Probability threshold used.","examples":[0.95],"type":"number"},"columns":{"description":"AI.DETECT_ANOMALIES output columns.","examples":[["state_name","date","confirmed_cases","is_anomaly","lower_bound","upper_bound","anomaly_probability"]],"items":{"description":"AI.DETECT_ANOMALIES output column.","examples":["is_anomaly"],"type":"string"},"type":"array"},"data_col":{"description":"Value column.","examples":["confirmed_cases"],"type":"string"},"gib_processed":{"description":"Gibibytes BigQuery scanned; the metered cost basis.","examples":[0.012],"type":"number"},"history_table":{"description":"Table the forecast is fitted on.","examples":["bigquery-public-data.covid19_nyt.us_states"],"type":"string"},"row_count":{"description":"Rows returned.","examples":[10],"type":"integer"},"rows":{"description":"Checked rows with their anomaly flag.","examples":[[{"anomaly_probability":"0.12","confirmed_cases":"8631000","date":"2023-03-20","is_anomaly":"false","state_name":"Texas"}]],"items":{"additionalProperties":true,"description":"One checked point.","examples":[{"anomaly_probability":"0.12","confirmed_cases":"8631000","date":"2023-03-20","is_anomaly":"false","state_name":"Texas"}],"properties":{},"required":[],"type":"object"},"type":"array"},"target_table":{"description":"Table checked for anomalies.","examples":["bigquery-public-data.covid19_nyt.us_states"],"type":"string"},"timestamp_col":{"description":"Timestamp column.","examples":["date"],"type":"string"}},"required":["history_table","target_table","timestamp_col","data_col","anomaly_prob_threshold","columns","rows","row_count","gib_processed"],"type":"object"},"status":{"const":"ok","description":"Present only on a delivered result.","type":"string"},"worker":{"description":"Catalog name of the worker that ran.","examples":["market.quote"],"type":"string"}},"required":["status","worker","price_usd","result","provenance","receipt_id","receipt_url"],"title":"data.anomalies response","type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":10.0,"price_match":true,"latency_ms":857,"error":null}],"description_full":"Detect anomalies in a target table's time series against a history table, using AI.DETECT_ANOMALIES (TimesFM). Both tables share the same timestamp and value column names.","last_updated":"2026-09-23T14:03:51.501Z","schemes":["exact"]}