Data x402 offerings

Scores JSONL rows using fixed rules and adds _quality. Detects some PII and bad-word patterns; optional redaction and score filtering. Detection is incomplete and can produce false positives. No AI.

Problem: Compare these bounded estimator outputs against the supplied reference and objective rules. Input: JSON with reference, estimators, rules. Result: per-estimator metrics, rule verdicts, deterministic selected estimator or.... Limits: Software/model evidence only; 65536 request bytes; 5 s execution.

Problem: Validate timestamps, ordering, rates, gaps, and synchronization in this bounded trajectory or sensor trace. Input: JSON with clock id, samples, rules. Result: pass or fail verdict, normalized timeline, exact timing defects. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.

Fetch an RSS 2.0, Atom, or RSS 1.0 feed URL and parse it into normalized JSON: feed title/description/link plus items (title, link, id, published, author, plain-text summary, categories). Deterministic pure-XML parse with a lenient recovery pass for common malformations (reported in a warnings array). Item count is bounded (default 20, max 50). SSRF-guarded.

Run a read-only SQL query (SELECT/WITH, WHERE, GROUP BY, ORDER BY, window functions...) over a CSV loaded as table «datos» in a temporary in-memory SQLite database, and get the rows as JSON.

CSV to JSON converter - parses quoted CSV with a chosen delimiter and header row into an array of objects

Descriptive statistics for a list of numbers - mean, median, mode, standard deviation, quartiles and percentiles

Ingest external data with provenance - license, fetch evidence, parsing and quality gates

Data cleanup and schema mapping - target dataset, mapping spec, reject file and quality report

Entity resolution and deduplication - exact vs probabilistic matching, explainable merges and unmerge

Marketplace product feed cleanup - IDs, titles, categories, prices and per-channel validation with rejects

Document parsing and OCR quality - native text vs OCR, layout, confidence and visual review

Lead list quality audit - completeness, uniqueness, provenance, freshness and consent status

Refugee statistics by country (UNHCR) - refugees, asylum seekers, displaced and stateless people, with top host and origin countries

Time interval merger — sort, deduplicate, and combine overlapping or adjacent RFC 3339 date-time ranges.

Normalize an agent payload to a PHION service schema without changing payment-critical values; return a signed repair receipt

XML tier (deterministic, no LLM): verifies a claimed value lives at a named path in a public XML document, by independent double re-fetch. Use it for feeds and sitemaps; for JSON use /verify-json, for HTML use /verify. Paths address elements and @attributes (urlset.url[0].loc). String-exact; ambiguous or volatile values return unverifiable, never a guess. First 100 checks per client are free: resend with header X-Use-Free-Allowance: yes and no payment to use them.

Reconcile an agent session payment export. Match up to 64 supplied settlement rows and 64 delivery receipts, flag missing or contradictory records and reused transaction references, and total unique settlements exactly. Does not fetch the chain or prove the buyer received an API result. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.

Coerces messy text (key=value lines, CSV-ish, sentences) into clean JSON.

Extracts named entities (people, companies, places) from text. Wikidata resolution next iteration.

Validates JSON, detects PII inside values, reports schema stats. Pipeline agents use this as a data-quality gate.

Validates JSON, detects PII inside values, reports schema stats. Pipeline agents use this as a data-quality gate.

Coerces messy text (key=value lines, CSV-ish, sentences) into clean JSON.

Sigma STRATEGY_EVIDENCE: read persisted governed evidence for one research strategy.