{ "id": "classification-evaluate", "name": "Classification evaluation evidence", "description": "Evaluate up to 1,000 caller-supplied single-label expected/predicted pairs: confusion matrix, per-label precision/recall/F1/support, macro/weighted/micro summaries, balanced accuracy and mismatch evidence. Undefined per-label values use zero with explicit flags; labels are not verified ground truth.", "category": "data-assurance", "priceUsd": "0.01", "pricingStatus": "proposed-unverified", "pricing": { "unit": "one successful operation call", "proposedNominalUsd": "0.01", "sixDecimalTokenBaseUnits": "10000", "subscription": false, "includesPayerWalletOrNetworkFees": false, "liveQuoteVerified": false, "condition": "Actual SDK challenge is authoritative only within the caller's explicit authorization; configured six-decimal token peg is an operator assertion, not a conversion guarantee." }, "intents": [ "calculate confusion matrix precision recall f1 from evaluation labels", "score agent routing classification predictions against supplied labels", "inspect macro micro weighted metrics and error samples" ], "whenToUse": [ "calculate confusion matrix precision recall f1 from evaluation labels", "score agent routing classification predictions against supplied labels", "inspect macro micro weighted metrics and error samples" ], "whenNotToUse": [ "Train or execute a model or infer factual ground truth", "Multilabel classification probability calibration or deployment certification" ], "capabilities": [ "single-label classification metrics", "confusion matrix evidence", "undefined metric flags", "bounded mismatch samples" ], "related": [ "ranking-evaluate", "span-evaluate" ], "limits": { "inputBytes": 100000, "outputBytes": 400000, "jsonNodes": 12000, "depth": 20, "evidence": 200, "keyWorkBytes": 3000000, "matchingSteps": 2000000, "samples": 1000, "labels": 50 }, "errorCodes": [ "INPUT_LIMIT", "OUTPUT_LIMIT", "COMPLEXITY_LIMIT", "UNSAFE_KEY", "INVALID_NUMBER", "INVALID_POINTER", "DUPLICATE_ID", "DUPLICATE_FIELD", "INVALID_RULE", "KEY_WORK_LIMIT", "LABEL_LIMIT", "UNJUDGED_DOCUMENT", "INVALID_SPAN", "DUPLICATE_SPAN", "INVALID_UNICODE", "MATCHING_LIMIT", "INVALID_CADENCE", "INVALID_INTERVAL", "NUMERIC_OVERFLOW" ], "requirementsProfile": { "format": "declared-requirements-v1", "facts": { "execution.suppliedCode": false, "execution.remoteMutation": false, "execution.llmInference": false, "execution.paidMcp": false, "verification.semanticTruth": false, "verification.sourceAuthenticity": false, "verification.liveVulnerabilities": false, "numbers.arbitraryPrecisionJson": false, "numbers.model": "ieee754-binary64", "privacy.requestBodyPersisted": false, "execution.deterministic": true, "execution.networkAccess": false, "privacy.resultBodyPersisted": false, "payment.x402": true, "payment.mpp": true, "operation.id": "classification-evaluate", "operation.category": "data-assurance", "limit.httpRequestBytes": 131072, "limit.requestBytes": 100000, "limit.responseBytes": 524288, "limit.resultBytes": 400000, "limit.jsonDepth": 20, "limit.jsonNodes": 12000, "input.samples.maxItems": 1000, "input.labels.maxItems": 50 }, "unknownPolicy": "Undeclared requirements are unknown, never compatible. Matching declared facts does not establish semantic fit or input validity.", "preflight": "/preflight" }, "documentation": "/reference/tools/classification-evaluate.md", "serviceContract": "/reference/services/classification-evaluate.json", "errors": [ { "status": 400, "meaning": "Malformed JSON, missing/invalid idempotency key, or payment identifier mismatch", "retry": "Correct the request before payment" }, { "status": 402, "meaning": "Payment challenge or rejected payment", "retry": "Use official protocol SDK; inspect payment outcome before another payment" }, { "status": 409, "meaning": "Idempotency conflict, duplicate proof, or PAYMENT_UNCERTAIN", "retry": "Keep original key, body, and proof; reconcile uncertainty with operator; never blindly repay" }, { "status": 413, "meaning": "Input or generated output too large", "retry": "Reduce input; no payment attempted for validation failure" }, { "status": 415, "meaning": "Unsupported media type or compression", "retry": "Send uncompressed application/json" }, { "status": 422, "meaning": "Schema or service-specific semantic validation failure", "retry": "Correct input using returned error code; no payment attempted" }, { "status": 429, "meaning": "Request/payment-attempt rate exceeded", "retry": "Wait for rate limit window; preserve existing payment identity" }, { "status": 503, "meaning": "Payment configuration/provider/state unavailable, or live DNS preparation failed before settlement", "retry": "Check readiness; DNS preparation failures may retry the identical key/body/credential only; uncertainty requires reconciliation" } ], "numericPrecision": "JavaScript IEEE-754 numbers; use strings for large integer IDs/exact decimals where the schema accepts strings. No lossless numeric parsing.", "paymentWorkflow": { "discoveryOnly": false, "supportedProtocols": [ "x402", "mpp" ], "x402": { "credentialHeader": "PAYMENT-SIGNATURE", "challengeHeader": "PAYMENT-REQUIRED", "receiptHeader": "PAYMENT-RESPONSE", "version": 2, "scheme": "exact", "paymentIdentifier": "payment-identifier extension MUST equal the HTTP Idempotency-Key", "sdk": "@x402/core with @x402/evm" }, "mpp": { "supported": true, "credentialHeader": "Authorization", "challengeHeader": "WWW-Authenticate", "receiptHeader": "Payment-Receipt", "method": "tempo", "intent": "charge", "sdk": "mppx", "tokenDecimals": 6 }, "steps": [ "Check configured readiness and the exact service schema", "Generate a fresh random Idempotency-Key for this operation; never use a discovery probe fixture for purchases", "Send valid input without a credential to obtain the official protocol challenge", "Use the official SDK and authorized wallet to fulfill the challenge", "Retry only with identical key, body, protocol and credential", "On PAYMENT_UNCERTAIN stop and request operator reconciliation; never blindly pay again" ], "versionedRetries": "Request fingerprint includes service release version. Retries across a version upgrade can conflict; coordinate upgrades outside the 24-hour replay window and reconcile pending attempts.", "docs": "/llms.txt" }, "method": "POST", "paths": { "x402": "/v1/x402/classification-evaluate", "mpp": "/v1/mpp/classification-evaluate" }, "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "samples": { "maxItems": 1000, "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "minLength": 1, "maxLength": 80 }, "expected": { "type": "string", "minLength": 1, "maxLength": 80 }, "predicted": { "type": "string", "minLength": 1, "maxLength": 80 } }, "required": [ "id", "expected", "predicted" ], "additionalProperties": false } }, "labels": { "default": [], "maxItems": 50, "type": "array", "items": { "type": "string", "minLength": 1, "maxLength": 80 } } }, "required": [ "samples" ], "additionalProperties": false }, "outputSchema": { "type": "object", "required": [ "operation", "version", "result", "provenance" ], "properties": { "operation": { "const": "classification-evaluate", "type": "string" }, "version": { "const": "0.29.0", "type": "string" }, "result": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "profile": { "type": "string", "const": "single-label-evaluation-v1" }, "sampleCount": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "labels": { "type": "array", "items": { "type": "string" } }, "confusionMatrix": { "type": "array", "items": { "type": "array", "items": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 } } }, "perLabel": { "type": "array", "items": { "type": "object", "properties": { "precision": { "type": "number" }, "recall": { "type": "number" }, "f1": { "type": "number" }, "label": { "type": "string" }, "truePositive": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "falsePositive": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "falseNegative": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "support": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "predictedCount": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "precisionDefined": { "type": "boolean" }, "recallDefined": { "type": "boolean" }, "f1Defined": { "type": "boolean" } }, "required": [ "precision", "recall", "f1", "label", "truePositive", "falsePositive", "falseNegative", "support", "predictedCount", "precisionDefined", "recallDefined", "f1Defined" ], "additionalProperties": false } }, "accuracy": { "type": [ "number", "null" ] }, "balancedAccuracy": { "type": [ "number", "null" ] }, "macro": { "anyOf": [ { "type": "object", "properties": { "precision": { "type": "number" }, "recall": { "type": "number" }, "f1": { "type": "number" } }, "required": [ "precision", "recall", "f1" ], "additionalProperties": false }, { "type": "null" } ] }, "weighted": { "anyOf": [ { "type": "object", "properties": { "precision": { "type": "number" }, "recall": { "type": "number" }, "f1": { "type": "number" } }, "required": [ "precision", "recall", "f1" ], "additionalProperties": false }, { "type": "null" } ] }, "micro": { "anyOf": [ { "type": "object", "properties": { "precision": { "type": "number" }, "recall": { "type": "number" }, "f1": { "type": "number" } }, "required": [ "precision", "recall", "f1" ], "additionalProperties": false }, { "type": "null" } ] }, "mismatchCount": { "type": "integer", "minimum": 0, "maximum": 9007199254740991 }, "mismatches": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string" }, "expected": { "type": "string" }, "predicted": { "type": "string" } }, "required": [ "id", "expected", "predicted" ], "additionalProperties": false } }, "mismatchesTruncated": { "type": "boolean" }, "conventions": { "type": "array", "items": { "type": "string" } } }, "required": [ "profile", "sampleCount", "labels", "confusionMatrix", "perLabel", "accuracy", "balancedAccuracy", "macro", "weighted", "micro", "mismatchCount", "mismatches", "mismatchesTruncated", "conventions" ], "additionalProperties": false }, "provenance": { "type": "object", "required": [ "inputSha256", "outputSha256", "deterministic", "externalRequests" ], "properties": { "inputSha256": { "type": "string", "pattern": "^[a-f0-9]{64}$" }, "outputSha256": { "type": "string", "pattern": "^[a-f0-9]{64}$" }, "deterministic": { "const": true }, "externalRequests": { "const": 0 } } } }, "additionalProperties": false }, "exampleInput": { "samples": [ { "id": "e1", "expected": "answer", "predicted": "answer" }, { "id": "e2", "expected": "abstain", "predicted": "answer" }, { "id": "e3", "expected": "abstain", "predicted": "abstain" } ], "labels": [ "answer", "abstain" ] }, "exampleResponse": { "operation": "classification-evaluate", "version": "0.29.0", "result": { "profile": "single-label-evaluation-v1", "sampleCount": 3, "labels": [ "abstain", "answer" ], "confusionMatrix": [ [ 1, 1 ], [ 0, 1 ] ], "perLabel": [ { "precision": 1, "recall": 0.5, "f1": 0.6666666666666666, "label": "abstain", "truePositive": 1, "falsePositive": 0, "falseNegative": 1, "support": 2, "predictedCount": 1, "precisionDefined": true, "recallDefined": true, "f1Defined": true }, { "precision": 0.5, "recall": 1, "f1": 0.6666666666666666, "label": "answer", "truePositive": 1, "falsePositive": 1, "falseNegative": 0, "support": 1, "predictedCount": 2, "precisionDefined": true, "recallDefined": true, "f1Defined": true } ], "accuracy": 0.6666666666666666, "balancedAccuracy": 0.75, "macro": { "precision": 0.75, "recall": 0.75, "f1": 0.6666666666666666 }, "weighted": { "precision": 0.8333333333333334, "recall": 0.6666666666666666, "f1": 0.6666666666666666 }, "micro": { "precision": 0.6666666666666666, "recall": 0.6666666666666666, "f1": 0.6666666666666666 }, "mismatchCount": 1, "mismatches": [ { "id": "e2", "expected": "abstain", "predicted": "answer" } ], "mismatchesTruncated": false, "conventions": [ "Confusion matrix rows are expected labels and columns are predicted labels; labels use code-unit lexical order.", "Undefined per-label precision, recall or F1 is 0 with explicit defined flags. Macro includes all declared and observed labels; weighted uses expected support; balanced accuracy includes only supported labels.", "Supplied expectations are not verified. No training, probability calibration, multilabel matching or inference about deployment quality." ] }, "provenance": { "inputSha256": "94e0ebdf6418835b5e24379c85e0dcf742165925f5cc787097b124279db65c32", "outputSha256": "96304c42a7fa68f16782023dec0075af56722a1a75d391c578fcedb286492dc3", "deterministic": true, "externalRequests": 0 } }, "requiredHeaders": { "Content-Type": "application/json", "Idempotency-Key": "random 16–128 character operation identifier" }, "fixedExample": "/reference/examples/classification-evaluate.json", "execution": { "deterministic": true, "externalRequests": 0, "maxExternalRequests": 0, "resultSnapshotPersisted": false, "fixedExampleIsIllustrativeSnapshot": false, "requiresPayment": true, "supportsMcpExecution": false }, "releaseSnapshot": { "format": "static-release-reference-v1", "sourceVersion": "0.29.0", "sourceRegistrySha256": "a2b5ec09bf6c38b9d2879d746a4fded374f5928b445377b0270ef6aa8e6cac65", "generatedAt": "2026-10-06T15:38:00Z", "releaseAcceptance": "not-verified-by-generator", "runtimeReadiness": "not-evaluated", "livePaymentsVerified": false, "indexingVerified": false, "apiOrigin": null, "notice": "Build-time release reference. Runtime readiness, deployment, payment settlement and external indexing are not evaluated here. Prices are proposed; this file cannot authorize execution or payment." } }