{ "openapi": "3.0.1", "info": { "title": "AI Benchmark Claim Normalizer", "description": "Normalize structured AI benchmark claims and produce evidence-backed comparability refusals when versions, splits, metrics, prompts, shots, or model settings do not align.", "version": "0.1", "x-build-id": "1ZnXYjFS6Zpjy8xxu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flintglade~ai-benchmark-claim-normalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flintglade-ai-benchmark-claim-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flintglade~ai-benchmark-claim-normalizer/runs": { "post": { "operationId": "runs-sync-flintglade-ai-benchmark-claim-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flintglade~ai-benchmark-claim-normalizer/run-sync": { "post": { "operationId": "run-sync-flintglade-ai-benchmark-claim-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "claims" ], "properties": { "inputSchemaVersion": { "title": "Input schema version", "minimum": 1, "maximum": 1, "type": "integer", "description": "Versioned runtime input contract.", "default": 1 }, "claims": { "title": "Structured benchmark claims", "minItems": 1, "maxItems": 1000, "type": "array", "description": "Each claim must identify its evidence source, model, benchmark, and reported metric. Values remain strings so Decimal precision and operators are preserved.", "items": { "type": "object", "properties": { "claimId": { "title": "Claim ID", "description": "Unique ID used by comparison groups.", "type": "string", "minLength": 1, "maxLength": 300 }, "source": { "title": "Evidence source", "description": "User-supplied evidence URL and record locator; the URL is not fetched.", "type": "object", "properties": { "url": { "title": "Evidence URL", "description": "HTTP(S) locator with no embedded credentials.", "type": "string", "maxLength": 2048 }, "locator": { "title": "Evidence locator", "description": "Section, row, or fragment label in the source evidence.", "type": "string", "minLength": 1, "maxLength": 1000 } }, "required": [ "url", "locator" ] }, "model": { "title": "Model", "description": "Reported model identity and comparison-relevant configuration.", "type": "object", "properties": { "name": { "title": "Model name", "description": "Raw reported model name; different models may be compared.", "type": "string", "minLength": 1, "maxLength": 300 }, "revision": { "title": "Model revision", "description": "Optional model revision preserved as evidence.", "type": "string", "maxLength": 300 }, "precision": { "title": "Precision", "description": "Reported numeric precision such as fp16.", "type": "string", "maxLength": 100 }, "quantization": { "title": "Quantization", "description": "Reported quantization setting such as none or int8.", "type": "string", "maxLength": 100 }, "contextLength": { "title": "Context length", "description": "Reported model context length.", "type": "integer", "minimum": 1, "maximum": 100000000 } }, "required": [ "name" ] }, "benchmark": { "title": "Benchmark", "description": "Benchmark, dataset, version, and split reported by the source.", "type": "object", "properties": { "name": { "title": "Benchmark name", "description": "Raw benchmark name subject only to exact aliases.", "type": "string", "minLength": 1, "maxLength": 300 }, "dataset": { "title": "Dataset", "description": "Optional explicit dataset name.", "type": "string", "maxLength": 300 }, "version": { "title": "Benchmark version", "description": "Comparison-critical benchmark version.", "type": "string", "maxLength": 200 }, "datasetVersion": { "title": "Dataset version", "description": "Optional dataset release or revision.", "type": "string", "maxLength": 200 }, "split": { "title": "Dataset split", "description": "Comparison-critical split such as test or validation.", "type": "string", "maxLength": 100 } }, "required": [ "name" ] }, "metric": { "title": "Metric", "description": "Reported metric semantics and Decimal-preserving value.", "type": "object", "properties": { "name": { "title": "Metric name", "description": "Raw metric name subject only to exact aliases.", "type": "string", "minLength": 1, "maxLength": 300 }, "value": { "title": "Reported value", "description": "Finite decimal string with an optional comparison operator.", "type": "string", "minLength": 1, "maxLength": 200 }, "unit": { "title": "Metric unit", "description": "Reported unit; conversions require an explicit registry rule.", "type": "string", "maxLength": 100 }, "direction": { "title": "Metric direction", "description": "Whether higher or lower reported values are better.", "type": "string", "enum": [ "higher_is_better", "lower_is_better" ] }, "confidenceInterval": { "title": "Confidence interval", "description": "Optional ordered closed interval preserved as Decimal strings.", "type": "object", "additionalProperties": false, "properties": { "lower": { "title": "Lower bound", "description": "Finite Decimal lower bound.", "type": "string", "minLength": 1, "maxLength": 200 }, "upper": { "title": "Upper bound", "description": "Finite Decimal upper bound.", "type": "string", "minLength": 1, "maxLength": 200 }, "level": { "title": "Confidence level", "description": "Reported confidence level label.", "type": "string", "maxLength": 100 } }, "required": [ "lower", "upper" ] }, "uncertainty": { "title": "Reported uncertainty", "description": "Optional source-provided uncertainty description.", "type": "string", "maxLength": 500 } }, "required": [ "name", "value" ] }, "protocol": { "title": "Evaluation protocol", "description": "Prompting, shots, decoding, and hardware context.", "type": "object", "properties": { "shots": { "title": "Shots", "description": "Number of examples supplied to the model.", "type": "integer", "minimum": 0, "maximum": 1000000 }, "promptTemplate": { "title": "Prompt template", "description": "Stable prompt or template identifier.", "type": "string", "maxLength": 20000 }, "decoding": { "title": "Decoding settings", "description": "Reported decoding configuration.", "type": "string", "maxLength": 2000 }, "hardware": { "title": "Hardware", "description": "Reported evaluation hardware.", "type": "string", "maxLength": 2000 } } }, "date": { "title": "Claim date", "description": "Optional source-reported date excluded from the context fingerprint.", "type": "string", "maxLength": 100 }, "evidenceExcerpt": { "title": "Evidence excerpt", "description": "Optional bounded excerpt supplied by the user.", "type": "string", "maxLength": 20000 } }, "required": [ "claimId", "source", "model", "benchmark", "metric" ] } }, "comparisonGroups": { "title": "Explicit comparison groups", "maxItems": 200, "type": "array", "description": "Optional claim-ID groups. Pairwise decisions and exact field evidence are emitted without rankings or extra charges.", "items": { "type": "object", "additionalProperties": false, "properties": { "groupId": { "title": "Group ID", "description": "Unique label for this comparison group.", "type": "string", "minLength": 1, "maxLength": 300 }, "claimIds": { "title": "Claim IDs", "description": "Two to fifty unique claim IDs from this run.", "type": "array", "minItems": 2, "maxItems": 50, "items": { "type": "string", "minLength": 1, "maxLength": 300 } } }, "required": [ "groupId", "claimIds" ] }, "default": [] }, "aliasRegistryVersion": { "title": "Alias registry version", "enum": [ "1.0.0" ], "type": "string", "description": "Exact bundled registry version; aliases are never inferred.", "default": "1.0.0" }, "customAliases": { "title": "Explicit custom aliases", "type": "object", "description": "Optional domain-to-alias mappings. Collisions and unknown canonical benchmark or metric targets are rejected.", "default": {} }, "strictMode": { "title": "Strict comparison context", "type": "boolean", "description": "When true, missing registry-required context produces insufficient_context. When false, it remains a visible partial comparison and is never guessed.", "default": true } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }