ToolVet
78trust / 100

Retrieval Recovery Regression

by Retrieval recovery regression in AI models & inference

x402 APIPassing, checked 3 h ago

Compare complete, partial, and missed evidence recovery on one matched, hash-frozen cohort of up to 64 questions and papers. Report paired transitions and a caller-declared complete-recovery drop threshold. Descriptive evidence-ID overlap, not answer quality or causal inference. New modular adapter: retained result recovery for 24 hours, minimal receipt metadata for 90 days. Existing live route unchanged.

POST
https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression
Price
$0.074
per call in USDC
Uptime
100%
last 30 days
Response time
247 ms
332 ms slowest 5%
Last check
Passed
3 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression

Each call costs $0.074001 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression
content-type: application/json

{
  "baseline": {
    "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
    "observations": [
      {
        "paperId": "paper-a",
        "questionId": "q1",
        "retrievedEvidenceIds": [
          "a1"
        ]
      },
      {
        "paperId": "paper-b",
        "questionId": "q2",
        "retrievedEvidenceIds": [
          "b1"
        ]
      }
    ],
    "runId": "baseline"
  },
  "candidate": {
    "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
    "observations": [
      {
        "paperId": "paper-a",
        "questionId": "q1",
        "retrievedEvidenceIds": [
          "a1",
          "a2"
        ]
      },
      {
        "paperId": "paper-b",
        "questionId": "q2",
        "retrievedEvidenceIds": []
      }
    ],
    "runId": "candidate"
  },
  "corpusHash": "sha256:5e1bf4f25cdc1fc0fbcbb2240affabbd808fd2ba8fa1ce0b6723dac5dc682759",
  "dataClass": "synthetic",
  "evidence": [
    {
      "evidenceId": "a1",
      "paperId": "paper-a"
    },
    {
      "evidenceId": "a2",
      "paperId": "paper-a"
    },
    {
      "evidenceId": "b1",
      "paperId": "paper-b"
    }
  ],
  "maxCompleteDropBps": 0,
  "paperIds": [
    "paper-a",
    "paper-b"
  ],
  "questions": [
    {
      "expectedEvidenceIds": [
        "a1",
        "a2"
      ],
      "paperId": "paper-a",
      "questionId": "q1"
    },
    {
      "expectedEvidenceIds": [
        "b1"
      ],
      "paperId": "paper-b",
      "questionId": "q2"
    }
  ]
}

Parameters

ParameterTypeRequiredDescription
baselineobjectYes
candidateobjectYes
corpusHashstringYes
dataClassstringYes One of: public, synthetic.
evidencearrayYes
maxCompleteDropBpsintegerYes
paperIdsarrayYes
questionsarrayYes

Example response

The provider's example. We can't check it without paying.

{
  "data": {
    "chargedAmount": "74001",
    "productId": "retrieval-recovery-regression",
    "sourceContractAmount": "74000",
    "version": "maha-legacy-adapter/1"
  },
  "proof": {},
  "success": true
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.074001.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression' \
  -H 'content-type: application/json' \
  --data-raw '{"baseline":{"cohortSha256":"sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2","observations":[{"paperId":"paper-a","questionId":"q1","retrievedEvidenceIds":["a1"]},{"paperId":"paper-b","questionId":"q2","retrievedEvidenceIds":["b1"]}],"runId":"baseline"},"candidate":{"cohortSha256":"sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2","observations":[{"paperId":"paper-a","questionId":"q1","retrievedEvidenceIds":["a1","a2"]},{"paperId":"paper-b","questionId":"q2","retrievedEvidenceIds":[]}],"runId":"candidate"},"corpusHash":"sha256:5e1bf4f25cdc1fc0fbcbb2240affabbd808fd2ba8fa1ce0b6723dac5dc682759","dataClass":"synthetic","evidence":[{"evidenceId":"a1","paperId":"paper-a"},{"evidenceId":"a2","paperId":"paper-a"},{"evidenceId":"b1","paperId":"paper-b"}],"maxCompleteDropBps":0,"paperIds":["paper-a","paper-b"],"questions":[{"expectedEvidenceIds":["a1","a2"],"paperId":"paper-a","questionId":"q1"},{"expectedEvidenceIds":["b1"],"paperId":"paper-b","questionId":"q2"}]}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression' \
  -H 'content-type: application/json' \
  --data-raw '{"baseline":{"cohortSha256":"sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2","observations":[{"paperId":"paper-a","questionId":"q1","retrievedEvidenceIds":["a1"]},{"paperId":"paper-b","questionId":"q2","retrievedEvidenceIds":["b1"]}],"runId":"baseline"},"candidate":{"cohortSha256":"sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2","observations":[{"paperId":"paper-a","questionId":"q1","retrievedEvidenceIds":["a1","a2"]},{"paperId":"paper-b","questionId":"q2","retrievedEvidenceIds":[]}],"runId":"candidate"},"corpusHash":"sha256:5e1bf4f25cdc1fc0fbcbb2240affabbd808fd2ba8fa1ce0b6723dac5dc682759","dataClass":"synthetic","evidence":[{"evidenceId":"a1","paperId":"paper-a"},{"evidenceId":"a2","paperId":"paper-a"},{"evidenceId":"b1","paperId":"paper-b"}],"maxCompleteDropBps":0,"paperIds":["paper-a","paper-b"],"questions":[{"expectedEvidenceIds":["a1","a2"],"paperId":"paper-a","questionId":"q1"},{"expectedEvidenceIds":["b1"],"paperId":"paper-b","questionId":"q2"}]}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.074001 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.074001" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.074001 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fwww.mahastrategies.com%2Fapi%2Fv1%2Fcontext%2Fretrieval%2Frecovery-regression&method=POST
const res = await pay("https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "baseline": {
      "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
      "observations": [
        {
          "paperId": "paper-a",
          "questionId": "q1",
          "retrievedEvidenceIds": [
            "a1"
          ]
        },
        {
          "paperId": "paper-b",
          "questionId": "q2",
          "retrievedEvidenceIds": [
            "b1"
          ]
        }
      ],
      "runId": "baseline"
    },
    "candidate": {
      "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
      "observations": [
        {
          "paperId": "paper-a",
          "questionId": "q1",
          "retrievedEvidenceIds": [
            "a1",
            "a2"
          ]
        },
        {
          "paperId": "paper-b",
          "questionId": "q2",
          "retrievedEvidenceIds": []
        }
      ],
      "runId": "candidate"
    },
    "corpusHash": "sha256:5e1bf4f25cdc1fc0fbcbb2240affabbd808fd2ba8fa1ce0b6723dac5dc682759",
    "dataClass": "synthetic",
    "evidence": [
      {
        "evidenceId": "a1",
        "paperId": "paper-a"
      },
      {
        "evidenceId": "a2",
        "paperId": "paper-a"
      },
      {
        "evidenceId": "b1",
        "paperId": "paper-b"
      }
    ],
    "maxCompleteDropBps": 0,
    "paperIds": [
      "paper-a",
      "paper-b"
    ],
    "questions": [
      {
        "expectedEvidenceIds": [
          "a1",
          "a2"
        ],
        "paperId": "paper-a",
        "questionId": "q1"
      },
      {
        "expectedEvidenceIds": [
          "b1"
        ],
        "paperId": "paper-b",
        "questionId": "q2"
      }
    ]
  }),
});
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.074001 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.074001"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://www.mahastrategies.com/api/v1/context/retrieval/recovery-regression",
        json={
            "baseline": {
                "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
                "observations": [
                    {
                        "paperId": "paper-a",
                        "questionId": "q1",
                        "retrievedEvidenceIds": [
                            "a1",
                        ],
                    },
                    {
                        "paperId": "paper-b",
                        "questionId": "q2",
                        "retrievedEvidenceIds": [
                            "b1",
                        ],
                    },
                ],
                "runId": "baseline",
            },
            "candidate": {
                "cohortSha256": "sha256:874ebcbb47229979ed9499f3733e3f483b970ceb0b0c1f9bc52c734f3176d8f2",
                "observations": [
                    {
                        "paperId": "paper-a",
                        "questionId": "q1",
                        "retrievedEvidenceIds": [
                            "a1",
                            "a2",
                        ],
                    },
                    {
                        "paperId": "paper-b",
                        "questionId": "q2",
                        "retrievedEvidenceIds": [],
                    },
                ],
                "runId": "candidate",
            },
            "corpusHash": "sha256:5e1bf4f25cdc1fc0fbcbb2240affabbd808fd2ba8fa1ce0b6723dac5dc682759",
            "dataClass": "synthetic",
            "evidence": [
                {
                    "evidenceId": "a1",
                    "paperId": "paper-a",
                },
                {
                    "evidenceId": "a2",
                    "paperId": "paper-a",
                },
                {
                    "evidenceId": "b1",
                    "paperId": "paper-b",
                },
            ],
            "maxCompleteDropBps": 0,
            "paperIds": [
                "paper-a",
                "paper-b",
            ],
            "questions": [
                {
                    "expectedEvidenceIds": [
                        "a1",
                        "a2",
                    ],
                    "paperId": "paper-a",
                    "questionId": "q1",
                },
                {
                    "expectedEvidenceIds": [
                        "b1",
                    ],
                    "paperId": "paper-b",
                    "questionId": "q2",
                },
            ],
        },
    )
    print(res.status_code, res.text)

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402250 ms$0.074
8 h agoPassed402252 ms$0.074
13 h agoPassed402223 ms$0.074
18 h agoPassed402293 ms$0.074
22 h agoPassed402246 ms$0.074
Show 3 older checks
27 h agoPassed402247 ms$0.074
31 h agoPassed402332 ms$0.074
35 h agoPassed402196 ms$0.074