# US 2026/0064855 A1 · Efficient evaluation of controls for a simulated inspection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0064855 A1
- Document ID: US20260064855A1
- Status: Published application
- Kind: A1
- Application number: 19/318,317
- Filed: 2025-09-03
- Published: 2026-03-05
- Earliest claimed: 2024-09-04
- Assignees: Interstice Labs, Inc. dba Trustero
- Applicants: Interstice Labs, Inc. dba Trustero
- Inventors: Phillip Liu; Aleksandr Olegovich Gonopolskiy; Martha Raber; Nicholas Adam Martin; Max Hirsch
- Web page: https://patentgrep.com/patent/US20260064855A1

## CPC

- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06F 21/577: {Assessing vulnerabilities and evaluating computer system security}
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06N 3/092: Reinforcement learning
- G06N 3/096: Transfer learning
- G06F 2221/034: Test or assess a computer or a system
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system performs efficient execution of control tests for an organization. The system receives description of a set of controls. The system identifies a set of control tests associated with the controls. For each control, the system collects supporting information for the control. For each control test, the system performs the following steps. The system determines whether supporting information indicates that a condition required by the control failed to occur. The system determines whether the supporting information is applicable to the control test. The system determines whether the supporting information passes the control test. The system builds an output data structure representing a result of the control test. The system determines a final result by summarizing a set of results obtained from the set of control tests and performing a target action based on the final result.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving description of a set of controls;
identifying a set of control tests associated with the set of controls;
for each control, collecting supporting information for the control;
for each control test from the set of control tests:
determining whether a supporting information indicates that a condition required by the control failed to occur,
determining whether the supporting information is applicable to the control test,
determining whether the supporting information passes the control test, and
building an output data structure representing a result of the control test;
determining a final result by summarizing a set of results obtained from the set of control tests; and
performing a target action based on the final result.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein determining whether the supporting information is applicable to the control test comprises:
generating a structured query input describing the supporting information and the control test with a request to determining whether the supporting information is applicable to the control test;
inputting the structured query input into a trained transformer-based neural network; and
processing an output sequence generated by the trained transformer-based neural network, wherein the output sequence comprises a result indicating whether the supporting information is applicable to the control test.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the structured query input is formatted according to a pre-defined schema for interaction with the trained transformer-based neural network, wherein the trained transformer-based neural network has been trained on a corpus of data using supervised fine-tuning and reinforcement learning, wherein processing the output sequence comprises applying post-generation parsing rules to extract data fields and generate an interpretable response.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
checking for completeness comprising, determining whether there is sufficient evidence to determine a result of the control test.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the output data structure stores a summary text describing a reason for the result of the control test.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein summarizing comprises:
responsive to determining that a control test failed, determining if another test result can be used instead of the failed control test.

### Claim 7 (depends on 4)

The computer-implemented method of claim 4, further comprising:
for each failed control test, including a reasoning of a failure in a summarization text.

### Claim 8

A non-transitory computer readable storage medium storing instructions that when executed by one or more computer processors, cause the one or more computer processors to perform steps comprising:
receiving description of a set of controls;
identifying a set of control tests associated with the set of controls;
for each control, collecting supporting information for the control;
for each control test from the set of control tests:
determining whether a supporting information indicates that a condition required by the control failed to occur,
determining whether the supporting information is applicable to the control test,
determining whether the supporting information passes the control test, and
building an output data structure representing a result of the control test;
determining a final result by summarizing a set of results obtained from the set of control tests; and
performing a target action based on the final result.

### Claim 9 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein determining whether the supporting information is applicable to the control test comprises:
generating a structured query input describing the supporting information and the control test with a request to determining whether the supporting information is applicable to the control test;
inputting the structured query input into a trained transformer-based neural network; and
processing an output sequence generated by the trained transformer-based neural network, wherein the output sequence comprises a result indicating whether the supporting information is applicable to the control test.

### Claim 10 (depends on 9)

The non-transitory computer readable storage medium of claim 9, wherein the structured query input is formatted according to a pre-defined schema for interaction with the trained transformer-based neural network, wherein the trained transformer-based neural network has been trained on a corpus of data using supervised fine-tuning and reinforcement learning, wherein processing the output sequence comprises applying post-generation parsing rules to extract data fields and generate an interpretable response.

### Claim 11 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the instructions when executed by one or more computer processors, further cause the one or more computer processors to perform steps comprising:
checking for completeness comprising, determining whether there is sufficient evidence to determine a result of the control test.

### Claim 12 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein the output data structure stores a summary text describing a reason for the result of the control test.

### Claim 13 (depends on 8)

The non-transitory computer readable storage medium of claim 8, wherein summarizing comprises:
responsive to determining that a control test failed, determining if another test result can be used instead of the failed control test.

### Claim 14 (depends on 11)

The non-transitory computer readable storage medium of claim 11, wherein the instructions when executed by one or more computer processors, further cause the one or more computer processors to perform steps comprising:
for each failed control test, including a reasoning of a failure in a summarization text.

### Claim 15

A computer system comprising:
one or more computer processors; and
a non-transitory computer readable storage medium storing instructions that when executed by the one or more computer processors, cause the one or more computer processors to perform steps comprising:
receiving description of a set of controls;
identifying a set of control tests associated with the set of controls;
for each control, collecting supporting information for the control;
for each control test from the set of control tests:
determining whether a supporting information indicates that a condition required by the control failed to occur,
determining whether the supporting information is applicable to the control test,
determining whether the supporting information passes the control test, and
building an output data structure representing a result of the control test;
determining a final result by summarizing a set of results obtained from the set of control tests; and
performing a target action based on the final result.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein determining whether the supporting information is applicable to the control test comprises:
generating a structured query input describing the supporting information and the control test with a request to determining whether the supporting information is applicable to the control test;
inputting the structured query input into a trained transformer-based neural network; and
processing an output sequence generated by the trained transformer-based neural network, wherein the output sequence comprises a result indicating whether the supporting information is applicable to the control test.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein the structured query input is formatted according to a pre-defined schema for interaction with the trained transformer-based neural network, wherein the trained transformer-based neural network has been trained on a corpus of data using supervised fine-tuning and reinforcement learning, wherein processing the output sequence comprises applying post-generation parsing rules to extract data fields and generate an interpretable response.

### Claim 18 (depends on 15)

The computer system of claim 15, wherein the instructions when executed by one or more computer processors, further cause the one or more computer processors to perform steps comprising:
checking for completeness comprising, determining whether there is sufficient evidence to determine a result of the control test.

### Claim 19 (depends on 15)

The computer system of claim 15, wherein the output data structure stores a summary text describing a reason for the result of the control test.

### Claim 20 (depends on 15)

The computer system of claim 15, wherein summarizing comprises:
responsive to determining that a control test failed, determining if another test result can be used instead of the failed control test.
