Prosecution Insights
Last updated: April 19, 2026
Application No. 18/471,014

LOCAL EXPLANATION OF BLACK BOX MODEL BASED ON CONSTRAINED PERTURBATION AND ENSEMBLE-BASED SURROGATE MODEL

Non-Final OA §112
Filed
Sep 20, 2023
Examiner
CHOI, YUK TING
Art Unit
2164
Tech Center
2100 — Computer Architecture & Software
Assignee
Tata Consultancy Services Limited
OA Round
1 (Non-Final)
72%
Grant Probability
Favorable
1-2
OA Rounds
3y 3m
To Grant
99%
With Interview

Examiner Intelligence

Grants 72% — above average
72%
Career Allow Rate
466 granted / 652 resolved
+16.5% vs TC avg
Strong +37% interview lift
Without
With
+37.4%
Interview Lift
resolved cases with interview
Typical timeline
3y 3m
Avg Prosecution
29 currently pending
Career history
681
Total Applications
across all art units

Statute-Specific Performance

§101
16.8%
-23.2% vs TC avg
§103
55.0%
+15.0% vs TC avg
§102
13.5%
-26.5% vs TC avg
§112
6.8%
-33.2% vs TC avg
Black line = Tech Center average estimate • Based on career data from 652 resolved cases

Office Action

§112
DETAILED ACTION 1. The present application 18/471,014, filed on 09/20/2023, is being examined under the first inventor to file provisions of the AIA. Clams 1- 6 are pending in this application. Drawings 2. The drawings received on 09 / 20 /202 3 are accepted by the Examiner. Priority 3. Acknowledgment is made of applicant's claim for priority to foreign application No. IN20232101420 filed on 03 /0 2 /202 3. Information Disclosure Statement 4. The information disclosure statement (IDS) submitted on 09/20/2023 is being considered by the examiner. Claim Rejections - 35 USC § 112 The following is a quotation of 35 U.S.C. 112(b): (b ) CONCLUSION.— The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. 5. Claims 2, 4 and 6 are rejected under 35 U.S.C. 112(b), as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claims 2, 4 and 6 recite an equation CV/Length/4. It is unclear what the symbol “/” means in the equation. Allowable Subject Matter The closest prior art Nia et al. (US 2022/0198277 A1) discloses local machine learning (ML) explainability (MLX) techniques that e xplain any ML classifier or regressor for tabular datasets. An interpretable surrogate ML model is used to explain the behavior of a complex black-box ML model on a generated local neighborhood of local sample samples. For evaluating the black-box model and training the surrogate explainer model, a generator ML model of a Generative Adversarial Network (GAN) is trained and used to generate a realistic local sample neighborhood according to the characteristics of the dataset that the black-box model was trained on. The generator ML model generat es explanations for specific predictions from the black-box mode l. Nia et al. fails to anticipate or render obvious all the recited features including generating a plurality of perturbed datapoints around the local instance by varying values for each continuous features, which is constrained by a Coefficient of Variation (CV) score, obtained from distribution of a percentage of sample data selected from a test dataset and generating a plurality of perturbed datapoints around the local instance by varying values for each categorical features generated by randomly selecting a value from a categorical column that covers more than a predefined percentage of the percentage of the sample data and other features in the instant claims 1, 3 and 5. Another closest prior art Nourian et al. (US 2021/0049503 A1) discloses a machine learning model, the machine learning model trained, during a training phase, to learn patterns to correctly classify input data associated with risk analysis. One or more features of the machine learning model may be analyzed, the one or more features being defined based on one or more constraints associated with one or more values and relationships and whether said one or more values and relationships satisfy at least one of the one or more constraints. In response to further analyzing the one or more features and the training data, providing at least a global and a local explanation about a given instance, and generating a report summarizing the global and local explanations, the global explanation providing general information about one or more functionalities of the machine learning model and a visualization that summarizes the machine learning model's global behavior with respect to the one or more features that are influential in generating one or more identifiable outcomes, and the local explanation providing an understanding of how possible changes to the instance's feature values adjust or shift an expected result or projected outcome beyond a first threshold. Nourian et al. fails to anticipate or render obvious all the recited features including generating a plurality of perturbed datapoints around the local instance by varying values for each continuous features, which is constrained by a Coefficient of Variation (CV) score, obtained from distribution of a percentage of sample data selected from a test dataset and generating a plurality of perturbed datapoints around the local instance by varying values for each categorical features generated by randomly selecting a value from a categorical column that covers more than a predefined percentage of the percentage of the sample data and other features in the instant claims 1, 3 and 5. The features in independent claims 1, 3 and 5 are novel and non-obvious over closest prior art. The dependent claims 2, 4 and 6 are being definite, enabled by the specification, and further limiting to the independent claims, are also allowable. Any inquiry concerning this communication or earlier communications from the examiner should be directed to FILLIN "Examiner name" \* MERGEFORMAT YUK TING CHOI whose telephone number is FILLIN "Phone number" \* MERGEFORMAT (571)270-1637 . The examiner can normally be reached FILLIN "Work Schedule?" \* MERGEFORMAT Monday-Friday 9am-6pm . Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, FILLIN "SPE Name?" \* MERGEFORMAT AMY NG can be reached at FILLIN "SPE Phone?" \* MERGEFORMAT 5712701698 . The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /YUK TING CHOI/ Primary Examiner, Art Unit 2164
Read full office action

Prosecution Timeline

Sep 20, 2023
Application Filed
Mar 26, 2026
Non-Final Rejection — §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12591610
SYSTEMS AND METHODS FOR REMOVING NON-CONFORMING WEB TEXT
2y 5m to grant Granted Mar 31, 2026
Patent 12579156
SYSTEMS AND METHODS FOR VISUALIZING ONE OR MORE DATASETS
2y 5m to grant Granted Mar 17, 2026
Patent 12562753
SYSTEM AND METHOD FOR MULTI-TYPE DATA COMPRESSION OR DECOMPRESSION WITH A VIRTUAL MANAGEMENT LAYER
2y 5m to grant Granted Feb 24, 2026
Patent 12536282
METHODS AND APPARATUS FOR MACHINE LEARNING BASED MALWARE DETECTION AND VISUALIZATION WITH RAW BYTES
2y 5m to grant Granted Jan 27, 2026
Patent 12511258
DYNAMIC STORAGE OF SEQUENCING DATA FILES
2y 5m to grant Granted Dec 30, 2025
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
72%
Grant Probability
99%
With Interview (+37.4%)
3y 3m
Median Time to Grant
Low
PTA Risk
Based on 652 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month