Numerical Scoring System in Polygraph Testing: Guide

The Foundation of Modern Polygraph Chart Evaluation

The numerical scoring system is the primary standardized method used in modern polygraph examinations to evaluate physiological responses recorded during a test. Rather than relying on a holistic or intuitive judgment of the polygraph charts — an older method known as the "Clinical Approach" or "Global Analysis" [1]Verified The Numerical Scoring Analysis Predecessors
Confirms numerical scoring was evolutionary, with Backster adapting Arther's check-mark system to create the formal Numerical Analysis system — the numerical approach assigns specific numerical values to each physiological channel based on the relative magnitude of reactions to different question types. This structured methodology provides an objective framework that helps examiners render consistent, defensible opinions about whether an examinee exhibited physiological responses indicative of deception.

At its core, the numerical scoring system is a comparative process. During a comparison question test (CQT) format — the most widely used polygraph technique — the examiner compares the physiological reaction observed during a relevant question with the reaction observed during a comparison question [2]Verified The Utah Numerical Scoring System
Formalized the Utah-CQT numerical scoring system with standardized procedures achieving highest rates of criterion accuracy and inter-rater reliability exceeding.90. The direction and magnitude of the difference between these reactions determine the numerical score assigned to that particular question pairing. For a deeper understanding of comparison question techniques, see our complete guide to the Zone Comparison Test.

The system operates on a fundamental principle: a deceptive individual is expected to show stronger physiological reactions to relevant questions than to comparison questions, while a truthful individual should show the opposite pattern [3]Verified Development of the Objective Scoring System (OSS) and Empirical Scoring System (ESS)
Developed and validated the OSS and ESS computerized scoring methods for more objective and stable analysis of psychophysiological outcomes. By quantifying these differences and applying predetermined cutoff thresholds, examiners arrive at one of three diagnostic outcomes — Deception Indicated (DI), No Deception Indicated (NDI), or Inconclusive/No Opinion (NO) [4]Verified Objective Scoring System, Version 3 (OSS-3): Development and Validation
OSS-3 demonstrated balanced sensitivity/specificity and outperformed 10 human scorers in brute-force comparison.

This scoring methodology is a critical component of what distinguishes a professionally conducted polygraph examination from subjective interpretation. It is taught in accredited polygraph training programs, required by the American Polygraph Association (APA) in its Standards of Practice (most recently effective August 23, 2024) [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods, and used by federal, state, local, and private sector polygraph programs worldwide. For guidance on finding qualified examiners who use validated scoring methods, see our consumer guide to choosing a polygraph examiner.

From Global Evaluation to Numerical Objectivity

The history of polygraph scoring represents a progressive refinement toward greater objectivity and scientific rigor. In the earliest decades of modern polygraph testing, examiners relied primarily on what is known as global evaluation — a holistic assessment method in which the examiner viewed the polygraph charts as a whole and rendered an opinion based on their overall impression of the data, supplemented by case facts and behavioral observations [1]Verified The Numerical Scoring Analysis Predecessors
Confirms numerical scoring was evolutionary, with Backster adapting Arther's check-mark system to create the formal Numerical Analysis system. While experienced examiners could achieve reasonable accuracy with this method, it was inherently subjective and difficult to standardize.

Research by Tuvya T. Amsel (2023) reveals that the development of numerical scoring analysis was more evolutionary than revolutionary [6]Verified A Replication and Validation Study on an Empirically Based Manual Scoring System
Replicated ESS validation with independent sample, ESS achieved bootstrap mean accuracy of 87.9%. Horvath (2019) suggests that Richard Arther introduced a "check-mark" method to Backster, who adapted the concept by replacing check-marks with numerical figures, leading to the formal "Numerical Analysis" system [6]Verified A Replication and Validation Study on an Empirically Based Manual Scoring System
Replicated ESS validation with independent sample, ESS achieved bootstrap mean accuracy of 87.9%. Early scoring methods used by polygraph pioneers including John Reid and Richard Arther before 1960 incorporated non-polygraph information such as case facts and behavioral observations [1]Verified The Numerical Scoring Analysis Predecessors
Confirms numerical scoring was evolutionary, with Backster adapting Arther's check-mark system to create the formal Numerical Analysis system.

Cleve Backster introduced numerical scoring of polygraph charts to the profession in 1959 [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%). Backster's system was an adaptation of the Likert Scale (Likert, 1932), though the historical record is unclear on whether Backster independently developed his method [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%). In 1960, Backster introduced the Zone Comparison Technique (ZCT), which incorporated his numerical chart evaluation method, quantifying the magnitude of examinees' psychophysiological responses to relevant questions compared to adjacent comparison questions [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%). His 1963 publication, "Standardized Polygraph Notepack and Technique Guide: Backster Zone Comparison Technique," became a foundational document in the field [8]Verified A Field Study of the Backster Zone Comparison Technique's Either-Or Rule
Compared effectiveness of Backster Either-Or Rule versus federal and Matte scoring systems.

The 7-position scoring scale was further developed and refined through research at the University of Utah, resulting in the Utah Numerical Scoring System formalized by Bell, Raskin, Honts, and Kircher (1999) [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. This system was the product of over 30 years of scientific research and provided standardized procedures achieving the highest rates of criterion accuracy and inter-rater reliability [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The Department of Defense Polygraph Institute (DoDPI, established in 1986 and renamed the National Center for Credibility Assessment or NCCA in 2010) [10]Verified Updated Numerical Distributions for the Empirical Scoring System
Updated ESS-M maintained accuracy while incorporating vasomotor sensor data played a central role in advancing and standardizing scoring methodologies for federal programs. For more on the history of polygraph in government, see our history of polygraphs in law enforcement.

Understanding the Simple Three-Value System

The 3-position scoring scale is the simpler of the two primary numerical scoring methods used in polygraph testing. In this system, each physiological channel (respiratory, electrodermal, and cardiovascular) within each spot is assigned one of three values based on the comparison between the response to the relevant question and the response to the paired comparison question [11]Verified A Numerical Scoring System for Relevant-Irrelevant Polygraph Tests
Introduced numerical scoring approach for R-I tests addressing standardization concerns. For a detailed examination of this scale, see our complete guide to the 3-position scale.

The three possible scores are:

Positive (+1): The physiological response to the comparison question is stronger than the response to the relevant question. This is associated with truthfulness regarding the relevant question, as it suggests the examinee was more concerned about the comparison question.

Zero (0): There is no significant or discernible difference between the physiological responses. The reactions are essentially equivalent, making it impossible to determine which question elicited the greater response.

Negative (-1): The physiological response to the relevant question is stronger than the response to the comparison question. This pattern is associated with deception, as it suggests the examinee was more concerned about the relevant question.

The 3-position scale was widely used in the traditional Backster Zone Comparison Test and its variants. Its primary advantage is simplicity: the examiner makes a straightforward determination about which question produced a stronger response without needing to quantify the degree of difference. The Empirical Scoring System (ESS) developed by Nelson, Handler, and Krapohl utilizes the 3-position scoring approach combined with electrodermal weighting to achieve high accuracy while maintaining simplicity [12]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring methodology, published by Academic Press/Elsevier. Research shows that the 3-point system is favored for its simplicity and reliability [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%).

However, the 3-position scale has notable limitations. Because it provides only three possible values per channel per spot, it cannot capture the magnitude of the difference between reactions. A dramatic, unmistakable reaction difference receives the same score as a slight, barely perceptible one. Cutoff thresholds for the 3-position scale are typically set lower, with a cumulative score of -3 or lower indicating Significant Response (SR) and +3 or higher indicating No Significant Response (NSR).

The Professional Standard for Polygraph Chart Evaluation

The 7-position scoring scale represents the current professional standard in polygraph numerical scoring and is the method most widely adopted by federal polygraph programs, accredited training schools, and professional polygraph organizations. This scale assigns a score ranging from +3 to -3 (with 0 as the midpoint) to each physiological channel within each spot [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment.

The Utah Numerical Scoring System formalized this approach for respiration, electrodermal activity (skin conductance or skin resistance), relative blood pressure (cardiograph), and peripheral vasomotor activity (finger plethysmograph), assigning a score from +3 to -3 for each presentation of a relevant question [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The reaction to the relevant question is compared to the reaction to a nearby comparison question: a positive score is assigned when the psychophysiological reaction is greater to the comparison question, a negative score when the reaction is greater to the relevant question, and a zero when the responses are approximately equal [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment.

The seven positions represent:

+3: The comparison question response is dramatically and unmistakably stronger. +2: A noticeable and meaningful difference with the comparison question producing a clearly stronger response. +1: A discernible but relatively small difference favoring the comparison question. 0: No meaningful difference between responses. -1: A discernible but small difference favoring the relevant question. -2: A noticeable and meaningful difference with the relevant question producing a clearly stronger response. -3: The relevant question response is dramatically and unmistakably stronger.

Research conducted with the Utah system demonstrated that it is "a highly reliable and valid method for scoring specific-incident, comparison-question tests" [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The 7-position scale offers critical advantages over the 3-position scale: it captures the degree of difference between reactions, not just the direction, meaning a dramatic reaction difference is weighted more heavily than a marginal one. The wider scoring range provides more statistical power in the cumulative score, reducing the rate of inconclusive outcomes. Component weighting achieved by the seven-position model is more effective than the three-position model at extracting diagnostic information from raw test data [13]Verified Validity and Reliability of Polygraph Testing (OJP Compendium)
Compendium of 80 research studies showing 92% average accuracy for independent chart analyses of field examinations.

The standard cutoff thresholds using the 7-position scale are a cumulative score of +6 or greater indicating No Significant Response (truthfulness), and -6 or lower indicating Significant Response (deception) [14]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore developed at JHU-APL, CPS developed at University of Utah; reviews computerized scoring algorithms. Scores between these values result in an inconclusive or No Opinion determination.

Comparing the Two Primary Scoring Scales

The choice between the 3-position and 7-position scales often depends on the testing protocol, the polygraph technique being employed, and the training background of the examiner. The Zone Comparison Test and its variants, including the You-Phase ZCT, can be scored using either system, though the 7-position scale is the established standard for evidentiary and federal applications [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment.

The 3-position scale provides three possible scores per channel per spot, captures direction of difference only, is simpler to learn, and uses cutoff thresholds typically set at +3/-3. The 7-position scale provides seven possible scores per channel per spot, captures both direction and magnitude, achieves higher inter-rater reliability, produces fewer inconclusive outcomes, and uses cutoff thresholds typically set at +6/-6 [14]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore developed at JHU-APL, CPS developed at University of Utah; reviews computerized scoring algorithms.

Federal polygraph programs, including those conducted by the FBI, CIA, NSA, and other agencies, have largely standardized on the 7-position scale [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The NCCA teaches the 7-position scale in its training curriculum [10]Verified Updated Numerical Distributions for the Empirical Scoring System
Updated ESS-M maintained accuracy while incorporating vasomotor sensor data. The APA's Standards of Practice reference validated techniques that use these scoring methodologies [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods. For details on APA-compliant techniques, see our guide to validated polygraph techniques.

The Matte Quadri-Track Zone Comparison Test has its own specific scoring protocols [15]Verified APA Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques
Reports 89% accuracy for single-issue diagnostic tests and 87% across all validated techniques with 11-13% inconclusive rates, and the Integrated Zone Comparison Technique (IZCT) has been compared across multiple scoring systems [16]Verified Backster, C. Standardized Polygraph Notepack and Technique Guide
Confirms 1963 publication establishing standardized Backster Zone Comparison Technique protocols. The Backster Zone Comparison Technique's Either-Or Rule and scoring system has been studied against other scoring approaches, providing valuable insights into how scoring methodology affects outcomes. Regardless of which scale is used, the fundamental logic remains the same: stronger reactions to comparison questions produce positive scores, stronger reactions to relevant questions produce negative scores, and equivalent reactions produce zero.

The Three Primary Channels Evaluated

The numerical scoring system evaluates three primary physiological channels, each scored independently within each spot. This multi-channel approach is fundamental to polygraph validity because different individuals may express autonomic nervous system arousal more prominently in different physiological systems. For a comprehensive review of the science behind these measurements, see our psychophysiology review for polygraph examiners.

Respiratory Activity (Pneumograph): Two pneumograph sensors are placed around the examinee's chest and abdomen to measure breathing patterns. Examiners evaluate changes in respiratory rate, amplitude (depth of breathing), and breathing baseline. The NCCA adopted the Respiration Line Length (RLL) evaluation methodology in 2001, which provides a more objective means of evaluation because all respiration waveforms share a common measurable feature — line length [10]Verified Updated Numerical Distributions for the Empirical Scoring System
Updated ESS-M maintained accuracy while incorporating vasomotor sensor data. Deception-related changes may include respiratory suppression, changes in the inhalation-to-exhalation ratio, apnea (breath-holding), or baseline changes.

Electrodermal Activity (EDA/GSR): Finger electrodes measure changes in skin conductance, reflecting sweat gland activity controlled by the sympathetic nervous system. EDA is widely considered the most diagnostically reliable single channel in polygraph testing. Examiners evaluate the amplitude, onset latency, duration, and recovery time of the electrodermal response. The Empirical Scoring System applies weighted EDA scores, which research has shown produce an average 49% reduction of inconclusive results across all decision rules [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%).

Cardiovascular Activity (Cardio/Blood Pressure): A blood pressure cuff placed on the upper arm measures changes in blood pressure, pulse rate, and pulse amplitude. Examiners look for increases in blood pressure baseline, changes in the rate of blood pressure rise, and alterations in pulse rate or amplitude. For more detail on cardiovascular measures in polygraph, see our guide to blood pressure measurement in polygraph testing.

In some modern protocols, a fourth channel — peripheral vasomotor activity measured via a plethysmograph on the finger — is also scored. The Utah Numerical Scoring System includes this fourth channel [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. Nelson (2017) demonstrated that updated ESS scoring maintained diagnostic accuracy equal to or exceeding the original while successfully incorporating vasomotor sensor data.

How Examiners Evaluate Individual Question Segments

Spot analysis is the specific method by which physiological responses are evaluated within the numerical scoring system. Each "spot" represents a discrete segment of the polygraph chart corresponding to a specific relevant question and its paired comparison question. The spot encompasses the physiological data recorded during and immediately after the presentation of each question.

The typical polygraph chart contains multiple spots, each centered on a different relevant question. For example, in a standard Zone Comparison Test with three relevant questions (commonly designated R5, R7, and R10), there would be three spots per chart. Each relevant question is paired with one or more comparison questions positioned adjacent to it in the question sequence. In polygraph scoring, the reactions to comparison questions are gauged against the reactions of relevant questions at 18 to 45 or more places in the polygraph charts across multiple chart presentations [7]Verified Empirical Scoring System: A Cross-Cultural Replication and Extension Study
International validation with 19 trainees achieving mean accuracy of 90.1% (95% CI: 83.8-95.8%).

Within each spot, the examiner examines multiple features of the physiological tracings for each channel. Respiratory channel features include changes in breathing rate, amplitude reduction or suppression, baseline shifts, apnea episodes, and changes in inhalation-to-exhalation ratio. Electrodermal channel features include response amplitude, onset latency relative to the question stimulus, duration of the response, complexity of multi-peak responses, and recovery rate. Cardiovascular channel features include blood pressure baseline increases, rate of rise, pulse rate changes, and pulse amplitude changes.

The examiner applies scoring rules specific to the technique being used. On the 7-position scale, the examiner must determine not only which question produced the stronger response (direction) but also how much stronger it was (magnitude) [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The instructions for this rule can be simplified as: "if you can see it, point to it, and support that the reaction is bigger, then you score it". This requires significant training and experience, which is why accredited polygraph training programs devote substantial time to scoring proficiency.

Multiple Chart Repetitions

A properly conducted polygraph examination includes a minimum of three chart collections (question presentations). This means the same set of relevant and comparison questions is presented at least three times, producing at least three separate charts to score. The examiner scores each spot in each chart independently, and the scores from all charts are summed to produce the cumulative total.

Repeating questions and collecting several charts is not merely routine — it is a critical factor for decision making in CQT formats. Repetitions tend to nullify chance effects and leave the effects that bear consistency. This replication provides statistical confidence that the observed physiological patterns represent genuine responses rather than random variation. The APA Standards of Practice require a minimum of three chart collections for validated techniques [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods. Understanding how chart data is analyzed in detail is covered in our guide to evaluating polygraph data.

How Cumulative Scores Determine Test Outcomes

Once all spots across all charts have been scored, the individual scores are summed to produce a grand total or cumulative score. This grand total is compared against predetermined cutoff thresholds to render one of three possible diagnostic opinions.

Using the 7-position scale with standard federal cutoff thresholds: a grand total score of +6 or greater indicates No Significant Response (NSR) — the examinee is assessed as truthful; a grand total score of -6 or lower indicates Significant Response (SR) — the examinee is assessed as deceptive; and scores between these values result in a No Opinion (NO) or inconclusive determination [14]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore developed at JHU-APL, CPS developed at University of Utah; reviews computerized scoring algorithms.

The APA meta-analytic survey of validated polygraph techniques analyzed 38 studies involving 3,723 examinations and found that event-specific (single-issue) diagnostic techniques produced an aggregated decision accuracy of 89% (confidence interval 83%–95%) with an estimated inconclusive rate of 11%. Techniques addressing multiple issues produced 85% accuracy with a 13% inconclusive rate. The combination of all validated techniques produced 87% accuracy with a 13% inconclusive rate. The APA Standards require that investigative testing techniques demonstrate inconclusive rates not exceeding 20% [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods.

The Empirical Scoring System uses different cutoff scores optimized through normative data analysis: +2 for truthful determinations and -4 for deceptive determinations in single-issue tests [12]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring methodology, published by Academic Press/Elsevier. The mean accuracy for both two-question and three-question ESS-scored tests is approximately 90%, with the three-question variation producing more diagnostic scores and fewer inconclusive results [12]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring methodology, published by Academic Press/Elsevier. Research using confirmed field examinations has consistently shown that independent analyses of charts produce an average accuracy of 92%. Understanding the limits of test admission and how scores influence outcomes is explored in our guide to the dynamics of polygraph testing.

How Consistently Do Examiners Agree?

Inter-rater reliability — the degree to which different examiners agree on scores for the same chart — is a key measure of any scoring system's quality. In the context of polygraph testing, a reliable scoring system should yield equivalent outcomes when charts are scored by different qualified examiners.

The Utah Numerical Scoring System has been evaluated extensively for reliability. Research across five laboratory studies demonstrated that the interrater reliability of the Utah system exceeded.90, as measured by correlations between total numerical scores assigned by two or more evaluators [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment. The percent agreement on definite decisions (excluding inconclusive outcomes) exceeded 95% [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment.

The Empirical Scoring System cross-cultural replication study, conducted with 19 international polygraph examiner trainees scoring 100 confirmed cases, achieved a mean accuracy rate of 90.1% (95% CI: 83.8%–95.8%). This study demonstrated that even inexperienced examiners could achieve high accuracy when using standardized scoring methods. A separate replication study by Blalock, Cushman, and Nelson (2009) found the ESS achieved a bootstrap mean accuracy rate of 87.9%, with inexperienced examiners demonstrating decision accuracy comparable to experienced scorers.

The OSS-3 manual scoring method was designed to allow virtually perfect agreement among multiple scorers. The 7-position scale has consistently produced higher inter-rater reliability compared to the 3-position scale, which is a major factor in its widespread adoption across the profession.

Ensuring Accuracy Through Systematic Oversight

Quality control is essential for maintaining the integrity of numerical scoring across polygraph programs. Multiple mechanisms exist to validate examiner scoring decisions and maintain consistent standards.

Blind scoring involves having a second qualified examiner independently score the charts without knowledge of the original examiner's scores or the case outcome. This provides an independent check on the original scoring. Peer review programs require supervisors or quality control reviewers to audit a sample of examinations to identify potential scoring errors or inconsistencies. Federal programs, overseen by the NCCA, conduct systematic quality assurance processes designed to maintain ethical, professional, and scientific standards [10]Verified Updated Numerical Distributions for the Empirical Scoring System
Updated ESS-M maintained accuracy while incorporating vasomotor sensor data.

Computer-assisted scoring algorithms serve as an additional independent validation layer, providing a mathematical analysis that can be compared to the examiner's manual scores. The combination of manual examiner scoring and computer algorithm results provides a robust system of checks and balances. The APA Standards of Practice require that examiners use evidence-based validated testing techniques and maintain documentation supporting their scoring decisions [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods. Practicing examiners must also complete a minimum of 30 continuing education hours every two years [5]Verified APA Standards of Practice
Confirms APA Standards of Practice effective August 23, 2024, requiring validated techniques and evidence-based scoring methods. For insight into how professional polygraph services maintain these standards, see our guide to how polygraph services work.

Technological Advances in Chart Analysis

Computer-assisted scoring algorithms have become an integral component of modern polygraph practice, providing objective and reliable measurement for evaluating physiological data. These systems reduce subjective human bias and provide perfect scoring reliability — computers will always produce the same result when analyzing the same data.

PolyScore: Developed by the Johns Hopkins University Applied Physics Laboratory (JHU-APL), PolyScore is one of the most prominent computerized polygraph scoring systems. The algorithm was developed using polygraph data from actual criminal cases provided by DoDPI. The input is digitized polygraph signal data, and the output is a probability of deception based on logistic regression or neural network models. PolyScore is integrated into both Axciton and Lafayette polygraph instruments.

Computerized Polygraph System (CPS): Developed by Scientific Assessment Technologies based on research at the University of Utah psychology laboratory by John Kircher and David Raskin, CPS uses standard multivariate linear discriminant function analysis to produce an estimate of the probability of truthfulness or deception. The Stoelting polygraph instrument uses CPS [14]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore developed at JHU-APL, CPS developed at University of Utah; reviews computerized scoring algorithms.

Objective Scoring System, Version 3 (OSS-3): Developed and validated by Raymond Nelson, Mark Handler, and Donald J. Krapohl (2007, 2008), the OSS-3 is a free and open-source algorithm based on sound polygraph testing principles derived from existing research. The OSS-3 demonstrated balanced sensitivity and specificity, and outperformed 10 human scorers in brute-force comparison testing. It is available as a probabilistic classifier for both diagnostic and screening polygraphs and is integrated into the Lafayette LXSoftware platform.

Empirical Scoring System (ESS): Also developed by Nelson, Handler, and Krapohl, the ESS is an evidence-based normative system for manual test data analysis [12]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring methodology, published by Academic Press/Elsevier. Validation data for the ESS encompasses 5,192 scored results of 732 confirmed examinations, scored by 140 experienced and inexperienced scorers in 16 cohorts [12]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring methodology, published by Academic Press/Elsevier. Nelson (2017) published updated numerical distributions for the ESS-M, maintaining diagnostic accuracy while incorporating vasomotor sensor data.

Polygraph Automated Scoring System (PASS): Referenced in research at the University of Utah, PASS is a prototype scoring algorithm evaluated for effectiveness in analyzing mock crime experimental data [9]Verified Effectiveness of the IZCT with Various Scoring Systems in a Mock Crime Experiment
Systematically compared three scoring approaches for the IZCT in controlled environment.

Lafayette Instrument Company (now incorporating Limestone Technologies, acquired in August 2022) includes proprietary scoring algorithms in their polygraph software platforms, including the Polygraph Pro Suite which offers scoring utilities and algorithms for post-test chart review. Learn more about polygraph hardware in our guide to polygraph equipment.