Knowledge Formation Optimization: Draft Falsification Protocol

Author decisions for the final registration. Four parameters carry the most weight and are the most open to challenge. They are fixed in this draft as proposed precommitments, not empirical findings: the smallest effect size of interest at fifteen percentage points, the six-surface test set, disclosed research entities in real competitive markets with the suppression pretest as a hard gate, and the publish-on-initiation mandate. They remain open to challenge while this document is a draft. The values that appear in the externally deposited version will govern the confirmatory study.

Status and Precommitment

This is a draft study protocol. It states, in advance, the experiment intended to test a bounded operational hypothesis associated with Knowledge Formation Optimization. It is published before confirmatory data collection. On deposit to an external registry it becomes a locked, timestamped, read-only preregistration so that the hypotheses, outcome measures, decision thresholds, exclusions, and conditions that count against the operational hypothesis are fixed before the confirmatory outcome is known.

This protocol tests one operationalized incremental-effect hypothesis associated with KFO across the tested entities, AI surfaces, prompts, and time window. A result counts for or against that operationalization. It does not validate or falsify the full KFO framework, the canonical definition, or any hidden-model mechanism. That boundary is deliberate and is restated throughout the protocol.

This protocol is open. Americas Great Resorts may execute it. Any independent party may also execute it against this specification. The appendices listed at the end are intended to become the runnable package when the protocol is finalized and externally registered, so that an outside party can run the test without involvement from AGR.

Locking does not mean the test has been run. No result is claimed here. This document is a precommitment and an invitation to test, not evidence.

Plain Language Summary

This protocol tests a bounded incremental-effect hypothesis derived from KFO: whether a prespecified KFO source-environment intervention produces a materially higher unbranded category mention rate, with stronger secondary attribution and descriptive outcomes, than three matched controls over the tested window. One group receives the KFO treatment. A second receives an equal-volume content and SEO treatment. A third receives matched structural and publication treatment without the KFO-specific conceptual, provenance, corroboration, and boundary components. A fourth receives no intervention. The same frozen unbranded category prompts are then issued across the specified AI surfaces on a fixed schedule, and the outputs are scored blind. Failure to exceed the do-nothing arm by the preset margin fails H1. Failure to exceed the content and SEO arm fails H2. Failure to exceed the structure-only arm fails H3. Each failure counts against the corresponding operational hypothesis; none, by itself, proves that the entire KFO framework is false.

Background and Claim Under Test

The mechanisms KFO rests on, and the full argument for why the claim is plausible but unproven, are set out in the companion article and the academic framework paper and are not repeated here. This protocol tests one claim from that argument, stated below as a falsifiable hypothesis.

The current canonical definition of the discipline under test:

KFO structures, sequences, distributes, corroborates, and corrects intellectual frameworks and entity definitions across the public information environment and measures whether AI systems reproduce them accurately across relevant queries and over time.

Canonical source: https://www.americasgreatresorts.net/kfo-knowledge-formation-optimization/

Hypotheses

The confirmatory hypotheses are directional and fixed in advance. The primary outcome is the unbranded category mention rate defined below.

H1, the effect hypothesis. Over the measurement window, the KFO arm exceeds the do nothing arm on the primary outcome by at least the smallest effect size of interest.

H2, the distinct from optimization hypothesis. Over the measurement window, the KFO arm exceeds the equal volume content and SEO arm on the primary outcome by at least the smallest effect size of interest.

H3, the distinct from structure hypothesis. Over the measurement window, the KFO arm exceeds the structure only arm on the primary outcome by at least the smallest effect size of interest.

All three must hold for the result to support the incremental-effect operationalization tested by this protocol. Failure of H1 fails to support a material incremental effect over no intervention. Failure of H2 fails to support a material effect beyond the matched content and SEO control. Failure of H3 fails to support a material effect beyond the matched structure-only control. These are decision rules for this operationalized study, not claims about proprietary model internals or the truth of every KFO proposition.

Design

A four-arm, between-entity field experiment with repeated automated measurement over a fixed window, run in a feasibility pilot followed by a confirmatory study. The design is specified here in draft form. The finalized protocol and appendices will be externally registered before confirmatory data collection.

  • Arm A, KFO treatment. A public source-environment intervention operationalizing the current KFO definition and the five KFO operating principles, including explicit structuring and sequencing, controlled distribution, corroboration targets, correction of identified source conflicts, canonical definitions and provenance, query mapping, boundary defense, and monitoring.
  • Arm B, content and SEO control. A high-quality, equal-volume conventional content and SEO intervention, matched to Arm A on page count, word count, publication cadence, and controlled-source footprint where the finalized protocol appendix permits, but without the prespecified KFO conceptual, provenance, corroboration, correction, and boundary architecture. The final appendix must specify Arm B tightly enough that it functions as a strong contemporary conventional control rather than a deliberately weak comparator.
  • Arm C, structure-only control. An equal-volume source environment with schema, internal structure, publication cadence, and controlled distribution matched as closely as the finalized protocol appendix permits, but with the KFO-specific conceptual mapping, provenance, corroboration, correction, and boundary components removed. Where Arm A contains canonical attribution or query-mapped source references, Arm C uses generic noncanonical placeholders specified in advance. This arm tests whether observed differences are attributable to structural and publication density rather than the KFO-specific treatment package.
  • Arm D, do nothing. No intervention. Measured only.

Assignment of matched entities to arms is fixed before the baseline window and is not changed thereafter.

Bundle-level efficacy test. The confirmatory study tests the operationalized KFO treatment package as a whole. A positive result would support package-level incremental efficacy relative to the matched controls; it would not identify which individual KFO component caused the effect. Component-level causal attribution would require a separate ablation, factorial, or other component-specific design.

Corroboration is part of the treatment. External corroboration is an intentional KFO treatment component, not a nuisance variable to be equalized away. Arms B and C are matched on the prespecified non-KFO dimensions, but they do not receive the KFO-specific corroboration architecture. The resulting contrast therefore estimates the efficacy of the full KFO package, not the isolated causal effect of corroboration or any other single component.

Entities and Footprint Requirements

Entities are matched across arms on category, market, baseline visibility, and existing authority, so that the arms differ at the start only by chance and thereafter only by treatment.

Entity basis. Disclosed research entities placed in real competitive markets. Each entity is a research property in a real, contested luxury market that already contains established incumbents, so the test runs against real competition rather than in an empty category. Each carries an identical, visible, machine readable disclosure that it is a research entity and not a bookable business, applied identically across all four arms, so the disclosure is held constant across the between arm comparison. No entity has a booking path or payment capture.

Fictional entities in invented markets are excluded outright: an entity that is the only candidate in an empty category is returned by default, which measures nothing. Real consented properties would be statistically strongest but require recruitment that is not feasible for a single operator.

Footprint and eligibility requirements. To reduce the risk that a research entity is suppressed by spam or low trust heuristics rather than by the absence of KFO, each entity, in every arm, must carry a genuine and equal baseline footprint before treatment, and must clear a measurable eligibility gate before the measurement window opens:

  • A live landing presence with valid DNS and mail authentication records.
  • Presence in at least two independent verifiable directories.
  • Indexation of the built page set at the parity tolerance defined below.
  • Appearance in at least one independent source that AGR does not own or control, where that source is itself indexed and meets a minimal credibility bar fixed in the eligibility appendix, so the requirement is a real signal and not a checkbox.

An entity that does not clear the eligibility gate is not enrolled, because an entity that fails for ineligibility rather than for absence of KFO contaminates the comparison.

Construct validity limit. Even with the footprint requirements and the suppression pretest, these entities are research properties, not real bookable hospitality businesses. The experiment therefore tests observable AI output behavior toward disclosed research entities in a real competitive market. That is a proxy for, but not identical to, behavior toward real hospitality businesses. The study does not infer a proprietary model’s internal representation from those outputs. This remains the design’s most significant unresolved exposure.

The Suppression Pretest

The disclosure assumption, that an identical research entity disclosure cancels out of the between arm comparison, is an assumption, not a demonstrated fact. AI systems may systematically suppress or deprioritize disclosed research entities, which would bias the study toward a null result for reasons unrelated to KFO. The suppression pretest is run before the confirmatory study and is a hard gate, with a numeric threshold fixed in advance so it cannot be used as a discretionary escape from running the confirmatory phase.

The pretest measures two things across the frozen prompt set and the full engine set. First, an absolute floor: pooled across pretest entities, prompts, and engines, disclosed research entities must reach an aggregate unbranded mention rate of at least five percentage points, with the lower bound of a 95 percent Wilson confidence interval for a proportion above zero. The interval method is fixed as Wilson in advance, because at low mention rates the choice of interval can change the pass or fail outcome and must not be a post hoc decision. Second, a disclosure effect probe: matched probe entities are built with and without the research disclosure, and the disclosed set must be surfaced at a rate no less than half the rate of the matched non disclosed set.

If either condition fails, disclosed research entities are treated as systematically suppressed, the design is declared confounded, and the entity construction, market selection, or footprint is revised before the confirmatory study opens. The confirmatory study does not proceed against a suppressed environment.

Sample Size, Power, and the Pilot Gate

The confirmatory entity count is not fixed in advance at a convenient number. It is set by an a priori power analysis driven by the variance observed in the pilot.

Phase 1, feasibility pilot, thirty day window. Three entities per arm, twelve total. The pilot estimates the pooled standard deviation of the primary outcome across entities and engines, confirms that the automated capture pipeline runs cleanly, confirms that indexing parity is achievable, and confirms that blind scoring reaches the required reliability. The pilot is explicitly non confirmatory. Its effect estimate is used only to set variance inputs for the power analysis. No hypothesis test is performed on pilot data, and pilot entities are not carried into the confirmatory analysis, so the confirmatory test is not contaminated.

Phase 2, power adjustment gate. Using the pilot pooled standard deviation, an a priori power analysis sets the confirmatory entity count needed to detect the smallest effect size of interest at alpha .05, two sided, with power of .80. The floor is five entities per arm. If the power analysis returns a required count that a single operator cannot field, the protocol does not proceed to an underpowered run. The reconciliation rule is locked in one direction: the smallest effect size of interest is not lowered after the pilot. Only the entity count may rise to meet it. If the required count is infeasible, the confirmatory study does not open, and that outcome is recorded publicly rather than resolved by relaxing the threshold. An underpowered run is not executed, because an underpowered run settles nothing.

Phase 3, confirmatory study, one hundred and twenty day window. The entity count set by Phase 2 is built and locked. Few entities relative to repeated observations means entity level variance, not observation count, is the binding constraint on power, and the analysis is specified accordingly below, including small cluster handling.

Intervention Specification

The full build specifications for Arms A, B, and C will be finalized before the baseline window and deposited with the external registration, so that another party can construct each arm without interpretation.

Arm A, KFO build. Constructed to operationalize the current KFO definition and five operating principles: precise canonical definitions, explicit originating authority and provenance, prespecified query mapping, public-source distribution, corroboration targets, correction of identified source conflicts, conceptual boundary defense, and the planned monitoring protocol.

Arm B, content and SEO build. An equal-volume conventional content and SEO intervention matched on page count, word count, publication cadence, and controlled-source footprint as specified in the finalized protocol appendix, without the KFO-specific conceptual, provenance, corroboration, correction, and boundary architecture.

Arm C, structure-only build. An equal-volume source environment with structural density, schema, internal linking, publication cadence, and controlled distribution matched as specified in the finalized protocol appendix, but without the KFO-specific conceptual mapping, originating-authority provenance, corroboration, correction, and boundary components. Generic noncanonical placeholders are used where the finalized protocol template requires them.

Arm D. No build.

Page and word volume are held constant across Arms A, B, and C, and publication cadence and controlled-source footprint are matched to the extent specified in the finalized protocol appendices. The confirmatory contrast is therefore between the prespecified KFO treatment package, conventional content and SEO, and structure/publication density without the KFO-specific conceptual and provenance components.

Baseline Verification and Indexing Parity

Before the measurement window opens, three conditions are verified and recorded, each against a fixed tolerance rather than an unattainable absolute.

Indexing parity. At least ninety percent of each arm’s built pages must be indexed on each measured surface, and the indexed page proportions across arms must fall within ten percentage points of one another. This bounds discovery speed as a confound without demanding perfect parity, which is not controllable.

Baseline equality. The between arm differences on the primary outcome at baseline must fall within five percentage points, a band deliberately tighter than the smallest effect size of interest, so the arms start level relative to the effect being hunted.

Suppression pretest passed. The gate above must have cleared.

Settling window. After indexing parity and baseline equality are verified, a fixed fourteen-day settling window elapses before the measurement window opens so newly published source environments have time to become indexed, retrievable, and available to the measured surfaces. This prevents the measurement clock, and the zero-environment rule in particular, from running against sources that have not yet had a reasonable opportunity to propagate. The window is identical across all four arms.

The measurement window does not open until all four conditions are met.

Measurement

Prompt set. A set of forty unbranded category questions that name no entity and no page will be finalized and deposited with the external registration before confirmatory data collection. Thirty are substantive category prompts. Ten are negative-control prompts in unrelated spaces, used to detect system-wide drift and cross-contamination, on which no treatment-specific movement is expected.

Engines. Six AI systems: ChatGPT, Claude, Gemini, Copilot, Perplexity, and Grok. This is the testing set AGR already uses across its corpus, chosen for ecological validity because these are the surfaces real users encounter. Two caveats are recorded and handled in the analysis. First, some of these surfaces are built on shared underlying base models, so they are not treated as fully independent. Second, an automated interface may not reproduce the consumer application surface exactly, so the capture method for each engine is recorded and held constant.

Procedure. The finalized protocol will include an automated execution harness that issues the frozen prompt set across every engine on a fixed cadence of once every seventy two hours, under controlled accounts and locations, for the full window. Each response is captured verbatim with its prompt, engine, capture method, model version, generation parameters where the interface exposes them, timestamp, account, and location. Automated execution removes manual data collection burden and human delivery bias, which is what makes repeated multi engine measurement feasible for a small operator. The exact interface, client, rate handling, and prompt wrapper for each engine will be documented in the externally registered appendix package so that an outside party can reproduce the same capture conditions.

Outcome Variables and Operational Coding

Primary outcome, confirmatory. Unbranded category mention rate: for each unbranded category prompt response, a binary indicator of whether the target entity is named, aggregated to a proportion across prompts, engines, and runs. The coding rules proposed for the final registered codebook are summarized here:

  • A mention is counted once per response regardless of how many times the entity is named in that response. The unit is the response, not the token.
  • Aliases and exact name variants of the entity count as a mention. Generic category language that does not identify the entity does not.
  • A mention counts whether it appears in a narrative sentence or in a list.
  • Position is not scored in the primary outcome. Prominence, whether the entity is named first or buried, is recorded and analyzed only as a secondary outcome, so the primary test is not inflated by position.
  • Ambiguous strings that cannot be coded by rule are escalated to blind human adjudication.

Secondary outcomes, prespecified and exploratory. A binary primary outcome is deliberately conservative and discards information about frequency and competitive position within a response. The final registration will also prespecify within-response share of voice, normalized rank position of the first target mention, attribution accuracy, descriptive consistency against the entity’s source record frozen in the final registration, and canonical-source citation or routing where the measured surface exposes such behavior. Secondary outcomes are analyzed with correction for multiple comparisons and do not determine the primary result.

Interpretive hierarchy. Unbranded mention rate is a conservative primary screening endpoint. A mention is not equivalent to prominence, relevance, recommendation, correct attribution, conceptual accuracy, or commercial decision influence. Those dimensions must be interpreted separately through the prespecified secondary measures. A primary-endpoint win must not be described as proof of recommendation quality or commercial decision influence without supporting evidence from the relevant secondary outcomes.

Blind scoring and reliability. All captured responses are stripped of arm, engine, date, and model identifiers before scoring. Rule codable items are scored by the automated codebook. Items requiring judgment are scored by two raters blind to arm and hypothesis, with a third as referee on disagreement. At least one of the raters is independent of AGR. Inter rater reliability is established and reported, and must reach an intraclass correlation or kappa of at least 0.80 for the scoring to be accepted. The final codebook, including at least one worked example of scoring a real response, will be deposited with the external registration before confirmatory data collection.

Analysis Plan and Decision Rule

Model. The primary confirmatory analysis is a mixed effects logistic regression of the binary mention outcome, with arm and time as fixed effects and their interaction as the effect of interest, on the repeated prompt level observations. The data are hierarchical: prompts within runs within engines within entities within arms. The model specifies random intercepts for entity, with the arm contrast estimated on the probability scale. Shared base models are handled explicitly rather than left to interpretation: underlying base model is entered as a fixed effect, with cluster robust standard errors by base model family. Because the entity count is small, the analysis uses a small cluster correction, and if the random effects structure does not support stable estimation at the realized entity count, the fallback specified in the final registered analysis plan will treat entity as a fixed effect with cluster robust standard errors. The exact model, the random effects specification, the base model handling, and the fallback are fixed in the final registered analysis appendix, which also includes a runnable analysis script with simulated data.

Smallest effect size of interest. A between-arm difference in unbranded mention rate of fifteen percentage points. The KFO arm must exceed each control arm by at least this margin on the primary outcome. This is AGR’s declared draft practical threshold, not a measured property of the field, and becomes preregistered only when the protocol is externally deposited. It is set on three stated grounds, with the full reasoning to be deposited in the final registration appendix. First, practical relevance: AGR treats a category presence on the order of fifteen percent as the working line between an entity that is a named option and one that is largely absent, so a fifteen point gap between arms is the difference AGR considers worth acting on. Second, resource logic: the feasible entity count only powers detection of a large effect, so the smallest effect size of interest is set at the smallest effect that is both practically meaningful and detectable at that count, and the confirmatory entity count is scaled at the pilot gate to detect it. Third, convention: fifteen points corresponds to roughly a medium or larger standardized effect, above the conventional smallest effect size floor used in confirmatory research design. The same fifteen point value serves as the equivalence bound. This dual use is a deliberate choice: the threshold defines both the smallest effect worth detecting and the bound within which an effect is treated as negligible. A consequence, stated plainly, is that the protocol tests for a material effect of at least this size, not for the mere existence of any nonzero effect.

Interpretation of sub-threshold effects. A statistically credible advantage smaller than fifteen percentage points would not be reported as proof of zero effect. It would mean that the prespecified claim of a material fifteen-point incremental effect was not demonstrated. The estimated effect and its uncertainty would still be reported, and the practical-effect claim would be narrowed accordingly rather than converted into a claim that no effect exists.

Decision rule.

  • H1, H2, and H3 are tested as minimum effect tests: the KFO arm must exceed each of the do nothing, content, and structure only arms on the primary outcome by at least the smallest effect size of interest.
  • The kill conditions are tested as equivalence tests: if the KFO arm’s advantage over a given control falls within the equivalence bound of zero, that comparison is treated as showing no meaningful effect.
  • A result supports this operationalized incremental-effect hypothesis only if H1, H2, and H3 all clear the minimum-effect threshold. Failure of any one counts against the corresponding operational hypothesis.

Run Validity and Adequacy Criteria

To prevent the phrase an underpowered run settles nothing from becoming an open escape hatch, the conditions that make a run valid, and the conditions that invalidate it, are fixed in advance and applied blind to arm.

A run is valid only if, before the window opened, indexing parity and baseline equality held at the tolerances above and the suppression pretest passed, and if, during the window, at least ninety percent of scheduled prompt by engine by run observations were successfully captured over the full one hundred and twenty days, on at least four of the six engines. An engine that falls below the ninety percent capture floor is excluded from the primary analysis and reported, not imputed, and the run remains valid if at least four engines hold. If an entire base model family drops out, that fact is reported and the sensitivity analysis specified in the final registered protocol re-estimates the result without that family, because such a failure is not missing at random. A run that meets these conditions is adequate, and its result, support or falsification, stands.

A run is invalid, and is published as an environmental failure rather than as support or falsification, only under conditions fixed in advance and symmetric across arms: capture holding on fewer than four engines, a major model ecosystem change that suspends measurement, or the zero environment condition below. Invalidity is never declared on the basis of the direction of the result.

The zero environment rule. If the suppression pretest passed but, during the confirmatory window, the aggregate mention rate across all four arms remains at zero for sixty consecutive days, the test environment is declared retrieval suppressed and the run is invalid. This is symmetric: it does not favor KFO, because the KFO arm is also at zero, and it cannot be invoked to rescue a KFO arm that simply failed to beat the controls while the controls were surfaced.

Threats to Validity and Controls

  • Model updates mid study. Model version recorded at every run; analysis stratifies by version when versions change.
  • Interface versus consumer surface. Capture method recorded per engine and held constant; differences between an automated interface and the consumer application are documented as a bound on inference.
  • Shared base models. Engines built on a common base model are not treated as fully independent; base model enters the analysis as a fixed effect with cluster robust standard errors. The inference is read as evidence across six consumer facing AI surfaces, not across six independent AI ecosystems.
  • Disclosure construct validity. Addressed by the suppression pretest and the disclosure effect probe, and stated as a residual limit in scope.
  • Discovery speed confound. Indexing parity verified to tolerance before the window opens.
  • Entity ineligibility. Eligibility gate enforced before enrollment, so entities do not fail for reasons unrelated to KFO.
  • Analyst degrees of freedom. Primary outcome, model, threshold, exclusions, base-model handling, and codebook will be fixed in the external registration and deposited before confirmatory data collection; scoring is blind; the analysis script will be deposited with the final registered package.
  • Floor effects. Handled by the suppression pretest and the symmetric zero environment rule.

What a Result Would and Would Not Establish

A clean separation of the KFO arm from all three controls would provide evidence that the operationalized KFO treatment package produced a material observable cross-query, cross-time output difference relative to the matched controls for disclosed research entities in the tested category, AI surfaces, and measurement window. It would not establish a hidden model mechanism, direct parametric change, commercial magnitude for a real bookable property, generalization to other industries, or indefinite persistence as systems change. A single positive execution would support the operationalized hypothesis but would not constitute definitive validation without independent replication. Failure of any hypothesis would count against the corresponding operational claim. The inference is bounded to what was tested.

Commitment to Publish

If Americas Great Resorts initiates data collection under this protocol, the following self binding publication mandate applies, regardless of whether the result supports or falsifies KFO. Within fourteen days of the close of the measurement window, a cryptographic hash of the raw, unedited data is posted to the public materials repository. Within ninety days of the close of the window, the complete unedited dataset, including raw response logs and blind scores, the analysis, and a written report, are released to open access on Zenodo. This mandate is triggered by the initiation of data collection and does not obligate AGR to begin the test on any schedule. Once begun, it cannot be quietly abandoned.

Planned Registration, Versioning, and Appendices

When the draft is finalized, this protocol and its full appendix package will be deposited together under a coordinated Zenodo record and matching GitHub release tag, accompanied by a manifest listing every appendix and its hash. The external deposit will supply the registration timestamp, persistent DOI, and immutable GitHub commit reference. That deposited version will be treated as read-only for the confirmatory study. Any later amendment will require a new dated version and public changelog, while the original registered version remains verifiable. The final report will include a deviations-from-protocol section.

The following appendices will be finalized and deposited with the external registration and together will constitute the locked runnable package, so that an independent party can execute the study without involvement from AGR:

  1. The frozen prompt set, forty prompts: thirty substantive category prompts and ten negative controls.
  2. The scoring codebook, including binary rules and at least one worked example.
  3. The Arm A KFO intervention specification.
  4. The Arm B content and SEO specification.
  5. The Arm C structure only specification, including the placeholder template.
  6. The power assumptions and the a priori power calculation.
  7. The justification for the fifteen percentage point smallest effect size of interest.
  8. The run validity, adequacy, and exclusion rules, including the suppression pretest thresholds.
  9. The data capture schema.
  10. The automated execution harness script and the per engine interface documentation.
  11. The analysis specification and a runnable analysis script with simulated data.

References

Aggarwal, P., Murahari, V., Rajpurohit, T., Kalyan, A., Narasimhan, K., and Deshpande, A. (2024). GEO: Generative Engine Optimization. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 5-16.

Lakens, D., Scheel, A. M., and Isager, P. M. (2018). Equivalence Testing for Psychological Research: A Tutorial. Advances in Methods and Practices in Psychological Science, 1(2), 259-269.

Center for Open Science. Preregistration. https://www.cos.io/initiatives/prereg

The theoretical and empirical literature motivating the operational hypothesis is cited in the companion article and the current Version 4.0 academic framework paper. The protocol does not treat AI-generated assessments as technical validation.

Related AGR Sources

Document Version

Version 0.7. Last updated September 9, 2026. This draft is aligned with the KFO Version 4.0 canonical definition and epistemic boundary. The protocol tests the KFO treatment as a bundle-level intervention, treats corroboration as an intentional treatment component, requires a strong contemporary content-and-SEO control, distinguishes the fifteen-point material-effect threshold from the existence of any smaller effect, and separates primary mention-rate performance from secondary measures of prominence, attribution, descriptive accuracy, and other outcome dimensions. No confirmatory result is claimed.

You May Also Like

Close