> For the complete documentation index, see [llms.txt](https://docs.nested-knowledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nested-knowledge.com/resources/glossary.md). # Glossary Quickly look up terms used in Nested Knowledge. ### A **Abstract (AB)**: A study's abstract. Abbreviated AB throughout Nested Knowledge, as in AB screening (screening on abstracts). **Abstract Editor**: The tool in AutoLit for composing a structured abstract of the review, supported by Smart Abstract. **Adaptive Smart Tags (ASTs)**: An AI tagging tool that extracts the custom tags in your tag hierarchy for each filtered study. Works on abstracts and full texts, in standard mode or High Fidelity mode, which extracts texts, tables and figures from full-text pdfs. **Adjudication**: Resolving disagreements between reviewers to reach a final decision. In dual screening, an adjudicator settles the records two reviewers judged differently. Meta-analytical extraction and critical appraisal can be adjudicated the same way. **Advance**: To move a record forward to the next stage of the review — for example advancing a record from abstract to full-text screening. **Advanced Study Inspector**: A more powerful mode of Study Inspector, offering advanced filtering and querying across a nest's records. **Advancement/Inclusion Probability**: The score Robot Screener assigns each record, estimating how likely it is to be included; used to rank records and, optionally, to screen automatically. **Allocation**: Allocation enables you to assign Screening and other modules to specific users for sets of records. Turn on Allocation in Nest Settings and allocate records on various criteria. **Annotation**: A highlighted excerpt from a study's full text that captures the evidence behind a tag or an extracted value. You can annotate while tagging, during meta-analytical extraction, or directly on the full text. **API**: An application programming interface for interacting with external sites within Nested Knowledge. APIs are used to connect to external search engines in Nested Knowledge. **Arm (study arm)**: A single group within a study — such as the treatment arm or the control arm — that meta-analytical extraction captures data for separately. **Auto Adjudicate**: A dual-screening option that automatically finalizes the records both reviewers agreed on, leaving only their disagreements for manual adjudication. **AutoLit**: the interactive workspace where a review is built, from literature search through screening, tagging, meta-analytical extraction, and critical appraisal. Its counterpart is Synthesis, which presents the results. ### B **Background Jobs**: Nested Knowledge processes long-running tasks, such as large imports, AI runs, or exports, in the background so you can keep working while they finish. Access them through the three-line icon in the top-right corner of every page. **Bibliographic data**: The citation metadata attached to an imported record: its title, authors, journal, year, identifiers, and abstract. There is no need to create additional tags for bibliographic data. **Bibliomine**: A tool that mines the reference lists of uploaded studies to surface additional records for screening — a form of citation chasing. **Bulk Actions**: Operations applied to many studies at once from Study Inspector — such as updating screening decisions, applying or removing tags, document import etc. ### C **CER Builder**: A tool for exporting auto-generated Clinical Evaluation Report (CER) materials from a nest's data. **Child tag**: A tag nested directly beneath a parent tag in the tag hierarchy. **Children (when adding a tag column in an export table)**: When adding a tag column to an export table and children is toggled on, the selected tag is the column header and the child tags of the selected tag will be displayed in the cells beneath if applied to that study. See **Contents.** **Comments**: Notes left on specific records or on Nest Home for your team to discuss; comments can be resolved once they've been addressed. **Concepts (search exploration)**: In Search Exploration, the key topics surfaced from your records, used to see what a search is capturing and to refine the query. **Configure**: To set up a module's rules before work begins — for example screening criteria, the tag hierarchy, or extraction data elements. **Contents (when adding a tag column in an export table)**: When adding a tag column to an export and contents is toggled on, the selected tag is the column header and tag contents is displayed in the cells beneath if applied to that study. If Children is also toggled on, contents are also shown to child tags. See **Children.** **Core Smart Tags (CSTs)**: Ready-made AI tags for standard study characteristics such as Population, Interventions, Comparators and Outcomes (PICOs), study design, size, and location. These are built and extracted from study abstracts only using your research question. **Criteria-based screening (CBS)**: A screening approach in which each record is judged against an explicit list of yes/no inclusion criteria. **Critical Appraisal (CA)**: The module where studies are assessed for risk of bias or quality against an appraisal framework. It can be done by one reviewer or dual, and feeds critical appraisal visuals in Synthesis. **Custom Table Export**: A configurable export that turns a nest's extracted data into a formatted table for immediate download. See also Export, Dashboard. ### D **Dashboard**: A living visual summary of a nest's data, including tables and insights, configured in the Dashboard Editor and viewed in Synthesis. Unlike an export, it stays current as the underlying data changes. **Data Elements (in Meta-Analytical Extraction)**: In Meta-Analytical Extraction, the outcomes and measurements configured and extracted for each intervention — shown in gold, as distinct from interventions (purple). **Dendrogram**: A branching, tree-style visualization of a nest's tag hierarchy in Qualitative Synthesis. See also Sunburst. **DOI**: Digital Object Identifier — a persistent, unique identifier for a publication. **Dual screening**: A screening mode in which two reviewers screen each record independently and disagreements go to an adjudicator. It supports a more rigorous, auditable process and unlocks Screening Agreement statistics. **Duplicate Review**: The step where records imported more than once across search sources are identified and automatically merged, so each study is screened only once. Download and clear queue here. ### E **Examine**: An setting on the Configure Tag Hierarchy page to select a tag and examine associated records. **Explore NMA**: The interactive network meta-analysis view in Synthesis, for examining comparisons across three or more interventions, including indirect ones. Generated upon completion Meta-analytical Extraction. **Export**: A one-time download of a nest's data — for example a custom table export or a download from Study Inspector. Contrast with the Dashboard, which is a living output. ### F **Filter**: A condition that narrows the studies shown — by tag, screening status, or other attributes — in Study Inspector and across Synthesis. **Form-based Tagging**: A tagging configuration that presents the tag hierarchy as a form to complete for each study, suited to structured, questionnaire-style capture. Contrast with Standard Tagging. **Full Text (FT)**: A study's complete text, beyond its abstract. Abbreviated FT throughout Nested Knowledge, as in FT screening (screening on full texts). ### G **Google Scholar**: A freely accessible web search engine for scholarly literature, usable as a source when building a nest's records. ### H **History**: The log of actions taken on a study, showing what changed and when. Displayed as a left-hand tab on each study. ### I **Import**: Bringing records or data into a nest from an outside source — search files, full texts, or existing screening decisions and tags. **Include**: To mark a record as meeting the criteria, keeping it in the review; the opposite of exclude. Used at Full Text Screening or during single Screening. **Inspector**: Shorthand for Study Inspector. **Interrater reliability (Cohen's kappa)**: A measure of how consistently two reviewers agree beyond what chance alone would produce. Nested Knowledge reports it live as Cohen's kappa in Screening Agreement when dual screening is in use. **Intersections**: In Literature Search, when multiple searches are added, intersections is the overlap used to explore how tags relate. **Interventions**: The treatments or exposures under study — the "I" in PICO. In Meta-Analytical Extraction, interventions (shown in purple) are one of the two things you configure and extract, alongside data elements. ### K **Keywords**: The individual terms that make up a search query or configurable words to highlight in an abstract or full text to enhance screening. ### M **Manuscript (Manuscript Editor)**: The review's written write-up. The Manuscript Editor in AutoLit is where it's drafted from the nest's synthesized data and visuals. The manuscript is viewable as a separate tab in Synthesis. **Mentions**: Tagging a teammate in a comment on a specific study or in Nest Home with @ to notify them and draw their attention to it. **Merge**: To combine and merge data between two tags in the Tag hierarchy. **Meta-analysis (MA)**: The statistical pooling of results across studies to estimate an overall effect. In Nested Knowledge, meta-analyses are produced in quantitative synthesis upon completion of the optional module Meta-Analytical Extraction. **Meta-Analytical Extraction (MA Extraction)**: The optional module where quantitative data — interventions, outcomes, and other data elements — are extracted from studies to support meta-analysis and Quantitative Synthesis. Toggle on in Nest Settings. ### N **Navigation**: The menu along the side of a study during a review stage for moving between studies: Back or Skip. **Nest**: A single review project in Nested Knowledge: its records, screening decisions, tag hierarchy, extracted data, and outputs, all in one place. As a rule of thumb, one review equals one nest. **Nest Copy**: A duplicate of an existing nest, made to branch off a new review, run an update, or rebuild structure without touching the original. **Nest Home**: A nest's landing page, summarizing its status and giving access to each module. **Nest Version**: A saved state of a nest at a point in time, used to track a living review across its updates. Viewable in Nest Settings. **Network meta-analysis (NMA)**: Meta-analysis that compares three or more interventions at once, combining direct and indirect evidence. Explored interactively in Synthesis through Explore NMA. ### O **Organization**: A workspace that groups a team's nests, members, and settings under Organization Management. Organizations enable organization-level activity reporting, shared templates, and access control. ### P **Parent tag**: A tag that has other tags nested beneath it in the hierarchy. See also Child tag, Root tag. **PICO**: The Population, Intervention, Comparator, Outcome framework for structuring a review question. Nested Knowledge's Core Smart Tags builds and extracts a PICO hierarchy in Tagging. **PMC**: PubMed Central — a free full-text archive of biomedical literature, and a source for retrieving full texts. **PRISMA chart**: The standard flow diagram showing how records move from search through screening to inclusion. Nested Knowledge generates it automatically for a nest and is viewable and downloadable in Synthesis. **Protocol**: A document that guides how a review should be conducted — its objectives, methods, and inclusion criteria — set before screening begins. **PubMed**: A free database of biomedical literature from the U.S. National Library of Medicine that Nested Knowledge can search and import from. ### Q **Qualitative Synthesis (QLS)**: The living, interactive part of Synthesis that presents data extracted from Tagging, as distinct from pooled statistics generated from Meta-Analytical Extraction. **Quantitative Synthesis (QNS)**: The living, interactive part of Synthesis that presents data extracted from Meta-Analytical Extraction, as distinct from Qualitative Synthesis. **Query**: The string of terms and operators submitted to a database to retrieve records. **Questions**: A tab displayed next to each study displaying question tags configured and extracted. ### R **Ref ID**: The unique identifier Nested Knowledge assigns to each record in a nest. **Related Report Family**: A group of related reports manually linked as reporting the same underlying study. **Related Reports**: Separate records that report on the same underlying study — linked together so the study isn't screened or counted more than once. **Robot Screener**: An AI screening tool that learns from reviewers' abstract screening decisions in dual screening and assigns include/exclude for the remaining abstracts. It's machine-learning-based and abstract-only; it can fill one reviewer seat but still requires a human co-reviewer and adjudicator. See also Smart Screener. **Root tag**: The single tag at the top of a nest's tag hierarchy, from which all other tags descend. See also Parent tag, Child tag. ### S **Screening**: The module where records are assessed in a queue against inclusion and exclusion criteria to decide which studies enter the review. It can be single or dual, at the abstract and/or full-text level. **Screening Agreement**: A built-in analytic in a nest's **Nest Activity** view. It appears only when dual screening is on. It shows inter-reviewer agreement and live Cohen's kappa. See also Interrater reliability. **Screening model**: The machine-learning model behind Robot Screener, trained on reviewers' decisions to predict include/exclude for the remaining records. **Search (Literature Search)**: The module where records enter a nest, whether by importing search files, running automatic searches, or adding other sources. It includes duplicate review and search exploration. **Smart Abstract**: An AI tool that drafts a structured abstract of the review from its data, which you then refine in the Abstract Editor. **Smart Critical Appraisal (SCA)**: An AI tool that suggests answers to a study's critical appraisal questions for a person to review. **Smart Insights**: An AI tool that generates written summaries — insights — from a nest's data for a person to review and export in Synthesis. **Smart MA Extraction**: An AI tool that assists meta-analytical extraction by suggesting values for the configured data elements, which a person reviews. **Smart Nest**: An AI tool that builds an entire nest using an inputted research question and utilizes each module's AI tool to do so. It's designed for rapid review generation and insights for review. **Smart Screener**: An AI screening tool that evaluates records against your configured screening criteria/questions, at the abstract or full-text level. Like Robot Screener, it can fill a reviewer seat in dual screening, but it always requires a human co-reviewer and adjudicator. LLM-based. See also Robot Screener. **Smart Search**: An AI tool that helps generate and refine literature search strategies based on a research question. **Smart Tag**: A tag whose values are populated by AI rather than entered by hand — see Adaptive Smart Tags and Core Smart Tags. **Smart tools**: Nested Knowledge's suite of AI features that assist reviewers across the pipeline. Each is optional, keeps a person in control of the final decision, and is documented individually (Robot Screener, Smart Screener, Adaptive Smart Tags, and more). **Standard Screening**: Nested Knowledge's default screening configuration, in which each record is screened in a single pass. Contrast with Two Pass Screening. **Standard Tagging**: Nested Knowledge's default tagging configuration, applying tags to studies through the tag hierarchy. Contrast with Form-based Tagging. **Study (record)**: An individual reference in a nest — a citation and the data attached to it — as it moves through search, screening, tagging, and extraction. Sometimes called a record; managed one at a time in Study Inspector. **Study Inspector**: The record-level view of a nest: a filterable, sortable list of every study, where you can inspect and edit a single study's full data, apply bulk actions, and export. **Sunburst**: A radial visualization of a nest's tag hierarchy in Qualitative Synthesis, each ring a level of the hierarchy. See also Dendrogram. **Supplements**: Supplementary files attached to a study record, such as appendices or supporting data. **Synthesis**: The output side of a nest, where results are presented and shared. It includes qualitative synthesis, quantitative synthesis, dashboards, the manuscript, Insights, and interactive visuals. Its counterpart is AutoLit, where the work is done. **Synthesis Chat**: An AI tool that answers natural-language questions about a nest, reading its live data at the moment you ask rather than a saved snapshot. Responds with text-based answers and table/figure outputs upon request. ### T **Tag**: A datapoint or set of datapoints recorded about a study. Think of a tag as a column in your exported dataset. In Nested Knowledge, a tag is not only an include/exclude screening label. It is the data you collect during tagging. Tags also form the basis for interventions and data elements in Meta-Analytical Extraction. See also Tag hierarchy. **Tag hierarchy**: The organized, nested structure of tags configured for a nest. It defines what data the review will collect and how it's grouped, and it determines the columns available in exports and the shape of Synthesis. **Tagging**: The module where the configured tags are applied to studies in a queue, capturing the datapoints that populate the dataset and Synthesis. **Two Pass Screening**: A screening configuration that splits the review into two passes — abstract screening first, then full-text screening of the records that advance. It's what enables the abstract- versus full-text-level view in Screening Agreement. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.nested-knowledge.com/resources/glossary.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.