Literature Intelligence
Search 18 scholarly sources, curate records and available full text, extract evidence, inspect citation structure, and carry selected sources into analysis and writing.
Search is discovery, not proof of completeness. Source coverage, indexing delays, query translation, access rights, and connector availability can all affect the result set. Preserve your query and manually verify searches used for formal reviews.
Where It Lives
Each CATO project has a Literature area with Deep Search for retrieval and analysis and Library for durable curation. Search results, saved works, evidence outputs, fetched papers, and generated literature artifacts remain connected to the project rather than to one browser session.
18 Scholarly Sources
| Source | Primary contribution |
|---|---|
| PubMed | Biomedical and life-science records, indexing, abstracts, and publication types |
| PubMed Central (PMC) | Open full-text biomedical articles |
| Europe PMC | Biomedical metadata, citations, grants, preprints, and available full text |
| Unpaywall | Open-access location resolution for DOI records |
| CORE | Repository and open research content |
| Crossref | DOI, publication, funder, and citation metadata |
| OpenAlex | Scholarly works, concepts, institutions, authors, and citation relationships |
| DataCite | Research outputs and dataset DOI metadata |
| Semantic Scholar | Scholarly metadata, abstracts, and citation relationships |
| arXiv | Physics, mathematics, computer science, quantitative biology, and related preprints |
| bioRxiv | Biology preprints |
| medRxiv | Health-science and medical preprints |
| ChemRxiv | Chemistry preprints |
| SSRN | Working papers and preprints across social science and other fields |
| Research Square | Multidisciplinary preprints |
| OSF | Open Science Framework projects, registrations, and preprints |
| Zenodo | Papers, datasets, software, and other research outputs |
| HAL | Open repository manuscripts, theses, and other scholarly records |
ClinicalTrials.gov and patent search are separate specialized connectors. They complement the 18-source scholarly search and should be selected intentionally for protocol, registration, results, or intellectual-property questions.
Query Studio
- State the research question, population, intervention or exposure, comparator, outcomes, and date range where relevant.
- Choose Evidence-first when established, well-supported results are the priority or Novelty-first when emerging work is the goal.
- Select the source families and study-type filters appropriate to the question.
- Run the query with the Search control or
Ctrl/Cmd+Enterwhile Query Studio is focused. - Inspect the translated search and per-source status, then refine terms if important concepts were lost.
Example
“Adults with resected stage II–III non-small-cell lung cancer; adjuvant immune checkpoint inhibitors versus chemotherapy or observation; disease-free and overall survival; randomized trials and systematic reviews; 2018 onward.”
Study-Type and Source Filtering
Filters can target randomized trials, meta-analyses, systematic reviews, cohorts, case-control studies, case series, case reports, and reviews. Where a source exposes structured publication types, CATO uses them in the source query; elsewhere it applies metadata and text-based classification after retrieval.
Classification is imperfect, especially for preprints and records with sparse abstracts. Review the article itself before making a study eligible or excluding it from a formal review.
Results, Deduplication, and Ranking
Results from enabled sources are normalized and deduplicated using available DOI, database identifier, title, author, and publication metadata. The grid retains source badges so you can see where a record was found. Ranking reflects the selected search mode and available metadata; it is not a measure of study quality or truth.
- Open a record to verify title, authors, venue, year, DOI or source ID, abstract, and links.
- Inspect apparent duplicates when a preprint, conference version, and journal article may represent the same work.
- Save eligible or promising works to Library; do not rely on transient result ordering.
- Record explicit reasons for exclusion outside a casual discovery workflow.
Full Text and the Workspace Reader
CATO resolves legally available open-access copies through sources such as PMC, Europe PMC, repositories, and open-access metadata services. A successfully fetched paper can open as a durable Workspace artifact for reading and supported annotation. When full text is unavailable, the interface identifies the available metadata or abstract rather than treating it as the complete paper.
Know the evidence boundary: an abstract cannot support detailed claims about methods, subgroup definitions, adverse events, adjustments, or limitations that appear only in full text.
Library and Collections
Library stores the works you want to keep across searches. Organize them into collections, inspect normalized identifiers and source links, add notes, and open available paper content. Tree and grid views support different curation styles.
- Use collections for protocol stages such as Candidate, Included, Excluded, Background, and Methods.
- Keep exclusion rationale separate from informal notes if it will enter a review audit trail.
- Resolve duplicate or conflicting metadata before citation export or manuscript generation.
- Prefer stable DOI, PMID, PMCID, preprint, registry, or repository IDs over title-only matching.
Evidence Matrix
Evidence extraction converts selected works into comparable structured fields such as population, intervention or exposure, comparator, outcomes, design, sample size, effect information, and potential bias or limitations. Extraction output is persisted as a research artifact so it can be reopened and used by later review or writing steps.
- Run extraction on a curated, manageable set rather than every search result.
- Open the supporting passage for every decision-critical field.
- Distinguish “not reported” from “not found in the text available to CATO.”
- Correct design and outcome mismatches before synthesis.
Citation Network
Citation relationships from available metadata can be rendered as an interactive graph with centrality, communities, and related-work exploration. Networks help identify influential clusters, bridge papers, and disconnected subfields; they do not replace critical appraisal and are biased toward sources and eras with richer citation metadata.
Watch Alerts
Save a useful search as a watch to check for new matching records. Current production allowances are:
| Plan | Active watches | Check cadence |
|---|---|---|
| Standard | 10 | Daily |
| Enterprise | 50 | Hourly |
| Pay as you go | No fixed account cap | Hourly |
External indexing and connector timing can delay a new record even when a watch runs on schedule.
Send Literature to Chat
- Select works from results or Library.
- Select Send to Chat.
- Choose Ask with context, Analyze and extract, Draft a section, or Plan next steps.
- Review the context packet and prefilled prompt, then remove irrelevant sources or add a focused question.
- In Chat, open cited sources or fetched-paper artifacts before accepting the synthesis.
Context packets help bound the task. Explicitly say “use only the attached sources” when that constraint matters, and ask CATO to flag claims that lack support in the available text.
Generated Literature Artifacts
Evidence tables, briefs, review drafts, landscape analyses, gap reports, citation exports, and related research outputs are stored as durable project artifacts. Open them in the Workspace to review versions, provenance, source links, annotations, and reviewer findings, then carry the intended version into a manuscript.
Systematic Review Synthesis
The systematic-review workflow performs multi-pass synthesis of a curated evidence set, including study-design recognition, narrative synthesis, quality and limitation prompts, and structured outputs. It is available on Enterprise and Pay-as-you-go accounts, plus eligible custom institutional accounts.
It does not make a review systematic by itself. A defensible systematic review still requires a protocol, information-specialist-quality searches where appropriate, deduplication, dual screening or adjudication, documented exclusions, validated extraction, risk-of-bias assessment, and reporting consistent with the applicable standard.
Run Status and Failures
Search and research operations expose per-source progress and warnings. One connector can fail while others return results, so read the source status before interpreting a small result set. Durable research output is finalized and persisted where possible even if a later presentation or handoff step must retry.
Search and Synthesis Checklist
- Save the exact question, date, translated queries, filters, and enabled sources.
- Check source errors, indexing dates, spelling variants, controlled vocabulary, and identifier formats.
- Resolve duplicate preprint/journal versions and retractions or corrections.
- Verify eligibility, extraction, and risk-of-bias judgments against full text.
- Confirm every generated citation and quotation in the authoritative source.
- Record where only an abstract or metadata—not full text—was available.
- Export the search and evidence artifacts required for reproducibility.