Skip to content
OctymPowered By Proofig AI
What we check

Octym runs every integrity and quality check, in one review.

The complete package, grouped into three categories: what's inside the manuscript, how it stands against the published record and the requirements of wherever it's headed, and whether the science is sound. Every finding is a signal backed by evidence, never a verdict.

Internal manuscript integrity

8

Issues that originate inside the manuscript itself: manipulated or duplicated figures, numbers that don't add up, captions that don't match. The clear, must-fix problems, surfaced first.

External checks & requirements

11

Checks that compare the work against everything outside it: the published literature, authoritative records, and the requirements of wherever it's headed.

Research quality

6

Analysis of the research itself: whether the methods are sound, the work could be reproduced, and the science holds up.

8 checks

Internal manuscript integrity

Issues that originate inside the manuscript itself: manipulated or duplicated figures, numbers that don't add up, captions that don't match. The clear, must-fix problems, surfaced first.

AI-generated text signals

Calibrated signals of AI-generated or paraphrased writing, aware that non-native English is not evidence of anything. A signal for a person to weigh, never a determination about an author.

Image manipulation

Pixel-level forensics that flag where a figure has been cloned, spliced, or retouched, tuned for the image types that matter most in life science.

Powered by Proofig

Clone & spliceWestern-blot manipulationMicroscopy edits

Image duplication

Compares every figure against the others to catch reused or overlapping panels, including FACS / flow-cytometry.

Powered by Proofig

Within-paper duplicationFACS / flow cytometry

AI-generated images

Identifies synthetic, AI-generated scientific figures, surfaced as a signal with the evidence behind it.

Powered by Proofig

Graph & chart duplication

Finds data-visualizations reused or repurposed across the manuscript. A distinct forensic from photographic images.

Powered by Proofig

Statistical validation & consistency

Recomputes reported statistics and flags outright errors: p-values that don't match their test, means impossible for the stated sample, and figures that disagree with the text or tables.

p-value recomputationGRIM plausibilityText ↔ table ↔ figure matchEffect-size reporting

Figure–legend consistency

Verifies each panel referenced in the legend exists and is labeled, and flags caption ↔ figure mismatches.

Panel-label completeness

Claim & citation consistency

Reads each in-text claim and its citation to flag statements that need a source but lack one, and citations that don't align with the claim.

Claim ↔ citation alignmentUncited-claim flag
11 checks

External checks & requirements

Checks that compare the work against everything outside it: the published literature, authoritative records, and the requirements of wherever it's headed.

Image & graph plagiarism

Compares images and data-visualizations against the published literature to surface figures reused from other papers.

Powered by Proofig, the largest image-plagiarism database in the industry

Retracted reference detection

Cross-checks every reference against retraction records to flag citations to retracted papers or those under an expression of concern.

Backed by the Retraction Watch database

Hallucinated / non-existent references

Resolves each reference against scholarly databases; references that don't resolve are flagged as potentially fabricated or hallucinated.

Backed by OpenAlex

DOI, link & metadata accuracy

Converts titles to DOIs and checks that each reference's metadata (authors, year, journal) matches the authoritative record, flagging broken or mismatched citations.

Backed by OpenAlex

Citation patterns

Analyzes the bibliography for patterns like excessive self-citation or heavy concentration in a narrow set of sources. Signals for a human to weigh, not verdicts.

Data & code availability

Resolves the data, code, and materials a manuscript says are available, confirming the links and accession numbers actually lead somewhere.

Paper-mill signals

Looks for the combination of signals that tends to cluster in paper-mill submissions: templated structure, authorship and affiliation anomalies, figures that recur across unrelated papers, and reference lists that do not match the claims. Each one is a signal with its evidence attached, never a conclusion about the authors.

Author identity & affiliation

Verifies authors and their affiliations against the published record, surfacing the identity and authorship anomalies that often accompany paper-mill submissions.

Funder requirements

Reviews an application against the funder's own criteria: specific aims and structure, rigor and reproducibility expectations, and the declarations they require. Workflows are built for NIH R01 and R21, ERC Starting, Consolidator and Advanced, Horizon Europe, and more.

Structure & required sectionsRigor expectationsRequired declarations

Journal author guidelines

Reviews a manuscript against the instructions for authors of the journal it's going to: abstract and word limits, page and figure counts, reference limits, required statements, article structure, and the disclosures that journal enforces.

Length & count limitsRequired statementsArticle structureDisclosures & declarations

Reporting-standard alignment

Checks the work against the reporting standard it will be held to (ARRIVE 2.0, CONSORT, MDAR), so the checklist a journal or funder asks for is already satisfied.

REVIEWMethodsRigorData
6 checks

Research quality

Analysis of the research itself: whether the methods are sound, the work could be reproduced, and the science holds up.

Methods & rigor

Evaluates the soundness of the design (randomization, blinding, controls, and whether the sample size is justified) and whether the methods follow the relevant reporting standards.

Randomization & blindingSample-size reportingReporting-standard adherence (CONSORT / ARRIVE / STROBE / NIH rigor)

Reproducibility

Checks that the protocol, computational environment, and analysis are described completely enough to reproduce the result.

Protocol completenessComputational environment

Replicability

Reads statistical fragility, power, and effect-size plausibility to signal how likely a finding would replicate. A decision-support signal, never a verdict.

Statistical fragilityEffect-size plausibilityReplicability prediction

Research ethics

Checks that ethics / IRB approval, informed consent, conflicts of interest, funding, and AI use are disclosed and internally consistent, aligned with COPE expectations.

IRB & consentCoI & fundingAI-use disclosureCOPE alignment

Novelty & contribution

Compares the manuscript's central claim against the prior literature to surface how much is genuinely new, where the contribution overlaps existing work, and whether the novelty a venue expects is actually present.

Claim vs. prior literatureOverlap with existing work

Peer-review-grade analysis

Synthesizes every dimension into a structured, reviewer-style read. Major issues first, each comment anchored to the passage it's about. Decision-support for a human, not an accept/reject verdict.

Signals, not verdicts. Octym surfaces findings with evidence and traces each to its source. A person always decides what matters. Octym never accuses anyone of misconduct.

FAQ

The checks, answered.

See every check on any manuscript.

Contact us, or log in.