No synthetic marker found in these counts. That is not proof of where the data came from.
The sorting behind these counts was checked against labels made by a council of models; for some classes too few entries could be checked. No person has read the individual rows, and no clinician has read the class definitions.
Registry data from ClinicalTrials.gov, an online database; the U.S. National Library of Medicine maintains its website. This lab is independent of the registry; the grouping and counts are the lab's work, not the registry's.
Registry records change; the live record on ClinicalTrials.gov is current, this file is not. https://clinicaltrials.gov/
source: ClinicalTrials.gov
data processed by the registry, as given: 2026-10-09T09:00:05; the registry gives no time zone
snapshot fetched at: 2026-10-11 03:59:17 UTC
terms: https://clinicaltrials.gov/about-site/terms-conditions (last updated 2023-01-31)
modifications made by the lab:
  1. Primary-outcome wording was classified into classes by the versioned rule lexicon 0.3.2-draft (sha256 f4bd1af4c664); a model-proposed class is counted only when its quote is an exact piece of the registry text.
  2. Studies were left out by stated scope rules, with these counts: X1 554, X2 7, X3 0, X4 91, X5 48, X6 0 (explained in trial-atlas-data-dictionary.txt; X6 is a person's exclusion list).
  3. Start dates without a recorded date type are counted as their own kind; no type is assumed.
  4. No registry wording was clipped by these tools; any clipping on a published page must be added to this list.
  5. Registry pages were re-saved as UTF-8 JSON after parsing; values and key order are kept, whitespace is not.
  6. This page and its downloads show counts only: no registry wording, trial ids or sponsor names.
  7. Start years are also grouped into five-year periods for narrow screens; the yearly counts are in the downloads.
  8. Phase codes are written in plain words (PHASE1 as Phase 1, PHASE1/PHASE2 as Phase 1/2, EARLY_PHASE1 as Early phase 1); NA is shown as written, and a study with no phase is shown as None given.
licence: The lab's licence covers its own tags, code and counts only; registry text and fields remain ClinicalTrials.gov data under its terms.
retention: The registry's terms apply for as long as the data are kept, in any copy, file or page made from them.
no warranty: ClinicalTrials.gov states that the U.S. Government makes no warranties, expressed or implied, about its data and assumes no liability for any party's use of them.
sponsor responsibility: Study sponsors and investigators write and are responsible for their own records. The registry's Disclaimer says the U.S. government "does not review or approve the safety and science of all studies listed on this website" and that NLM staff only review study information for apparent errors, deficiencies or inconsistencies. See the registry's Disclaimer.
disclaimer url: https://clinicaltrials.gov/about-site/disclaimer
disclaimer last updated: 2023-08-03
third party copyright: Some registry data may be subject to third-party copyright, and the data carry an international copyright outside the United States and its Territories or Possessions.
keep current: The registry says it is updated daily and that data in any publication or distribution should be kept current at all times. This copy is dated and may be out of date; the live record is the current one.
how to cite: Sensei Ewok Research Lab (senseiewok.ai). Trial endpoint atlas, dated copy d164700bb17d, lexicon 0.3.2-draft, registry data processed 2026-10-09, accessed [the date you read it]. Counts derived from ClinicalTrials.gov (an online database whose website the U.S. National Library of Medicine maintains).