AI Science Tracker
EN

Texas A&M University

2 discoveries from 2026

Discoveries

The lightest and heaviest jiu-jitsu classes showed distinct match progression

Source check: Source checked. Not independent scientific confirmation.

Finding: A fitted model of 78 men’s no-gi Brazilian jiu-jitsu matches found that the 66 kg and over-99 kg groups differed from the middle weight classes in how recorded match states led to eventual outcomes. The matches came from one 2019 championship.

Technology: Hierarchical absorbing Markov model with Bayesian random-partition clustering

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A fitted hierarchical absorbing Markov model and an Ewens–Pitman attraction random-partition model infer transition patterns by weight class from recorded matches.
Test and result
The model pooled recorded transitions across classes and compared posterior probabilities of eventual match outcomes separately by weight class. The analysis used 244 sequences after excluding the absolute division from the original 93-match dataset.
Limitation / still unknown
The findings concern this tournament and the model’s grouping and state definitions. They do not establish a causal effect of body weight or generalize to other competitions.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/abs/2610.31787 · https://arxiv.org/html/2610.31787v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 21 Nov 2026. Review scope: arXiv v1 data scope, hierarchical random-partition fit, and aggregate posterior comparisons for sports weight categories.

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Artificial intelligence-based detection of small and intermediate-to-large lymphocytes for cytologic diagnosis of canine lymphoma.

Source check: Source checked. Not independent scientific confirmation.

Finding: YOLOv11 transfer-learned on cytology images detects lymphocyte classes; 34 lymphoma and 11 non-lymphoma aspirates from 44 dogs, 25,761 cells/680 images; aspirate diagnosis inferred from intermediate/large cell proportion. Five-fold plus held-out test and cross-device configurations; test F1 86.02% overall, intermediate/large class precision 90.58%, recall 82.62%. Full Methods/Results read. Small retrospective veterinary sample.

Technology: YOLOv11, transfer-learned on cytology images, detects canine lymphoma lymphocyte classes; cell proportions support the aspirate-level diagnostic classification.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
YOLOv11, transfer-learned on cytology images, detects canine lymphoma lymphocyte classes; cell proportions support the aspirate-level diagnostic classification.
Test and result
YOLOv11 transfer-learned on cytology images detects lymphocyte classes; 34 lymphoma and 11 non-lymphoma aspirates from 44 dogs, 25,761 cells/680 images; aspirate diagnosis inferred from intermediate/large cell proportion. Five-fold plus held-out test and cross-device configurations; test F1 86.02% overall, intermediate/large class precision 90.58%, recall 82.62%. Full Methods/Results read. Small retrospective veterinary sample. Methods and Results establish cohort, comparator/ground truth and reported evaluation. Limitations are preserved in reason.
Limitation / still unknown
The study does not establish performance or consequences beyond the reported cohort, datasets, task or experimental setup.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://journals.sagepub.com/doi/full/10.1177/03009858261477051 · https://pubmed.ncbi.nlm.nih.gov/42669833/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.