ThreatGram 101
ThreatGram 101 - Extreme Telegram Replies Data with Threat Levels
Data 1: Raw and Unlabeled; 2 million unlabeled replies from 17 Telegram channels.
How to run
ltb · threatgram-101
$ npm i -g lettokenburn-cli$ ltb bench info threatgram-101
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
1 sourced entry| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| GPT-2 | 66.2 | N/A | Independent | medium | Dec 15, 2023 | ieeexplore.ieee.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
Data 1: Raw and Unlabeled; 2 million unlabeled replies from 17 Telegram channels. Data 2: Raw and Labeled; 15,076 replies from 17 Telegram channels categorized as no threat, judicial threat, and non-judicial threat.