Zero-Shot Classification
Laya
Safetensors
GGUF
Hebrew
hebrew
decision-model
calibrated
scam-detection
routing
Instructions to use BrainboxAI/nitzotz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use BrainboxAI/nitzotz with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Card: tested quick start outputs, question wording note, hard-case and timing caveats
Browse files
README.md
CHANGED
|
@@ -42,12 +42,19 @@ legitimate messages 88% of the time (AUC 0.88).
|
|
| 42 |
```python
|
| 43 |
import laya
|
| 44 |
agent = laya.load("BrainboxAI/nitzotz")
|
| 45 |
-
q = {"scam": {"type": "noul",
|
|
|
|
|
|
|
|
|
|
| 46 |
print(agent.predict("讛讞讘讬诇讛 砖诇讱 诪注讜讻讘转. 诇砖讞专讜专 砖诇诐 12.90 讘拽讬砖讜专", q)["answers"]["scam"]["noul"])
|
| 47 |
```
|
| 48 |
|
| 49 |
-
Output: `
|
| 50 |
-
reason") is true.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
**laya.exe** (the standalone binary from [ggmlc releases](https://github.com/monatis/ggmlc/releases/latest), no Python
|
| 53 |
needed). Download the Q8 file, start the daemon, then send one JSON request per line; each answer comes back on one line:
|
|
@@ -55,11 +62,12 @@ needed). Download the Q8 file, start the daemon, then send one JSON request per
|
|
| 55 |
```bash
|
| 56 |
hf download BrainboxAI/nitzotz nitzotz-q8_0.gguf --local-dir .
|
| 57 |
laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
| 58 |
-
{"id":"1","state":"
|
| 59 |
```
|
| 60 |
|
| 61 |
```json
|
| 62 |
-
|
|
|
|
| 63 |
```
|
| 64 |
|
| 65 |
`noul` is the probability that the claim is true. Several questions in one request are answered together in one pass.
|
|
@@ -134,10 +142,11 @@ from the wording of the question.
|
|
| 134 |
| laya.exe, Q8 file, CPU only (16 threads) | 335 ms | 177 ms | 1233 ms |
|
| 135 |
| Python (laya), CPU only | 387 ms | 130 ms | 1260 ms |
|
| 136 |
|
| 137 |
-
The short and long columns repeat one fixed input 30 times after 5 warm-up calls.
|
| 138 |
-
|
|
|
|
| 139 |
|
| 140 |
-
**The GGUF files give the same answers as the Python model.** Compared with the full-precision Python model on the
|
| 141 |
CPU:
|
| 142 |
|
| 143 |
| File, device | Same top answer, 50 questions | Largest probability gap | Same top answer, 596 spam questions | Largest gap | Average gap |
|
|
@@ -234,7 +243,9 @@ Caveats that change how much to trust the numbers:
|
|
| 234 |
- **Numbers, dates, amounts and rules**: not trained and not measured. Compute them in code and pass the result in.
|
| 235 |
- **Hard cases are the weak spot**: scams written to look legitimate (a "supplier" changing bank details, the "CEO"
|
| 236 |
asking for a transfer) and real messages that look like scams (a real bank alert with a link, a real verification
|
| 237 |
-
code). On the 65 hard cases the scam question is right 63.1% of the time
|
|
|
|
|
|
|
| 238 |
- **Urgency is subjective.** Even the two teacher models matched the intended urgency only about 62 to 64% of the time.
|
| 239 |
- **Sarcasm and irony** are probably read literally. Not measured.
|
| 240 |
- **512 tokens** (roughly 300 to 400 Hebrew words) per question. A longer message is cut from the end without a warning.
|
|
@@ -288,13 +299,21 @@ The full notice is in `NOTICE`.
|
|
| 288 |
```python
|
| 289 |
import laya
|
| 290 |
agent = laya.load("BrainboxAI/nitzotz")
|
| 291 |
-
q = {"scam": {"type": "noul",
|
|
|
|
|
|
|
|
|
|
| 292 |
print(agent.predict("讛讞讘讬诇讛 砖诇讱 诪注讜讻讘转. 诇砖讞专讜专 砖诇诐 12.90 讘拽讬砖讜专", q)["answers"]["scam"]["noul"])
|
| 293 |
```
|
| 294 |
|
| 295 |
<div dir="rtl">
|
| 296 |
|
| 297 |
-
讛驻诇讟: `
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 298 |
|
| 299 |
**讘诇讬 驻讬讬转讜谉, 注诐 laya.exe** (转讜讻谞讛 注爪诪讗讬转 诪-[ggmlc](https://github.com/monatis/ggmlc/releases/latest)). 诪讜专讬讚讬诐 讗转 拽讜讘抓
|
| 300 |
Q8, 诪驻注讬诇讬诐, 讜砖讜诇讞讬诐 讘拽砖转 JSON 讗讞转 讘讻诇 砖讜专讛. 讻诇 转砖讜讘讛 讞讜讝专转 讘砖讜专讛 讗讞转:
|
|
@@ -304,11 +323,12 @@ Q8, 诪驻注讬诇讬诐, 讜砖讜诇讞讬诐 讘拽砖转 JSON 讗讞转 讘讻诇 砖讜专讛. 讻诇 转
|
|
| 304 |
```bash
|
| 305 |
hf download BrainboxAI/nitzotz nitzotz-q8_0.gguf --local-dir .
|
| 306 |
laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
| 307 |
-
{"id":"1","state":"
|
| 308 |
```
|
| 309 |
|
| 310 |
```json
|
| 311 |
-
|
|
|
|
| 312 |
```
|
| 313 |
|
| 314 |
<div dir="rtl">
|
|
@@ -381,10 +401,10 @@ laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
|
| 381 |
| laya.exe, 拽讜讘抓 Q8, 诪注讘讚 讘诇讘讚 (16 转讛诇讬讻讜谞讬诐) | 335 ms | 177 ms | 1233 ms |
|
| 382 |
| 驻讬讬转讜谉 (laya), 诪注讘讚 讘诇讘讚 | 387 ms | 130 ms | 1260 ms |
|
| 383 |
|
| 384 |
-
讘注诪讜讚讜转 砖诇 讛讛讜讚注讛 讛拽爪专讛 讜讛拽诇讟 讛讗专讜讱 讗讜转讛 砖讗诇讛 专爪讛 30 驻注诪讬诐, 讗讞专讬 5 讛专爪讜转 讞讬诪讜诐.
|
| 385 |
-
讗讝 讗诇讛 诪住驻专讬诐 讘拽讬专讜讘.
|
| 386 |
|
| 387 |
-
**拽讜讘爪讬 讛-GGUF 谞讜转谞讬诐 讗转 讗讜转谉 转砖讜讘讜转 讻诪讜 诪讜讚诇 讛驻讬讬转讜谉.** 讘讛砖讜讜讗讛 诇诪讜讚诇 讛驻讬讬转讜谉 讛诪诇讗 注诇 讛诪注讘讚:
|
| 388 |
|
| 389 |
| 拽讜讘抓, 诪讻砖讬专 | 讗讜转讛 转砖讜讘讛 诪讜讘讬诇讛, 50 砖讗诇讜转 | 讛驻专砖 讛住转讘专讜转 诪专讘讬 | 讗讜转讛 转砖讜讘讛 诪讜讘讬诇讛, 596 砖讗诇讜转 住驻讗诐 | 讛驻专砖 诪专讘讬 | 讛驻专砖 诪诪讜爪注 |
|
| 390 |
|---|---|---|---|---|---|
|
|
@@ -476,7 +496,8 @@ laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
|
| 476 |
- **诪住驻专讬诐, 转讗专讬讻讬诐, 住讻讜诪讬诐 讜讻诇诇讬诐**: 诇讗 讗讜诪谉 注诇讬讛诐 讜诇讗 谞诪讚讚. 讞砖讘讜 讗讜转诐 讘拽讜讚 讜讛注讘讬专讜 讗转 讛转讜爪讗讛.
|
| 477 |
- **讛诪拽专讬诐 讛拽砖讬诐 讛诐 谞拽讜讚转 讛转讜专驻讛**: 讛讜谞讗讜转 砖谞讻转讘讜 讻讚讬 诇讛讬专讗讜转 诇讙讬讟讬诪讬讜转 ("住驻拽" 砖诪讞诇讬祝 驻专讟讬 讞砖讘讜谉 讘谞拽, "讛诪谞讻"诇" 砖诪讘拽砖
|
| 478 |
讛注讘专讛), 讜讛讜讚注讜转 讗诪讬转讬讜转 砖谞专讗讜转 讻诪讜 讛讜谞讗讛 (讛转专讗讛 讗诪讬转讬转 诪讛讘谞拽 注诐 拽讬砖讜专, 拽讜讚 讗讬诪讜转 讗诪讬转讬). 注诇 65 讛诪拽专讬诐 讛拽砖讬诐 砖讗诇转
|
| 479 |
-
讛讛讜谞讗讛 爪讜讚拽转 讘-63.1% 诪讛诪拽专讬诐.
|
|
|
|
| 480 |
- **讚讞讬驻讜转 讛讬讗 注谞讬讬谉 住讜讘讬讬拽讟讬讘讬.** 讗驻讬诇讜 砖谞讬 诪讜讚诇讬 讛诪讜专讛 讛住讻讬诪讜 注诐 讛讚讞讬驻讜转 讛诪转讜讻谞谞转 专拽 讘讻-62 注讚 64% 诪讛诪拽专讬诐.
|
| 481 |
- **爪讬谞讬讜转 讜讗讬专讜谞讬讛** 讻谞专讗讛 谞拽专讗讜转 诪讬诇讜诇讬转. 诇讗 谞诪讚讚.
|
| 482 |
- **512 讟讜拽谞讬诐** (讘注专讱 300 注讚 400 诪讬诇讬诐 讘注讘专讬转) 诇砖讗诇讛. 讛讜讚注讛 讗专讜讻讛 讬讜转专 谞讞转讻转 诪讛住讜祝 讘诇讬 讗讝讛专讛.
|
|
|
|
| 42 |
```python
|
| 43 |
import laya
|
| 44 |
agent = laya.load("BrainboxAI/nitzotz")
|
| 45 |
+
q = {"scam": {"type": "noul",
|
| 46 |
+
"instructions": "讛讛讜讚注讛 诪谞住讛 诇讙专讜诐 诇谞诪注谉 诇诇讞讜抓 注诇 拽讬砖讜专, 诇砖诇诐 讗讜 诇诪住讜专 驻专讟讬诐 讘诇讬 住讬讘讛 诇讙讬讟讬诪讬转.",
|
| 47 |
+
"criteria": {"true": "讻谉, 讝讛 谞讬住讬讜谉 诪专诪讛",
|
| 48 |
+
"false": "诇讗, 讝讜 讛讜讚注讛 诇讙讬讟讬诪讬转, 讙诐 讗诐 讬砖 讘讛 拽讬砖讜专 讗讜 讘拽砖转 转砖诇讜诐"}}}
|
| 49 |
print(agent.predict("讛讞讘讬诇讛 砖诇讱 诪注讜讻讘转. 诇砖讞专讜专 砖诇诐 12.90 讘拽讬砖讜专", q)["answers"]["scam"]["noul"])
|
| 50 |
```
|
| 51 |
|
| 52 |
+
Output: `0.8613`, the probability that the claim ("the message tries to make the reader click a link, pay or hand
|
| 53 |
+
over details for no legitimate reason") is true.
|
| 54 |
+
|
| 55 |
+
**The wording of the question matters.** This is the exact question the scam test used, and the numbers on this card
|
| 56 |
+
are for it. In our tries a shorter wording ("the message is a scam attempt") gave clearly worse answers, for example
|
| 57 |
+
a high scam probability for a plain verification code. If you change the wording, check it on your own messages first.
|
| 58 |
|
| 59 |
**laya.exe** (the standalone binary from [ggmlc releases](https://github.com/monatis/ggmlc/releases/latest), no Python
|
| 60 |
needed). Download the Q8 file, start the daemon, then send one JSON request per line; each answer comes back on one line:
|
|
|
|
| 62 |
```bash
|
| 63 |
hf download BrainboxAI/nitzotz nitzotz-q8_0.gguf --local-dir .
|
| 64 |
laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
| 65 |
+
{"id":"1","state":"讛讬讬, 讛驻讙讬砖讛 诪讞专 讘-10 注讚讬讬谉 讘转讜拽祝?","questions":{"scam":{"type":"noul","instructions":"讛讛讜讚注讛 诪谞住讛 诇讙专讜诐 诇谞诪注谉 诇诇讞讜抓 注诇 拽讬砖讜专, 诇砖诇诐 讗讜 诇诪住讜专 驻专讟讬诐 讘诇讬 住讬讘讛 诇讙讬讟讬诪讬转.","criteria":{"true":"讻谉, 讝讛 谞讬住讬讜谉 诪专诪讛","false":"诇讗, 讝讜 讛讜讚注讛 诇讙讬讟讬诪讬转, 讙诐 讗诐 讬砖 讘讛 拽讬砖讜专 讗讜 讘拽砖转 转砖诇讜诐"}}}}
|
| 66 |
```
|
| 67 |
|
| 68 |
```json
|
| 69 |
+
{"status":"ready","model":"laya"}
|
| 70 |
+
{"model": "nitzotz", "family": "nitzotz", "route": "forced nitzotz", "answers": {"scam": {"type": "noul", "action": {"act_probability": 0.1511}, "confidence": 0.8785, "noul": 0.1215}}, "usage": {"input_tokens": 66, "output_tokens": 0, "latency_ms": 117.02}, "id": "1"}
|
| 71 |
```
|
| 72 |
|
| 73 |
`noul` is the probability that the claim is true. Several questions in one request are answered together in one pass.
|
|
|
|
| 142 |
| laya.exe, Q8 file, CPU only (16 threads) | 335 ms | 177 ms | 1233 ms |
|
| 143 |
| Python (laya), CPU only | 387 ms | 130 ms | 1260 ms |
|
| 144 |
|
| 145 |
+
The short and long columns repeat one fixed input 30 times after 5 warm-up calls. Timings on this laptop change a
|
| 146 |
+
lot from one session to another (an earlier measurement of the same setup was several times slower), so treat these
|
| 147 |
+
as rough.
|
| 148 |
|
| 149 |
+
**The GGUF files give almost the same answers as the Python model.** Compared with the full-precision Python model on the
|
| 150 |
CPU:
|
| 151 |
|
| 152 |
| File, device | Same top answer, 50 questions | Largest probability gap | Same top answer, 596 spam questions | Largest gap | Average gap |
|
|
|
|
| 243 |
- **Numbers, dates, amounts and rules**: not trained and not measured. Compute them in code and pass the result in.
|
| 244 |
- **Hard cases are the weak spot**: scams written to look legitimate (a "supplier" changing bank details, the "CEO"
|
| 245 |
asking for a transfer) and real messages that look like scams (a real bank alert with a link, a real verification
|
| 246 |
+
code). On the 65 hard cases the scam question is right 63.1% of the time, which is below the
|
| 247 |
+
70.8% you would get by always answering "not a scam" there. Its ranking on those cases is also weak
|
| 248 |
+
(AUC 0.63).
|
| 249 |
- **Urgency is subjective.** Even the two teacher models matched the intended urgency only about 62 to 64% of the time.
|
| 250 |
- **Sarcasm and irony** are probably read literally. Not measured.
|
| 251 |
- **512 tokens** (roughly 300 to 400 Hebrew words) per question. A longer message is cut from the end without a warning.
|
|
|
|
| 299 |
```python
|
| 300 |
import laya
|
| 301 |
agent = laya.load("BrainboxAI/nitzotz")
|
| 302 |
+
q = {"scam": {"type": "noul",
|
| 303 |
+
"instructions": "讛讛讜讚注讛 诪谞住讛 诇讙专讜诐 诇谞诪注谉 诇诇讞讜抓 注诇 拽讬砖讜专, 诇砖诇诐 讗讜 诇诪住讜专 驻专讟讬诐 讘诇讬 住讬讘讛 诇讙讬讟讬诪讬转.",
|
| 304 |
+
"criteria": {"true": "讻谉, 讝讛 谞讬住讬讜谉 诪专诪讛",
|
| 305 |
+
"false": "诇讗, 讝讜 讛讜讚注讛 诇讙讬讟讬诪讬转, 讙诐 讗诐 讬砖 讘讛 拽讬砖讜专 讗讜 讘拽砖转 转砖诇讜诐"}}}
|
| 306 |
print(agent.predict("讛讞讘讬诇讛 砖诇讱 诪注讜讻讘转. 诇砖讞专讜专 砖诇诐 12.90 讘拽讬砖讜专", q)["answers"]["scam"]["noul"])
|
| 307 |
```
|
| 308 |
|
| 309 |
<div dir="rtl">
|
| 310 |
|
| 311 |
+
讛驻诇讟: `0.8613`, 讛讛住转讘专讜转 砖讛讟注谞讛 ("讛讛讜讚注讛 诪谞住讛 诇讙专讜诐 诇谞诪注谉 诇诇讞讜抓 注诇 拽讬砖讜专, 诇砖诇诐 讗讜 诇诪住讜专 驻专讟讬诐 讘诇讬 住讬讘讛 诇讙讬讟讬诪讬转")
|
| 312 |
+
谞讻讜谞讛.
|
| 313 |
+
|
| 314 |
+
**讛谞讬住讜讞 砖诇 讛砖讗诇讛 诪砖谞讛.** 讝讜 讘讚讬讜拽 讛砖讗诇讛 砖讘讛 讛砖转诪砖 诪讘讞谉 讛讛讜谞讗讜转, 讜讛诪住驻专讬诐 讘讻专讟讬住 讛讝讛 讛诐 注诇讬讛. 讘谞讬住讬讜谞讜转 砖诇谞讜 谞讬住讜讞
|
| 315 |
+
拽爪专 讬讜转专 ("讛讛讜讚注讛 讛讬讗 谞讬住讬讜谉 讛讜谞讗讛") 谞转谉 转砖讜讘讜转 讙专讜注讜转 讘讛专讘讛, 诇诪砖诇 讛住转讘专讜转 讙讘讜讛讛 诇讛讜谞讗讛 诇拽讜讚 讗讬诪讜转 专讙讬诇. 讗诐 诪砖谞讬诐 讗转
|
| 316 |
+
讛谞讬住讜讞, 讘讜讚拽讬诐 讗讜转讜 拽讜讚诐 注诇 讛讛讜讚注讜转 砖诇讻诐.
|
| 317 |
|
| 318 |
**讘诇讬 驻讬讬转讜谉, 注诐 laya.exe** (转讜讻谞讛 注爪诪讗讬转 诪-[ggmlc](https://github.com/monatis/ggmlc/releases/latest)). 诪讜专讬讚讬诐 讗转 拽讜讘抓
|
| 319 |
Q8, 诪驻注讬诇讬诐, 讜砖讜诇讞讬诐 讘拽砖转 JSON 讗讞转 讘讻诇 砖讜专讛. 讻诇 转砖讜讘讛 讞讜讝专转 讘砖讜专讛 讗讞转:
|
|
|
|
| 323 |
```bash
|
| 324 |
hf download BrainboxAI/nitzotz nitzotz-q8_0.gguf --local-dir .
|
| 325 |
laya.exe daemon nitzotz-q8_0.gguf --device vulkan
|
| 326 |
+
{"id":"1","state":"讛讬讬, 讛驻讙讬砖讛 诪讞专 讘-10 注讚讬讬谉 讘转讜拽祝?","questions":{"scam":{"type":"noul","instructions":"讛讛讜讚注讛 诪谞住讛 诇讙专讜诐 诇谞诪注谉 诇诇讞讜抓 注诇 拽讬砖讜专, 诇砖诇诐 讗讜 诇诪住讜专 驻专讟讬诐 讘诇讬 住讬讘讛 诇讙讬讟讬诪讬转.","criteria":{"true":"讻谉, 讝讛 谞讬住讬讜谉 诪专诪讛","false":"诇讗, 讝讜 讛讜讚注讛 诇讙讬讟讬诪讬转, 讙诐 讗诐 讬砖 讘讛 拽讬砖讜专 讗讜 讘拽砖转 转砖诇讜诐"}}}}
|
| 327 |
```
|
| 328 |
|
| 329 |
```json
|
| 330 |
+
{"status":"ready","model":"laya"}
|
| 331 |
+
{"model": "nitzotz", "family": "nitzotz", "route": "forced nitzotz", "answers": {"scam": {"type": "noul", "action": {"act_probability": 0.1511}, "confidence": 0.8785, "noul": 0.1215}}, "usage": {"input_tokens": 66, "output_tokens": 0, "latency_ms": 117.02}, "id": "1"}
|
| 332 |
```
|
| 333 |
|
| 334 |
<div dir="rtl">
|
|
|
|
| 401 |
| laya.exe, 拽讜讘抓 Q8, 诪注讘讚 讘诇讘讚 (16 转讛诇讬讻讜谞讬诐) | 335 ms | 177 ms | 1233 ms |
|
| 402 |
| 驻讬讬转讜谉 (laya), 诪注讘讚 讘诇讘讚 | 387 ms | 130 ms | 1260 ms |
|
| 403 |
|
| 404 |
+
讘注诪讜讚讜转 砖诇 讛讛讜讚注讛 讛拽爪专讛 讜讛拽诇讟 讛讗专讜讱 讗讜转讛 砖讗诇讛 专爪讛 30 驻注诪讬诐, 讗讞专讬 5 讛专爪讜转 讞讬诪讜诐. 讛讝诪谞讬诐 注诇 讛诪讞砖讘 讛讝讛 诪砖转谞讬诐 讛专讘讛 讘讬谉
|
| 405 |
+
讛驻注诇讛 诇讛驻注诇讛 (诪讚讬讚讛 拽讜讚诪转 砖诇 讗讜转讛 讛讙讚专讛 讬爪讗讛 讗讬讟讬转 驻讬 讻诪讛), 讗讝 讗诇讛 诪住驻专讬诐 讘拽讬专讜讘.
|
| 406 |
|
| 407 |
+
**拽讜讘爪讬 讛-GGUF 谞讜转谞讬诐 讻诪注讟 讗转 讗讜转谉 转砖讜讘讜转 讻诪讜 诪讜讚诇 讛驻讬讬转讜谉.** 讘讛砖讜讜讗讛 诇诪讜讚诇 讛驻讬讬转讜谉 讛诪诇讗 注诇 讛诪注讘讚:
|
| 408 |
|
| 409 |
| 拽讜讘抓, 诪讻砖讬专 | 讗讜转讛 转砖讜讘讛 诪讜讘讬诇讛, 50 砖讗诇讜转 | 讛驻专砖 讛住转讘专讜转 诪专讘讬 | 讗讜转讛 转砖讜讘讛 诪讜讘讬诇讛, 596 砖讗诇讜转 住驻讗诐 | 讛驻专砖 诪专讘讬 | 讛驻专砖 诪诪讜爪注 |
|
| 410 |
|---|---|---|---|---|---|
|
|
|
|
| 496 |
- **诪住驻专讬诐, 转讗专讬讻讬诐, 住讻讜诪讬诐 讜讻诇诇讬诐**: 诇讗 讗讜诪谉 注诇讬讛诐 讜诇讗 谞诪讚讚. 讞砖讘讜 讗讜转诐 讘拽讜讚 讜讛注讘讬专讜 讗转 讛转讜爪讗讛.
|
| 497 |
- **讛诪拽专讬诐 讛拽砖讬诐 讛诐 谞拽讜讚转 讛转讜专驻讛**: 讛讜谞讗讜转 砖谞讻转讘讜 讻讚讬 诇讛讬专讗讜转 诇讙讬讟讬诪讬讜转 ("住驻拽" 砖诪讞诇讬祝 驻专讟讬 讞砖讘讜谉 讘谞拽, "讛诪谞讻"诇" 砖诪讘拽砖
|
| 498 |
讛注讘专讛), 讜讛讜讚注讜转 讗诪讬转讬讜转 砖谞专讗讜转 讻诪讜 讛讜谞讗讛 (讛转专讗讛 讗诪讬转讬转 诪讛讘谞拽 注诐 拽讬砖讜专, 拽讜讚 讗讬诪讜转 讗诪讬转讬). 注诇 65 讛诪拽专讬诐 讛拽砖讬诐 砖讗诇转
|
| 499 |
+
讛讛讜谞讗讛 爪讜讚拽转 讘-63.1% 诪讛诪拽专讬诐. 讝讛 驻讞讜转 诪讛-70.8% 砖讛讬讛 讬讜爪讗 讗诐 转诪讬讚 注讜谞讬诐 砖诐 "诇讗 讛讜谞讗讛", 讜讙诐
|
| 500 |
+
讛讚讬专讜讙 砖诇讜 讘诪拽专讬诐 讛讗诇讛 讞诇砖 (AUC 0.63).
|
| 501 |
- **讚讞讬驻讜转 讛讬讗 注谞讬讬谉 住讜讘讬讬拽讟讬讘讬.** 讗驻讬诇讜 砖谞讬 诪讜讚诇讬 讛诪讜专讛 讛住讻讬诪讜 注诐 讛讚讞讬驻讜转 讛诪转讜讻谞谞转 专拽 讘讻-62 注讚 64% 诪讛诪拽专讬诐.
|
| 502 |
- **爪讬谞讬讜转 讜讗讬专讜谞讬讛** 讻谞专讗讛 谞拽专讗讜转 诪讬诇讜诇讬转. 诇讗 谞诪讚讚.
|
| 503 |
- **512 讟讜拽谞讬诐** (讘注专讱 300 注讚 400 诪讬诇讬诐 讘注讘专讬转) 诇砖讗诇讛. 讛讜讚注讛 讗专讜讻讛 讬讜转专 谞讞转讻转 诪讛住讜祝 讘诇讬 讗讝讛专讛.
|