Add pipeline tag and paper link

README.md

@@ -1,18 +1,19 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen3.5-0.8B
-library_name: peft
+datasets:
+- SearchJev/search_jev_unified_v2_release_20260928
 language:
 - zh
 - en
+library_name: peft
+license: apache-2.0
+pipeline_tag: text-classification
 tags:
 - lora
 - searchjev
 - search-agent
 - system-1
 - calibration
-datasets:
-- SearchJev/search_jev_unified_v2_release_20260928
 ---
 
 # SearchJev-0.8B
@@ -27,10 +28,10 @@ This repository holds the LoRA adapter of **SearchJev-0.8B** on
 [Qwen/Qwen3.5-0.8B](https://huggingface.co/Qwen/Qwen3.5-0.8B), together with its per-question-type
 temperatures and option-label alphabet.
 
+- Paper: [SearchJev: A Fast and Calibrated System-1 Model for Search Agents](https://huggingface.co/papers/2610.05107)
 - Code (training and inference): <https://github.com/EvoScientist/Search_Jev>
 - Training data: [SearchDecision-Bench](https://huggingface.co/datasets/SearchJev/search_jev_unified_v2_release_20260928)
 - Training logs: [W&B report](https://forge.coreweave.com/wandb/R-DTeam/Search_JEV/reports/Search_Jev-Report--VmlldzoxODAzMTUwMw)
-- Paper: *SearchJev: A Fast and Calibrated System-1 Model for Search Agents*
 
 ## Usage
 
@@ -77,4 +78,4 @@ type fitted on 5,000 validation decisions. `config.resolved.yaml` is the exact c
 
 ## License
 
-Apache-2.0, like the Qwen3.5 base model.
+Apache-2.0, like the Qwen3.5 base model.