@prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix sl:    <http://www.semanlink.net/2001/00/semanlink-schema#> .
@prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
@prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
@prefix tag:   <http://www.semanlink.net/tag/> .
@prefix foaf:  <http://xmlns.com/foaf/0.1/> .
@prefix dc:    <http://purl.org/dc/elements/1.1/> .

tag:reasoning_information_retrieval
        a               sl:Tag ;
        skos:prefLabel  "Reasoning IR" .

tag:arxiv_doc  a        sl:Tag ;
        skos:prefLabel  "Arxiv Doc" .

tag:nlp_stanford  a     sl:Tag ;
        skos:prefLabel  "NLP@Stanford" .

tag:llm  a              sl:Tag ;
        skos:prefLabel  "LLM" .

tag:hierarchical_reasoning_model
        a               sl:Tag ;
        skos:broader    tag:reasoning_models ;
        skos:prefLabel  "Hierarchical Reasoning Model" .

tag:lm_reasonning  a    sl:Tag ;
        skos:prefLabel  "LM: reasonning" .

tag:deepseek_r1  a      sl:Tag ;
        skos:broader    tag:reasoning_models ;
        skos:prefLabel  "Deepseek-r1" .

tag:reinforcement_learning
        a               sl:Tag ;
        skos:prefLabel  "Reinforcement learning" .

tag:li_fei_fei  a       sl:Tag ;
        skos:prefLabel  "Li Fei-Fei" .

<http://www.semanlink.net/doc/2025/02/deepseek_r1_model_by_deepseek_a>
        dc:title         "deepseek-r1 Model by Deepseek-ai | NVIDIA NIM" ;
        sl:comment       "> DeepSeek-R1 is a first-generation **reasoning model trained using large-scale reinforcement learning** (RL) to solve complex reasoning tasks across domains such as math, code, and language. The model leverages RL to develop reasoning capabilities, which are further enhanced through supervised fine-tuning (SFT) to improve readability and coherence." ;
        sl:creationDate  "2025-02-24" ;
        sl:tag           tag:reinforcement_learning , tag:reasoning_models , tag:deepseek_r1 , tag:deepseek .

<http://www.semanlink.net/doc/2025/02/diffuse_one>
        dc:title         "diffuse.one/reasoning_update_0" ;
        sl:comment       "> There is an emerging pattern of fine-tuning a small language model followed by reinforcement learning.\r\n\r\n> A reasoning model is a large language model that is trained to output both a chain of thought and a response. The chain of thought should be relatively long (\r\n> 1,000 tokens) and the reasoning should improve its performance relative to a similar-sized non-reasoning models. This is sometimes called \"test-time\" or \"inference-time\" scaling because reasoning models emit more tokens per completion and gain some performance as a result." ;
        sl:creationDate  "2025-02-24" ;
        sl:tag           tag:reinforcement_learning , tag:reasoning_models , tag:reasoning_models_math_evals , tag:knowledge_distillation , tag:deepseek_r1 , tag:chain_of_thought .

<http://www.semanlink.net/doc/2025/02/cameron_r_wolfe_ph_d_sur_x_>
        dc:title         "Cameron R. Wolfe, Ph.D. sur X : \"The trajectory of research for open LLMs and open reasoning models has been shockingly similar, but there are still many open questions…\"" ;
        sl:comment       "> To me, these are pivotal questions to answer for current research on open reasoning models:\r\n> - Do the smaller / distilled models generalize well?\r\n> - Are we missing any gaps in performance?\r\n> - How do these findings relate to findings from traditional LLM research?" ;
        sl:creationDate  "2025-02-24" ;
        sl:tag           tag:reasoning_models .

tag:openai_o1  a        sl:Tag ;
        skos:broader    tag:reasoning_models ;
        skos:prefLabel  "OpenAI o1" .

tag:reasoning  a        sl:Tag ;
        skos:prefLabel  "Reasoning" .

tag:chain_of_thought  a  sl:Tag ;
        skos:prefLabel  "Chain-of-thought" .

tag:reasoning_models  a   sl:Tag ;
        rdfs:isDefinedBy  <http://semanlink.net/tag/reasoning_models.n3> ;
        sl:comment        "> a large language model that is trained to output both a chain of thought and a response ([src](doc:2025/02/diffuse_one))" ;
        skos:broader      tag:reasoning , tag:llm ;
        skos:prefLabel    "Reasoning models (Inference-time scaling)" ;
        skos:related      tag:reasoning_information_retrieval , tag:lm_reasonning ;
        foaf:page         tag:reasoning_models.html .

tag:reasoning_models_math_evals
        a               sl:Tag ;
        skos:broader    tag:reasoning_models ;
        skos:prefLabel  "Reasoning models: math evals" .

<http://www.semanlink.net/doc/2025/02/diffuse_one_reasoning_reflectio>
        dc:title         "diffuse.one/reasoning_reflections: AI for science with reasoning models" ;
        sl:creationDate  "2025-02-24" ;
        sl:tag           tag:reasoning_models , tag:ai_for_science .

tag:ai_for_science  a   sl:Tag ;
        skos:prefLabel  "AI for science" .

<http://www.semanlink.net/doc/2025/03/2501_19393_s1_simple_test_ti>
        dc:title         "[2501.19393] s1: Simple test-time scaling" ;
        sl:comment       "\"Researchers created an open rival to OpenAI’s o1 ‘reasoning’ model for under $50\" [techcrunch.com](https://techcrunch.com/2025/02/05/researchers-created-an-open-rival-to-openais-o1-reasoning-model-for-under-50/)" ;
        sl:creationDate  "2025-03-03" ;
        sl:tag           tag:reasoning_models , tag:emmanuel_candes , tag:knowledge_distillation , tag:li_fei_fei , tag:reasoning_models_math_evals , tag:arxiv_doc , tag:nlp_stanford .

tag:emmanuel_candes  a  sl:Tag ;
        skos:prefLabel  "Emmanuel Candès" .

tag:deepseek  a         sl:Tag ;
        skos:prefLabel  "DeepSeek" .

tag:knowledge_distillation
        a               sl:Tag ;
        skos:prefLabel  "Knowledge distillation" .