Delete docs

docs/tasks/abs_2_title.md

@@ -1,20 +0,0 @@
-# **Title Generation Task - Input Format**
-
-## **Overview**
-The **Title Generation** task predicts the **title** of a research paper based on its **abstract**. The user provides the **abstract**, and the model generates a suitable title.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Abstract: <abstract>
-```
-
-- `<abstract>`: The full abstract of the paper.
-
-### **Example Input**
-```
-Abstract: This paper investigates the frequency behavior in spontaneous connected speech of two optional syntactic processes, particle movement and complementizer deletion. It shows them to be sensitive both to internal linguistic factors and to perceived norms of the standard language. It further compares the pattern found in usage with answers to a brief prescriptive grammatical questionnaire, where it finds parallelism. There is also a result of interest to the general theory of quantitative variation in an interaction found between an internal semantic effect and the external sociolinguistic one.
-```
-
-This formatted prompt is then used as input for the model to generate the predicted title of the paper.

docs/tasks/abs_completion.md

@@ -1,23 +0,0 @@
-# **Abstract Completion Task - Input Format**
-
-## **Overview**
-The **Abstract Completion** task completes the abstract of a research paper. The user provides the **title** and a **partial abstract**, and the model completes the remaining abstract based on the given information.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Title: <title>
-Part of abstract: <abstract>
-```
-
-- `<title>`: The title of the paper.
-- `<abstract>`: The partial abstract provided for completion. Note that the abstract field could be empty as well.
-
-### **Example Input**
-```
-Title: Attention Is All You Need
-Part of abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
-```
-
-This formatted prompt is then used as input for the model to generate the completed abstract.

docs/tasks/citation_sentence.md

@@ -1,29 +0,0 @@
-# **Citation Sentence Generation Task - Input Format**
-
-## **Overview**
-The **Citation Sentence** task generates a citation sentence describing how **Paper A** cites **Paper B**. The user provides the **titles and abstracts of both papers**, and the model generates a structured citation sentence.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Title of Paper A: <title of Paper A>
-Abstract of Paper A: <abstract of Paper A>
-Title of Paper B: <title of Paper B>
-Abstract of Paper B: <abstract of Paper B>
-```
-
-- `<title of Paper A>`: The title of Paper A (the citing paper).
-- `<abstract of Paper A>`: The abstract of Paper A.
-- `<title of Paper B>`: The title of Paper B (the cited paper).
-- `<abstract of Paper B>`: The abstract of Paper B.
-
-### **Example Input**
-```
-Title of Paper A: A Neural Algorithm of Artistic Style
-Abstract of Paper A: We present an algorithm that generates artistic images of high perceptual quality. The algorithm uses neural representations to separate and recombine content and style of arbitrary images, providing a neural algorithm for the creation of artistic images.
-Title of Paper B: Image Style Transfer Using Convolutional Neural Networks
-Abstract of Paper B: We describe a method for transferring the style of one image onto the content of another image using convolutional neural networks. The method is based on matching the feature representations of the content and style images in a high-level convolutional neural network.
-```
-
-This formatted prompt is then used as input for the model to generate a **citation sentence** describing how **Paper A references Paper B**.

docs/tasks/gen_related_work.md

@@ -1,28 +0,0 @@
-# **Related Work Generation Task - Input Format**
-
-## **Overview**
-The Related Work Generation task generates a structured related work section based on the title and abstract of a given paper. The model analyzes the provided content and produces a coherent paragraph discussing relevant literature and prior work.
-
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Title of Paper: <title of the paper>
-
-Abstract of Paper: <abstract of the paper>
-```
-
-- `<title of the paper>`: The title of the paper for which related work is being generated.
-
-- `<abstract of the paper>`: The abstract of the paper, summarizing its key contributions and findings.
-
-
-### **Example Input**
-```
-Title of Paper: Criticality in Tissue Homeostasis: Models and Experiments
-
-Abstract of Paper: There is considerable theoretical and experimental support to the proposal that tissue homeostasis in the adult skin can be represented as a critical branching process. The homeostatic condition requires that the proliferation rate of the progenitor (P) cells (capable of cell division) is counterbalanced by the loss rate due to the differentiation of a P cell into differentiated (D) cells so that the total number of P cells remains constant. We consider the two-branch and three-branch models of tissue homeostasis to establish homeostasis as a critical phenomenon. It is first shown that some critical branching process theorems correctly predict experimental observations. A number of temporal signatures of the approach to criticality are investigated based on simulation and analytical results. The analogy between a critical branching process and mean-field percolation and sandpile models is invoked to show that the size and lifetime distributions of the populations of P cells have power-law forms. The associated critical exponents have the same magnitudes as in the cases of the mean-field lattice statistical models. The results indicate that tissue homeostasis provides experimental opportunities for testing critical phenomena.
-```
-
-This formatted prompt is then used as input for the model to generate a related work section discussing relevant literature and prior research related to the given paper.

docs/tasks/influential_papers.md

@@ -1,33 +0,0 @@
-# **Influential Papers Recommendation Task - Input Format**
-
-## **Overview**
-The **Influential Papers** task identifies the **K most influential papers** in a citation graph based on their number of citations. The user specifies the **number of papers (K)** to retrieve, and the model returns the **titles and abstracts** of the most cited papers.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Number of papers to consider: <K>
-```
-
-- `<K>`: The number of most influential papers to retrieve.
-
-### **Example Input**
-```
-Number of papers to consider: 3
-```
-
-This formatted prompt is then used as input for the model to generate a ranked list of the most influential papers.
-
-### **Example Output**
-```
-Here are the most influential papers:
-1. Title: Advances in Neural Networks, arXiv 2012.56789, Dec 2020
-   Abstract: This paper presents a comprehensive survey of neural network architectures and training techniques.
-   
-2. Title: Deep Learning for Image Recognition, arXiv 2101.12345, Jan 2021
-   Abstract: We introduce a novel deep learning model that achieves state-of-the-art accuracy on image classification tasks.
-   
-3. Title: Graph-Based Learning Methods, arXiv 2102.54321, Feb 2021
-   Abstract: This work explores the use of graph-based algorithms for semi-supervised learning and knowledge extraction.
-```

docs/tasks/intro_2_abs.md

@@ -1,20 +0,0 @@
-# **Introduction to Abstract Task - Input Format**
-
-## **Overview**
-The **Introduction to Abstract** task generates the **abstract** of a research paper based on its **introduction section**. The user provides the **introduction text**, and the model generates a suitable abstract.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Introduction: <introduction text>
-```
-
-- `<introduction text>`: The full introduction section of the paper.
-
-### **Example Input**
-```
-Introduction: This section provides an overview of the research problem and the motivation for the study. It outlines the objectives of the study and the significance of the research. The introduction also presents a brief review of the literature and the research gap that the study aims to address.
-```
-
-This formatted prompt is then used as input for the model to generate the predicted abstract of the paper.

docs/tasks/link_pred.md

@@ -1,34 +0,0 @@
-# **Citation Link Prediction Task - Input Format**
-
-## **Overview**
-The **Citation Link Prediction** task determines whether **Paper A** will cite **Paper B**. The user provides the **titles and abstracts** of both papers, and the model predicts **"Yes"** or **"No"** based on their relevance.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Title of Paper A: <title of Paper A>
-Abstract of Paper A: <abstract of Paper A>
-Title of Paper B: <title of Paper B>
-Abstract of Paper B: <abstract of Paper B>
-```
-
-- `<title of Paper A>`: The title of Paper A (the potential citing paper).
-- `<abstract of Paper A>`: The abstract of Paper A.
-- `<title of Paper B>`: The title of Paper B (the potential cited paper).
-- `<abstract of Paper B>`: The abstract of Paper B.
-
-### **Example Input**
-```
-Title of Paper A: A Study on Machine Learning
-Abstract of Paper A: This paper presents a study on machine learning algorithms.
-Title of Paper B: A Survey on Deep Learning
-Abstract of Paper B: This paper presents a survey on deep learning algorithms.
-```
-
-After receiving this input, the model will analyze the relationship between **Paper A and Paper B** and provide a **direct answer**:
-
-- **"Yes"** → If Paper A is likely to cite Paper B.
-- **"No"** → If Paper A is unlikely to cite Paper B.
-
-This formatted prompt is then used as input for the model to determine the citation relationship.

docs/tasks/paper_retrieval.md

@@ -1,33 +0,0 @@
-# **Citation Recommendation Task - Input Format**
-
-## **Overview**
-The **Citation Recommendation** task selects the **most likely paper to be cited** by **Paper A** from a list of **candidate papers**. The user provides the **title and abstract of Paper A**, along with the **titles of candidate papers**, and the model predicts which paper is most likely to be cited.
-
-## **Expected Input Format**
-The user input must strictly follow the format below:
-
-```
-Title of the Paper A: <title>
-Abstract of the Paper A: <abstract>
-candidate papers:
-0. <title>
-1. <title>
-2. <title>
-...
-```
-
-- `<title>`: The title of Paper A.
-- `<abstract>`: The abstract of Paper A.
-- **Candidate papers** are listed as `<candidate number>. <title>`.
-
-### **Example Input**
-```
-Title of the Paper A: A New Method for Finding Shortest Paths in Graphs
-Abstract of the Paper A: This paper presents a new method for solving the problem of finding the shortest path between two points in a graph. The method is based on a new algorithm that is more efficient than existing algorithms. The paper also presents experimental results that show the effectiveness of the new method.
-candidate papers:
-0. A Survey of Shortest Path Algorithms
-1. An Improved Algorithm for Finding Shortest Paths
-2. A Comparison of Shortest Path Algorithms
-```
-
-This formatted prompt is then used as input for the model to select the **most relevant paper** that Paper A is likely to cite.