The dataset of the paper titled "Context-Aware Code Change Embedding for Better Patch Correctness Assessment"

<p>This&nbsp;is&nbsp;the&nbsp;online&nbsp;repository&nbsp;of&nbsp;the&nbsp;paper&nbsp;&quot;Context-Aware&nbsp;Code&nbsp;Change&nbsp;Embedding&nbsp;for&nbsp;Better&nbsp;Patch&nbsp;Correctness&nbsp;Assessment&quot;&nbsp;under&nbsp;review&nbsp;by&nbsp;SANER2021.&nbsp;We&nbsp;release&nbsp;the&nbsp;source&nbsp;code&nbsp;of&nbsp;Cache,&nbsp;the&nbsp;patches&nbsp;used&nbsp;in&nbsp;our&nbsp;evaluation,&nbsp;as&nbsp;well&nbsp;as&nbsp;the&nbsp;experiment&nbsp;results.</p> <ul> <li> <p>Patches:&nbsp;Three&nbsp;patch&nbsp;benchmarks&nbsp;included&nbsp;in&nbsp;our&nbsp;study.&nbsp;</p> <ul> <li> <p>Tian: The patches from Tian&#39;s <a href="https://conf.researchr.org/details/ase-2020/ase-2020-papers/3/Evaluating-Representation-Learning-of-Code-Changes-for-Predicting-Patch-Correctness-i">ASE20</a>&nbsp;paper.</p> </li> <li> <p>Wang: The patches from Wang&#39;s <a href="https://conf.researchr.org/details/ase-2020/ase-2020-papers/54/Automated-Patch-Correctness-Assessment-How-Far-are-We-">ASE20</a>&nbsp;paper.</p> </li> <li> <p>Cache:&nbsp;The&nbsp;patches&nbsp;collected&nbsp;by&nbsp;ourselves,&nbsp;which&nbsp;is&nbsp;consist&nbsp;of&nbsp;17,377&nbsp;deduplicated&nbsp;overfitting&nbsp;patches&nbsp;from&nbsp;<a href="https://dl.acm.org/doi/10.1145/3338906.3338911">RepairThemAll</a>&nbsp;and&nbsp;17,377&nbsp;instances&nbsp;from&nbsp;<a href="https://dl.acm.org/doi/10.1145/3379597.3387491">ManySStuBs</a>(used&nbsp;as&nbsp;correct&nbsp;patches).</p> </li> </ul> </li> <li> <p>Results:</p> <ul> <li> <p>RQ1:&nbsp;The&nbsp;detailed&nbsp;result&nbsp;files&nbsp;in&nbsp;RQ1,&nbsp;which&nbsp;are&nbsp;named&nbsp;by&nbsp;the&nbsp;format&nbsp;of <em>[model]_[classifier]</em>.csv.</p> <p>For&nbsp;example,&nbsp;the&nbsp;file&nbsp;named&nbsp;<strong>BERT_DT.csv</strong>&nbsp;in&nbsp;the&nbsp;folder&nbsp;<strong>Tian&#39;s_dataset</strong>&nbsp;means&nbsp;that&nbsp;this&nbsp;file&nbsp;is&nbsp;the&nbsp;result&nbsp;of&nbsp;patches&nbsp;from&nbsp;<strong>Tian&#39;s</strong>&nbsp;study&nbsp;embedded&nbsp;by&nbsp;<strong>BERT</strong>&nbsp;and&nbsp;classified&nbsp;by&nbsp;<strong>Decision&nbsp;Tree</strong>.</p> <ul> <li> <p>Tian&#39;s_dataset :&nbsp;The&nbsp;detailed&nbsp;result&nbsp;files&nbsp;on&nbsp;Tian&#39;s&nbsp;dataset.&nbsp;</p> </li> <li> <p>Cache_dataset :&nbsp;The&nbsp;detailed&nbsp;result&nbsp;files&nbsp;on&nbsp;our&nbsp;own&nbsp;dataset.&nbsp;</p> </li> <li> <p>Cross_dataset :&nbsp;The&nbsp;detailed&nbsp;result&nbsp;files&nbsp;of&nbsp;representation&nbsp;learning&nbsp;techniques&nbsp;when&nbsp;training&nbsp;on&nbsp;our&nbsp;own&nbsp;dataset&nbsp;and&nbsp;testing&nbsp;on&nbsp;Tian&#39;s&nbsp;dataset.</p> </li> </ul> </li> <li>RQ2: The detailed result files in RQ2. <ul> <li> <p>Wang_Cache.csv:&nbsp;The&nbsp;detailed&nbsp;result&nbsp;of&nbsp;Cache&nbsp;on&nbsp;the&nbsp;dataset&nbsp;from&nbsp;Wang&#39;s <a href="https://conf.researchr.org/details/ase-2020/ase-2020-papers/54/">ASE20</a>.</p> </li> <li> <p>ODS_Cache.csv:&nbsp;The&nbsp;datailed&nbsp;result&nbsp;of&nbsp;Cache&nbsp;on&nbsp;the&nbsp;dataset&nbsp;from&nbsp;Xiong&#39;s&nbsp;<a href="https://dl.acm.org/doi/10.1145/3180155.3180182">ICSE18</a>&nbsp;paper.&nbsp;We&nbsp;directly&nbsp;compare&nbsp;against&nbsp;the&nbsp;results&nbsp;reported&nbsp;by&nbsp;the&nbsp;authors&nbsp;of&nbsp;ODS&nbsp;on&nbsp;139&nbsp;patches&nbsp;from&nbsp;Xiong&#39;s&nbsp;paper&nbsp;since&nbsp;the&nbsp;data&nbsp;and&nbsp;source&nbsp;code&nbsp;of&nbsp;ODS&nbsp;is&nbsp;unavailable.</p> </li> </ul> </li> </ul> </li> </ul> <p>Source:&nbsp;The&nbsp;source&nbsp;code&nbsp;and&nbsp;lib&nbsp;for&nbsp;running&nbsp;Cache is available at&nbsp;<a href="https://github.com/APR-Study/Cache">https://github.com/APR-Study/Cache</a>.</p>