[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-187772-en":3,"doc-seo-187772-105":30,"detail-sidebar-cat-1-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":11,"category_id":12,"category_name":13,"doc_title":14,"doc_description":15,"doc_content":16,"file_id":17,"file_url":18,"file_type":19,"file_size":20,"view_count":11,"is_deleted":4,"is_public":11,"is_downloadable":11,"audit_status":11,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":15,"update_tm":28,"read_time":29},187772,1099525198933,"Terk","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",1,11,"Presentations","Relevant-Identifier Prompting Strategy for Bug Repair Results Analysis","Relevant-Identifier Prompting Strategy is described as a method to generate targeted prompts for automated bug repair. The approach extracts lines from a buggy file, ranks lines by similarity using Levenshtein ratio, extracts candidate identifiers, finds accessible identifiers, intersects relevant and accessible sets, gathers type information, and builds prompts from these signals. Experiments report comparative performance across projects (e.g., Chart, Closure, Lang, Math, Mockito, Time) and analyze effects of masking rates, masking styles, strategies, and configuration variants.","|  |  | max_length |  |  |  |\n| --- | --- | --- | --- | --- | --- |\n|  |  |  |  |  |  |\n|  |  |  |  |  |  |\n|  | Decoder |  |  |  |  |\n|  |  |  |  |  |  |\n|  |  |  |  |  |  |\n| if (arr.len > |  |  |  |  |  |\n\n\n|  | \u003CMASK> :arr\u003Cbr>\u003CMASK> :max_length |  |  |  |  |\n| --- | --- | --- | --- | --- | --- |\n|  |  |  |  |  |  |\n|  |  | Encoder |  |  |  |\n|  |  |  |  |  |  |\n| if (\u003CMASK> .len > \u003CMASK>) { |  |  |  |  |  |\n\n| |  masked span token | \u003Cbr>Large\u003Cbr>Language Model\u003Cbr>| | ... generated code |\n| --- | --- | --- | --- | --- |\n| CategoryDataset dataset = \u003Cbr>this.plot.getDataset(index); if (\u003CSPAN>) {\u003Cbr>} ret~~urn result; ~~ dataset != null original buggy code\u003Cbr>...\u003Cbr>\u003Cbr>|  |  | CategoryDataset dataset = \u003Cbr>this.plot.getDataset(index); if (dataset == null) {\u003Cbr>return result;\u003Cbr>}\u003Cbr>...\u003Cbr>\u003Cbr>|  |\n\n| Algorithm 1 Relevant-Identifier Prompting Strategy |\n| --- |\n| Inputs: Buggy project, file and line: Proj , File, buggy line\u003Cbr>Output: Relevant-Identifier: prompts\u003Cbr>1: lines := EXTRACTLINES(File)\u003Cbr>2: similarities, identifiers := [ ], [ ]\u003Cbr>3: for line in lines do\u003Cbr>4: similarities.append(LEVENSHTEINRATIO(buggy line, line))\u003Cbr>5: lines ranked := RANKLINES(lines, similarities)\u003Cbr>6: for line in lines ranked do\u003Cbr>7: line identifiers := EXTRACTIDS(line)\u003Cbr>8: identifiers.extend(SIMPLEFILTER(line identifiers))\u003Cbr>9: accessibles := FINDACCESSIDS(Proj , File, buggy line)\u003Cbr>10: relevants := identifiers ∩ accessibles\u003Cbr>11: type infos := FINDTYPEINFO(Proj , relevants)\u003Cbr>12: prompts := BUILDPROMPTS(relevants, type infos) |\n\n| if (objectType != null) { |\n| --- |\n| - boolean isOverride = t.inGlobalScope() && |\n| /* use (Node) getJSDocInfo() in the next line */ |\n| + boolean isOverride = parent.getJSDocInfo() != null && |\n| parent.getType() == Token .ASSIGN && |\n\n\n| MockHandlerInterface\u003CT> oldMockHandler = getMockHandler(mock); |\n| --- |\n|  - MethodInterceptorFilter newFilter = new MethodInterceptor. . . \u003Cbr> /* use (MockUtil) getMockHandler() in the next line */  |\n| + MockHandler\u003CT> newMockHandler = new MockHandler\u003CT>(oldMockHandler); |\n| + MethodInterceptorFilter newFilter = newMethodInterceptorFilter(\u003Cbr>+ newMockHandler.getMockSettings()); |\n| ((Factory) mock) .setCallback(0, newFilter); |\n\n\n| int p = NodeUtil .precedence(type); |  |  |  |  |\n| --- | --- | --- | --- | --- |\n| - | Context | rhsContext | = | Context.OTHER; |\n| + | Context | rhsContext | = | getContextForNoInOperator(context); |\n| addExpr(first, p + 1, context); |  |  |  |  |\n\n\n| Project | FitRepair | CodeT5×4 | AlphaRepair | SelfAPR | RewardRepair | Recoder | TBar | CURE | CoCoNuT | PraPR | DLFix |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| Chart | 8 | 8 | 9 | 7 | 5 | 10 | 11 | 10 | 7 | 7 | 5 |\n| Closure | 29 | 23 | 23 | 19 | 15 | 21 | 16 | 14 | 9 | 12 | 11 |\n| Lang | 19 | 18 | 13 | 10 | 7 | 11 | 13 | 9 | 7 | 6 | 8 |\n| Math | 24 | 23 | 21 | 22 | 19 | 18 | 22 | 19 | 16 | 10 | 13 |\n| Mockito | 6 | 5 | 5 | 3 | 3 | 2 | 3 | 4 | 4 | 3 | 1 |\n| Time | 3 | 3 | 3 | 3 | 1 | 3 | 3 | 1 | 1 | 3 | 2 |\n| Total | 89 | 80 | 74 | 64 | 50 | 65 | 68 | 57 | 44 | 41 | 40 |\n\n\n| Project | Chart | Closure | Lang | Math | Mockito | Time | Average |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| CodeT5×4 | 34 | 510 | 803 | 693 | 1058 | 787 | 618 |\n| FitRepair | 20 | 414 | 356 | 448 | 378 | 271 | 363 |\n| Improvement | 41% | 19% | 56% | 35% | 64% | 66% | 41% |\n\n\n| Strategy | \\#Corr. / \\#Plaus. | \\#Corr./\\#Plaus. | Comp. | \\#Unique comp. |\n| --- | --- | --- | --- | --- |\n|  | (All) | (New) | Error pct | per bug |\n| Repetitive (default) | 15 / 30 | 2 / 3 | 82% | 138 |\n| Non-Repetitive | 14 / 25 | 1 / 2 | 79% | 104 |\n\n\n| Mask Rate | \\#Corr. / \\#Plaus.\u003Cbr>(All) | \\#Corr./\\#Plaus.\u003Cbr>(New) | Comp.\u003Cbr>Error pct | \\#Unique comp.\u003Cbr>per bug |\n| --- | --- | --- | --- | --- |\n| 10% | 16 / 23 | 2 / 2 | 83% | 79 |\n| 20% | 14 / 27 | 2 / 4 | 88% | 75 |\n| 30% | 14 / 30 | 2 / 4 | 87% | 92 |\n| 40% | 15 / 29 | 2 / 4 | 85% | 102 |\n| 50%(default) | 15 / 30 | 2 / 3 | 82% | 1","cbCaingz9ojv1q2u","https://ap.wps.com/l/cbCaingz9ojv1q2u","pdf",964527,13,"English","en",105,"# Relevant-Identifier Prompting Strategy\n## Inputs and Output\n## Procedure Steps\n## Experimental Results and Ablations","[{\"question\":\"What is the main output of the Relevant-Identifier Prompting Strategy?\",\"answer\":\"It outputs Relevant-Identifier prompts constructed from extracted relevant identifiers and their type information for guiding bug repair.\"},{\"question\":\"How are relevant identifiers selected for prompt building?\",\"answer\":\"The method ranks candidate lines by similarity to the buggy line, extracts identifiers from ranked lines, finds accessible identifiers in the project context, then intersects both sets and gathers type info before building prompts.\"},{\"question\":\"How do masking rate and masking method affect the results?\",\"answer\":\"The document presents performance changes across mask rates (e.g., 10% to 90%) and compares masking styles such as AST masking, single-line masking, and template masking, each with different correctness and error-rate outcomes.\"}]","Relevant-Identifier Prompting Strategy for Bug Repair Results Analysis | PDF",1788385323,5,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":14,"keywords":34,"description":15,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"relevant-identifier-prompting-strategy-for-bug-repair-results-analysis","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":11},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/template/","Template",2,{"item":49,"name":13,"@type":43,"position":50},"https://docshare.wps.com/template/presentations/",3,{"item":52,"name":14,"@type":43,"position":53},"https://docshare.wps.com/template/relevant-identifier-prompting-strategy-for-bug-repair-results-analysis/187772/",4,{"url":52,"name":14,"@type":55,"author":56,"headline":14,"publisher":58,"fileFormat":61,"inLanguage":23,"description":15,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-09-04","2026-09-02",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main output of the Relevant-Identifier Prompting Strategy?","Question",{"text":76,"@type":77},"It outputs Relevant-Identifier prompts constructed from extracted relevant identifiers and their type information for guiding bug repair.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are relevant identifiers selected for prompt building?",{"text":81,"@type":77},"The method ranks candidate lines by similarity to the buggy line, extracts identifiers from ranked lines, finds accessible identifiers in the project context, then intersects both sets and gathers type info before building prompts.",{"name":83,"@type":74,"acceptedAnswer":84},"How do masking rate and masking method affect the results?",{"text":85,"@type":77},"The document presents performance changes across mask rates (e.g., 10% to 90%) and compares masking styles such as AST masking, single-line masking, and template masking, each with different correctness and error-rate outcomes.","https://schema.org",{"og:url":52,"og:type":88,"og:title":14,"og:site_name":59,"og:description":15},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,97,102,107,112,117,122,127,131],{"id":12,"doc_module":11,"doc_module_name":46,"category_name":13,"show_sort_weight":95,"slug":96},90,"presentations",{"id":98,"doc_module":11,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},12,"Resumes",80,"resumes",{"id":103,"doc_module":11,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},14,"Invoices",70,"invoices",{"id":108,"doc_module":11,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},15,"Posters",60,"posters",{"id":113,"doc_module":11,"doc_module_name":46,"category_name":114,"show_sort_weight":115,"slug":116},16,"Social Media",50,"social-media",{"id":118,"doc_module":11,"doc_module_name":46,"category_name":119,"show_sort_weight":120,"slug":121},17,"Forms",40,"forms",{"id":123,"doc_module":11,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},18,"Letters",30,"letters",{"id":128,"doc_module":11,"doc_module_name":46,"category_name":129,"show_sort_weight":29,"slug":130},21,"Paper Templates","papers-templates",{"id":132,"doc_module":11,"doc_module_name":46,"category_name":133,"show_sort_weight":4,"slug":134},158,"General","general-158"]