@@ -805,9 +805,18 @@ <h2 class="title is-3 has-text-centered">Evaluation Framework</h2>
805805 />
806806 </ div >
807807 < div class ="content has-text-justified ">
808- < p > Our evaluation framework employs three core metrics:</ p >
808+ < p > Our evaluation framework employs four core metrics:</ p >
809809 < div class ="columns " style ="margin-top: 10px ">
810- < div class ="column is-4 ">
810+ < div class ="column is-3 ">
811+ < div class ="box ">
812+ < h5 class ="title is-5 "> 🔧 Render Score (T/V)</ h5 >
813+ < p style ="text-align: left ">
814+ Binary metric (0 or 1) indicating whether the generated code can be
815+ successfully loaded or rendered without syntax errors
816+ </ p >
817+ </ div >
818+ </ div >
819+ < div class ="column is-3 ">
811820 < div class ="box ">
812821 < h5 class ="title is-5 "> ✓ Syntax Score (T)</ h5 >
813822 < p style ="text-align: left ">
@@ -816,7 +825,7 @@ <h5 class="title is-5">✓ Syntax Score (T)</h5>
816825 </ p >
817826 </ div >
818827 </ div >
819- < div class ="column is-4 ">
828+ < div class ="column is-3 ">
820829 < div class ="box ">
821830 < h5 class ="title is-5 "> 🔍 Keyword Matching (V)</ h5 >
822831 < p style ="text-align: left ">
@@ -825,7 +834,7 @@ <h5 class="title is-5">🔍 Keyword Matching (V)</h5>
825834 </ p >
826835 </ div >
827836 </ div >
828- < div class ="column is-4 ">
837+ < div class ="column is-3 ">
829838 < div class ="box ">
830839 < h5 class ="title is-5 "> 👁️ VQA Score (V)</ h5 >
831840 < p style ="text-align: left ">
@@ -835,6 +844,37 @@ <h5 class="title is-5">👁️ VQA Score (V)</h5>
835844 </ div >
836845 </ div >
837846 </ div >
847+
848+ < div style ="margin-top: 40px ">
849+ < h3 class ="title is-4 has-text-centered "> Score Aggregation Methods</ h3 >
850+ < div class ="columns " style ="margin-top: 20px ">
851+ < div class ="column is-6 ">
852+ < div class ="box has-background-info-light ">
853+ < h5 class ="title is-5 has-text-centered "> 🎨 Renderable Formats</ h5 >
854+ < p class ="has-text-centered " style ="margin-bottom: 15px ">
855+ < em > HTML, React, SVG, LaTeX, Mermaid, etc.</ em >
856+ </ p >
857+ < div class ="content ">
858+ < pre style ="background: #f5f5f5; padding: 15px; border-radius: 5px; font-size: 0.9em; "> final_score = (0.2 × render_score) +
859+ (0.1 × keyword_matching) +
860+ (0.7 × vqa_score)</ pre >
861+ </ div >
862+ </ div >
863+ </ div >
864+ < div class ="column is-6 ">
865+ < div class ="box has-background-light ">
866+ < h5 class ="title is-5 has-text-centered "> 📝 Non-Renderable Formats</ h5 >
867+ < p class ="has-text-centered " style ="margin-bottom: 15px ">
868+ < em > JSON, XML, YAML, CSV, TOML</ em >
869+ </ p >
870+ < div class ="content ">
871+ < pre style ="background: #f5f5f5; padding: 15px; border-radius: 5px; font-size: 0.9em; "> final_score = (0.2 × render_score) +
872+ (0.8 × syntax_score)</ pre >
873+ </ div >
874+ </ div >
875+ </ div >
876+ </ div >
877+ </ div >
838878 </ div >
839879 </ div >
840880 </ div >
0 commit comments