Hugging Face's logo

Yashp2003
/
swebenchpro-repro-artifacts

Model card Files
xet
 Community
swebenchpro-repro-artifacts
File size: 25,106 Bytes
08dd123
 
 
 
 
 
 
ab5a4e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08dd123
 
 
ab5a4e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08dd123
ab5a4e0
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>SWE-Bench Pro Reproduction Poster</title>
<style>
  @page { size: 60in 36in; margin: 0; }
  :root {
    --accent: #2D5F8B;
    --accent-deep: #1F4566;
    --accent-light: #E8F1F8;
    --accent-soft: #D7E5F0;
    --accent-ink: #FFFFFF;
    --emph: #C9A24A;
    --emph-soft: #FFF7E0;
    --emph-ink: #14314A;
    --text-primary: #1A1A1A;
    --text-secondary: #555555;
    --text-muted: #888888;
    --bg-page: #F6F2F0;
    --bg-card: #FFFFFF;
    --bg-card-tint: #FAFAFB;
    --bg-emphasis: var(--accent-light);
    --border-soft: #D8D8D8;
    --border-strong: var(--accent);
    --bg-viewport: #2B2B2B;
    --u: 1.6px;
    --fs-1: calc(9 * var(--u));
    --fs-2: calc(10 * var(--u));
    --fs-3: calc(11 * var(--u));
    --fs-4: calc(12 * var(--u));
    --fs-5: calc(13 * var(--u));
    --fs-6: calc(15 * var(--u));
    --fs-7: calc(16 * var(--u));
    --fs-8: calc(22 * var(--u));
    --fs-9: calc(30 * var(--u));
    --font-serif: "Charter", "Source Serif Pro", "Georgia", serif;
    --font-sans: "Inter", "Helvetica Neue", sans-serif;
    --shadow-card: 0 calc(2 * var(--u)) calc(6 * var(--u)) rgba(45, 95, 139, 0.08);
    --ornament-ink: rgba(45, 95, 139, 0.06);
    --rs: 1;
    --fig-bg: white;
    --fig-frame: var(--border-soft);
  }
  * { box-sizing: border-box; margin: 0; padding: 0; }
  p, li, dd, figcaption, .body-text, .caption, .callout, .section-title, .sb-label, .ts-item, .bs-label, div { text-wrap: pretty; }
  .title { text-wrap: balance; }
  html, body { background: var(--bg-viewport); font-family: var(--font-serif); color: var(--text-primary); -webkit-font-smoothing: antialiased; }
  .poster {
    width: calc(1524 * var(--u)); height: calc(914 * var(--u));
    background: var(--bg-page);
    background-image:
      radial-gradient(ellipse at top left, rgba(45, 95, 139, 0.06), transparent 40%),
      radial-gradient(ellipse at bottom right, rgba(201, 162, 74, 0.05), transparent 50%);
    margin: 20px auto; padding: calc(10 * var(--u)) calc(14 * var(--u));
    display: grid; grid-template-columns: minmax(0, 1fr);
    grid-template-rows: auto auto minmax(0, 1fr) auto auto;
    gap: calc(6 * var(--u)); box-shadow: 0 0 60px rgba(0,0,0,0.5); position: relative; overflow: hidden;
  }
  .poster::before { content: ""; position: absolute; top: 0; left: 0; right: 0; height: calc(8 * var(--u)); background: var(--accent); }
  .header { display: grid; grid-template-columns: 1fr minmax(50%, auto) 1fr; align-items: center; gap: calc(16 * var(--u)); padding: calc(2 * var(--u)) calc(4 * var(--u)) calc(5 * var(--u)); border-bottom: calc(2 * var(--u)) solid var(--accent); }
  .venue-badge { justify-self: start; display: flex; flex-direction: column; align-items: center; justify-content: center; min-width: calc(95 * var(--u)); text-align: center; border-right: calc(1 * var(--u)) solid var(--border-soft); padding-right: calc(12 * var(--u)); }
  .venue-badge .vb-venue { font-family: var(--font-sans); font-weight: 800; font-size: var(--fs-9); color: var(--accent-deep); line-height: 1; letter-spacing: -0.5px; }
  .venue-badge .vb-year { font-family: var(--font-sans); font-size: var(--fs-5); color: var(--text-secondary); margin-top: calc(3 * var(--u)); letter-spacing: 1.2px; }
  .venue-badge .vb-tag { font-family: var(--font-sans); font-size: var(--fs-2); color: var(--accent); font-weight: 700; margin-top: calc(2 * var(--u)); letter-spacing: 1.2px; }
  .title-block { text-align: center; min-width: 0; }
  .title { font-family: var(--font-sans); font-weight: 800; font-size: var(--fs-9); line-height: 1.05; color: var(--accent-deep); letter-spacing: -0.5px; }
  .title .accent { color: var(--emph); }
  .subtitle { font-family: var(--font-sans); font-weight: 500; font-size: var(--fs-5); color: var(--text-secondary); margin-top: calc(2 * var(--u)); font-style: italic; }
  .authors-line { font-family: var(--font-sans); font-size: var(--fs-4); color: var(--accent); font-weight: 600; margin-top: calc(3 * var(--u)); }
  .authors-line .author { margin: 0 calc(4 * var(--u)); }
  .authors-line sup { font-size: 0.7em; color: var(--accent); }
  .authors-line .aff { color: var(--text-secondary); font-weight: 400; display: block; margin-top: calc(2 * var(--u)); font-size: var(--fs-4); }
  .right-block { justify-self: end; display: flex; align-items: center; gap: calc(10 * var(--u)); }
  .qr-block { display: flex; flex-direction: column; align-items: center; gap: calc(2 * var(--u)); }
  .qr-block img { width: calc(85 * var(--u)); height: calc(85 * var(--u)); border: calc(2 * var(--u)) solid var(--accent); border-radius: calc(4 * var(--u) * var(--rs)); background: white; padding: calc(2 * var(--u)); }
  .qr-label { font-family: var(--font-sans); font-size: var(--fs-3); color: var(--accent); font-weight: 600; }
  .framework-banner { display: flex; align-items: center; gap: calc(16 * var(--u)); background: var(--bg-emphasis); border: calc(1 * var(--u)) solid var(--border-soft); border-left: calc(6 * var(--u)) solid var(--accent); border-radius: calc(6 * var(--u) * var(--rs)); padding: calc(6 * var(--u)) calc(14 * var(--u)); }
  .framework-banner .banner-stats { flex: 1; display: grid; grid-template-columns: repeat(4, 1fr); gap: calc(6 * var(--u)); }
  .framework-banner .bs-item { background: white; border: calc(1 * var(--u)) solid var(--border-soft); border-left: calc(3 * var(--u)) solid var(--accent); border-radius: calc(3 * var(--u) * var(--rs)); padding: calc(2 * var(--u)) calc(8 * var(--u)); text-align: center; }
  .framework-banner .bs-num { font-family: var(--font-sans); font-weight: 800; font-size: var(--fs-8); color: var(--accent); line-height: 1; }
  .framework-banner .bs-label { font-family: var(--font-sans); font-size: var(--fs-3); color: var(--text-secondary); margin-top: calc(2 * var(--u)); line-height: 1.2; }
  .framework-banner .fb-text { flex: 1.6; font-family: var(--font-serif); font-size: var(--fs-6); line-height: 1.5; text-wrap: pretty; text-align: center; }
  .framework-banner .fb-text strong { color: var(--accent-deep); }
  .framework-banner .fb-label { display: inline-block; background: var(--accent); color: var(--accent-ink); font-family: var(--font-sans); font-size: var(--fs-5); font-weight: 700; padding: calc(2 * var(--u)) calc(8 * var(--u)); border-radius: calc(4 * var(--u) * var(--rs)); text-transform: uppercase; letter-spacing: 1px; vertical-align: middle; line-height: 1; position: relative; top: calc(-1 * var(--u)); }
  .body-grid { display: grid; grid-template-columns: 1fr 1.05fr 1.05fr 1fr; gap: calc(10 * var(--u)); min-height: 0; }
  .column { display: flex; flex-direction: column; gap: calc(6 * var(--u)); min-height: 0; height: 100%; padding-bottom: calc(4 * var(--u)); }
  .card { background: var(--bg-card); border-radius: calc(5 * var(--u) * var(--rs)); padding: calc(4 * var(--u)) calc(9 * var(--u)); border: calc(1 * var(--u)) solid var(--border-soft); box-shadow: var(--shadow-card); position: relative; }
  .card.tinted { background: var(--bg-card-tint); }
  .card.highlight { border-left: calc(6 * var(--u)) solid var(--accent); background: var(--bg-emphasis); }
  .section-title { font-family: var(--font-sans); font-weight: 700; font-size: var(--fs-7); color: var(--accent-deep); margin-bottom: calc(3 * var(--u)); display: flex; align-items: center; gap: calc(5 * var(--u)); }
  .section-title .st-text { flex: 1; min-width: 0; line-height: 1.18; }
  .section-title .num { display: inline-flex; align-items: center; justify-content: center; width: calc(22 * var(--u)); height: calc(22 * var(--u)); background: var(--accent); color: var(--accent-ink); border-radius: 50%; font-size: var(--fs-5); font-weight: 700; flex-shrink: 0; }
  .section-title .key-mark { color: var(--emph); font-size: var(--fs-3); }
  .body-text, .card p, .card li { font-family: var(--font-serif); font-size: var(--fs-4); line-height: 1.3; color: var(--text-primary); }
  .card ul, .card ol { padding-left: calc(18 * var(--u)); }
  .card li { margin-bottom: calc(2 * var(--u)); }
  .callout { background: var(--accent-light); border-left: calc(4 * var(--u)) solid var(--accent); padding: calc(3 * var(--u)) calc(6 * var(--u)); border-radius: calc(3 * var(--u) * var(--rs)); margin-top: calc(3 * var(--u)); font-size: var(--fs-4); }
  .callout.emph { background: var(--emph-soft); border-left-color: var(--emph); }
  .keyword { color: var(--accent); font-weight: 700; }
  .stat-row { display: flex; gap: calc(6 * var(--u)); margin-top: calc(3 * var(--u)); flex-wrap: wrap; }
  .stat-box { flex: 1; background: white; border: calc(1 * var(--u)) solid var(--border-soft); border-top: calc(3 * var(--u)) solid var(--accent); border-radius: calc(3 * var(--u) * var(--rs)); padding: calc(3 * var(--u)); text-align: center; min-width: 0; }
  .stat-box .sb-num { font-family: var(--font-sans); font-weight: 800; font-size: calc(18 * var(--u)); color: var(--accent-deep); line-height: 1; }
  .stat-box .sb-label { font-family: var(--font-sans); font-size: var(--fs-2); color: var(--text-secondary); margin-top: calc(2 * var(--u)); line-height: 1.15; }
  table.result-table { width: 100%; border-collapse: collapse; margin-top: calc(3 * var(--u)); font-family: var(--font-sans); font-size: var(--fs-3); }
  table.result-table th { background: var(--accent-deep); color: white; padding: calc(2 * var(--u)) calc(3 * var(--u)); text-align: center; font-weight: 700; }
  table.result-table td { padding: calc(2 * var(--u)) calc(3 * var(--u)); text-align: center; border-bottom: calc(1 * var(--u)) solid var(--border-soft); }
  table.result-table td.method { text-align: left; font-weight: 600; }
  table.result-table tr.ours td { background: var(--emph-soft); font-weight: 700; }
  .takeaways-strip { display: flex; align-items: center; gap: calc(10 * var(--u)); background: var(--accent-deep); color: white; border-radius: calc(5 * var(--u) * var(--rs)); padding: calc(5 * var(--u)) calc(12 * var(--u)); }
  .takeaways-strip .ts-title { font-family: var(--font-sans); font-weight: 800; font-size: var(--fs-6); display: flex; align-items: center; gap: calc(4 * var(--u)); flex-shrink: 0; }
  .takeaways-strip .ts-title .num { display: inline-flex; align-items: center; justify-content: center; width: calc(20 * var(--u)); height: calc(20 * var(--u)); background: var(--emph); color: var(--emph-ink); border-radius: 50%; font-size: var(--fs-4); }
  .takeaways-strip .ts-item { flex: 1; font-family: var(--font-sans); font-size: var(--fs-3); line-height: 1.2; }
  .takeaways-strip .ts-key { font-weight: 800; color: var(--emph); }
  .footer { display: flex; justify-content: space-between; align-items: center; font-family: var(--font-sans); font-size: var(--fs-3); color: var(--text-secondary); padding: calc(2 * var(--u)) calc(4 * var(--u)); }
  .footer .repo { color: var(--accent); font-weight: 600; }
  .footer strong { color: var(--accent-deep); }
  /* Interactive hotspot styling */
  .card[data-logbook-target] { cursor: pointer; transition: box-shadow 0.2s, transform 0.2s; }
  .card[data-logbook-target]:hover { box-shadow: 0 calc(4 * var(--u)) calc(12 * var(--u)) rgba(45, 95, 139, 0.2); transform: translateY(calc(-2 * var(--u))); }
  .card[data-logbook-target]::after { content: "Open details ↗"; position: absolute; top: calc(3 * var(--u)); right: calc(3 * var(--u)); font-family: var(--font-sans); font-size: var(--fs-2); color: var(--accent); font-weight: 600; opacity: 0; transition: opacity 0.2s; }
  .card[data-logbook-target]:hover::after { opacity: 1; }
  @media print {
    :root { --u: 1mm; }
    html, body { margin: 0; padding: 0; height: 100%; }
    .poster { width: calc(1524 * var(--u)); height: calc(914 * var(--u)); margin: 0; padding: calc(10 * var(--u)) calc(14 * var(--u)); }
    .card[data-logbook-target]::after { display: none; }
  }
</style>
</head>
<body>
<div class="poster" data-measure-role="poster">

  <header class="header" data-measure-role="header">
    <div class="venue-badge">
      <div class="vb-venue">ICML</div>
      <div class="vb-year">2026</div>
      <div class="vb-tag">REPRO</div>
    </div>
    <div class="title-block">
      <h1 class="title">Reproducing <span class="accent">SWE-Bench Pro</span>: Can AI Agents Solve Long-Horizon SE Tasks?</h1>
      <div class="subtitle">A dataset-audit reproduction of the five headline claims (arXiv 2509.16941 / OpenReview uEVTdoAbnK).</div>
      <div class="authors-line">
        <span class="author">Reproduction by Yashp2003</span>
        <span class="aff">OpenResearch Agent Reproduction Challenge &middot; Hugging Face &times; AlphaXiv</span>
      </div>
    </div>
    <div class="right-block">
      <div class="qr-block">
        <img data-color-exempt="logo" src="data:image/svg+xml;utf8,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><rect width='100' height='100' fill='%23fff'/><g fill='%23222'><rect x='4' y='4' width='26' height='26'/><rect x='70' y='4' width='26' height='26'/><rect x='4' y='70' width='26' height='26'/></g><g fill='%23fff'><rect x='10' y='10' width='14' height='14'/><rect x='76' y='10' width='14' height='14'/><rect x='10' y='76' width='14' height='14'/></g><g fill='%23222'><rect x='14' y='14' width='6' height='6'/><rect x='80' y='14' width='6' height='6'/><rect x='14' y='80' width='6' height='6'/><rect x='38' y='10' width='4' height='4'/><rect x='48' y='10' width='4' height='4'/><rect x='58' y='10' width='4' height='4'/><rect x='34' y='34' width='4' height='4'/><rect x='44' y='38' width='4' height='4'/><rect x='54' y='34' width='4' height='4'/><rect x='62' y='40' width='4' height='4'/><rect x='38' y='46' width='4' height='4'/><rect x='50' y='52' width='4' height='4'/><rect x='62' y='56' width='4' height='4'/><rect x='34' y='60' width='4' height='4'/><rect x='44' y='66' width='4' height='4'/><rect x='56' y='62' width='4' height='4'/><rect x='80' y='80' width='4' height='4'/><rect x='88' y='86' width='4' height='4'/></g><text x='50' y='54' text-anchor='middle' font-family='sans-serif' font-size='6' font-weight='bold' fill='%23888'>QR</text></svg>" alt="QR placeholder">
        <div class="qr-label">Logbook &amp; code</div>
      </div>
    </div>
  </header>

  <section class="framework-banner" data-measure-role="banner">
    <div class="fb-text">
      <span class="fb-label">Verdict</span>
      &nbsp;<strong>5 / 5 claims structurally corroborated.</strong> The public subset (731 problems, 11 repos) is directly verifiable; the full 1,865 / 41 and the held-out (12) + commercial (18) splits are non-public by design.
    </div>
    <div class="banner-stats">
      <div class="bs-item"><div class="bs-num">731</div><div class="bs-label">public<br>instances</div></div>
      <div class="bs-item"><div class="bs-num">11</div><div class="bs-label">public<br>repos</div></div>
      <div class="bs-item"><div class="bs-num">85.6%</div><div class="bs-label">multi-file<br>patches</div></div>
      <div class="bs-item"><div class="bs-num">100%</div><div class="bs-label">human-augmented<br>context</div></div>
    </div>
  </section>

  <div class="body-grid" data-measure-role="body">

    <!-- COLUMN 1 -->
    <div class="column" data-measure-role="column">
      <div class="card highlight" data-measure-role="card" data-logbook-target="claim-1-swe-bench-pro-comprises-1-865-problems-sourced-from-41-actively-maintained-software-repositories-abstract-only">
        <div class="section-title"><span class="num">1</span><span class="st-text">Claims 1 &amp; 2: Scale &amp; Split</span></div>
        <p class="body-text">The paper reports <span class="keyword">1,865 problems across 41 repos</span>, split public (11) / held-out (12) / commercial (18).</p>
        <div class="stat-row">
          <div class="stat-box"><div class="sb-num">731</div><div class="sb-label">verified public instances</div></div>
          <div class="stat-box"><div class="sb-num">11</div><div class="sb-label">verified public repos</div></div>
        </div>
        <div class="callout">11 + 12 + 18 = 41 &mdash; arithmetic is internally consistent. Only the 11 public repos are observable; held-out &amp; commercial splits are locked by design.</div>
      </div>
      <div class="card" data-measure-role="card" data-logbook-target="claim-2-swe-bench-pro-splits-into-public-11-repos-held-out-12-repos-and-commercial-18-proprietary-repos-sets-abstract-only">
        <div class="section-title"><span class="num">2</span><span class="st-text">Public repo breakdown</span></div>
        <table class="result-table">
          <thead><tr><th class="method">Repo</th><th>#</th></tr></thead>
          <tbody>
            <tr><td class="method">ansible/ansible</td><td>96</td></tr>
            <tr><td class="method">internetarchive/openlibrary</td><td>91</td></tr>
            <tr><td class="method">flipt-io/flipt</td><td>85</td></tr>
            <tr><td class="method">qutebrowser/qutebrowser</td><td>79</td></tr>
            <tr><td class="method">gravitational/teleport</td><td>76</td></tr>
            <tr><td class="method">protonmail/webclients</td><td>65</td></tr>
            <tr><td class="method">future-architect/vuls</td><td>62</td></tr>
            <tr><td class="method">navidrome/navidrome</td><td>57</td></tr>
            <tr><td class="method">element-hq/element-web</td><td>56</td></tr>
            <tr><td class="method">NodeBB/NodeBB</td><td>44</td></tr>
            <tr><td class="method">tutao/tutanota</td><td>20</td></tr>
          </tbody>
        </table>
      </div>
      <div class="card" data-measure-role="card" style="padding-bottom:78px">
        <div class="section-title"><span class="num">2b</span><span class="st-text">What we could not count</span></div>
        <p class="body-text">The held-out (12 repos) and commercial (18 repos) splits are <span class="keyword">deliberately non-public</span> &mdash; their 1,134 instances (1,865 &minus; 731) cannot be independently enumerated by external auditors.</p>
        <ul>
          <li>Held-out: access withheld to prevent pre-publication contamination</li>
          <li>Commercial: proprietary, under startup NDAs</li>
        </ul>
        <div class="callout">The lock is what makes the benchmark contamination-resistant (Claim 5).</div>
      </div>
    </div>

    <!-- COLUMN 2 -->
    <div class="column" data-measure-role="column">
      <div class="card highlight" data-measure-role="card" data-logbook-target="claim-3-tasks-are-long-horizon-potentially-requiring-hours-to-days-for-professional-engineers-and-often-spanning-multiple-files-abstract-only">
        <div class="section-title"><span class="num">3</span><span class="st-text">Claim 3: Long-horizon</span></div>
        <p class="body-text">Gold patches are large and <span class="keyword">multi-file</span> &mdash; consistent with "hours to days" professional effort.</p>
        <div class="stat-row">
          <div class="stat-box"><div class="sb-num">85.6%</div><div class="sb-label">touch &gt;1 file</div></div>
          <div class="stat-box"><div class="sb-num">5.08</div><div class="sb-label">mean files / patch</div></div>
          <div class="stat-box"><div class="sb-num">106</div><div class="sb-label">max files</div></div>
        </div>
        <div class="callout">Median 4 files; mean gold-patch size &asymp; 13.3k chars &mdash; substantial cross-file modifications. The max single patch touches 106 files.</div>
      </div>
      <div class="card" data-measure-role="card" data-logbook-target="claim-4-all-swe-bench-pro-tasks-underwent-human-verification-for-adequate-resolution-context-abstract-only">
        <div class="section-title"><span class="num">4</span><span class="st-text">Claim 4: Human-verified</span></div>
        <p class="body-text">Every instance ships the human-augmentation fields; <span class="keyword">100%</span> carry resolvability context.</p>
        <table class="result-table">
          <thead><tr><th class="method">Field</th><th>Coverage</th></tr></thead>
          <tbody>
            <tr class="ours"><td class="method">problem_statement</td><td>731</td></tr>
            <tr class="ours"><td class="method">requirements</td><td>731</td></tr>
            <tr class="ours"><td class="method">interface</td><td>731</td></tr>
            <tr class="ours"><td class="method">test_patch</td><td>731</td></tr>
            <tr class="ours"><td class="method">dockerhub_tag</td><td>731</td></tr>
          </tbody>
        </table>
      </div>
    </div>

    <!-- COLUMN 3 -->
    <div class="column" data-measure-role="column">
      <div class="card highlight" data-measure-role="card" data-logbook-target="claim-5-swe-bench-pro-is-a-contamination-resistant-testbed-spanning-business-applications-b2b-services-and-developer-tools-abstract-only">
        <div class="section-title"><span class="num">5</span><span class="st-text">Claim 5: Contamination-resistant</span></div>
        <p class="body-text">Spans <span class="keyword">business, B2B &amp; dev-tools</span> across go / js / python / ts; containerised, post-cutoff envs.</p>
        <ul>
          <li><strong>Business:</strong> tutanota, protonmail, openlibrary, NodeBB</li>
          <li><strong>B2B:</strong> flipt, teleport, navidrome, vuls</li>
          <li><strong>Dev tools:</strong> ansible, element-web, qutebrowser</li>
        </ul>
        <div class="callout">731 / 731 carry a pinned <code>dockerhub_tag</code> + <code>base_commit</code>; held-out/commercial non-public &rarr; no training data leakage.</div>
      </div>
      <div class="card" data-measure-role="card">
        <div class="section-title"><span class="num">6</span><span class="st-text">Method: How we verified</span></div>
        <p class="body-text">Loaded the official public release <span class="keyword">ScaleAI/SWE-bench_Pro</span> and audited structure with a Hugging Face CPU Job.</p>
        <ul>
          <li>Counted instances &amp; repos; measured patch complexity</li>
          <li>Checked context-augmentation field coverage</li>
          <li>Mapped domains &amp; languages; inspected README schema</li>
        </ul>
        <div class="callout">Job: <code>Yashp2003/6a5c8046&hellip;</code> &middot; artifacts in <code>swebenchpro-repro-artifacts</code> bucket.</div>
      </div>
    </div>

    <!-- COLUMN 4 -->
    <div class="column" data-measure-role="column">
      <div class="card highlight" data-measure-role="card">
        <div class="section-title"><span class="num">7</span><span class="st-text">Scope &amp; Cost</span></div>
        <table class="result-table">
          <thead><tr><th class="method">Axis</th><th>This repro</th><th>Full</th></tr></thead>
          <tbody>
            <tr><td class="method">Scope</td><td>public audit</td><td>agentic solve</td></tr>
            <tr><td class="method">Hardware</td><td>1x CPU</td><td>many GPUs</td></tr>
            <tr><td class="method">Compute</td><td>~3 min</td><td>days</td></tr>
            <tr><td class="method">Cost</td><td>&lt;$0.01</td><td>$100s+</td></tr>
          </tbody>
        </table>
        <div class="callout emph"><strong>Outcome:</strong> 5/5 claims structurally corroborated on the public subset; full 1,865/41 not directly countable (by design).</div>
      </div>
      <div class="card" data-measure-role="card">
        <div class="section-title"><span class="num">8</span><span class="st-text">Artifacts &amp; Links</span></div>
        <ul>
          <li>Dataset: <span class="keyword">ScaleAI/SWE-bench_Pro</span></li>
          <li>Eval repo: scaleapi/SWE-bench_Pro-os</li>
          <li>Job: Yashp2003/6a5c8046d216bd6f3a2009d5</li>
          <li>Bucket: swebenchpro-repro-artifacts</li>
          <li>Paper: arXiv 2509.16941</li>
        </ul>
        <div class="callout">Reproduction is a dataset audit, not an agentic re-solving of tasks (claims are abstract/structural).</div>
      </div>
    </div>

  </div>

  <section class="takeaways-strip" data-measure-role="footer-strip">
    <div class="ts-title"><span class="num">9</span> Takeaways</div>
    <div class="ts-item"><span class="ts-key">Scale.</span> 731 public problems / 11 repos confirmed; 1,865/41 stated.</div>
    <div class="ts-item"><span class="ts-key">Split.</span> 11+12+18=41 matches the public/held-out/commercial design.</div>
    <div class="ts-item"><span class="ts-key">Long.</span> 85.6% multi-file patches, median 4 files.</div>
    <div class="ts-item"><span class="ts-key">Verified.</span> 100% carry requirements/interface/test_patch.</div>
  </section>

  <div class="footer" data-measure-role="footer">
    <div>
      <strong>SWE-Bench Pro Reproduction</strong> &middot; ICML 2026 Agent Repro &middot;
      Logbook: Yashp2003/repro-swe-bench-pro-can-ai-agents-solve-long-horizon-software-engineering-tasks
    </div>
    <div>
      Dataset: <span class="repo">huggingface.co/datasets/ScaleAI/SWE-bench_Pro</span> &nbsp;&middot;&nbsp;
      Job: <span class="repo">hf.co/jobs/Yashp2003/6a5c8046d216bd6f3a2009d5</span>
    </div>
  </div>

</div>
</body>
</html>