File size: 3,340 Bytes
d81bfd6
 
2f90d6e
d81bfd6
 
 
 
 
 
 
 
 
 
2f90d6e
d81bfd6
2f90d6e
 
 
d81bfd6
 
2f90d6e
 
 
d81bfd6
 
 
2f90d6e
 
 
d81bfd6
 
 
2f90d6e
 
 
d81bfd6
 
 
2f90d6e
 
 
d81bfd6
 
 
2f90d6e
 
 
d81bfd6
 
 
2f90d6e
 
 
d81bfd6
2f90d6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d81bfd6
 
 
2f90d6e
 
 
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
{
  "schema_version": 1,
  "title": "Learning Randomized Reductions — five-claim reproduction",
  "emoji": "🎯",
  "space_id": "DineshAI/hCAEcqig2C",
  "paper": {
    "arxiv_id": "2412.18134",
    "openreview_id": "hCAEcqig2C"
  },
  "tags": [
    "icml2026-repro",
    "paper-hCAEcqig2C"
  ],
  "updated_at": "2026-07-26T00:00:00+00:00",
  "root": {
    "slug": "current-scorecard",
    "title": "Current five-claim scorecard",
    "file": "pages/current-scorecard/page.md",
    "children": [
      {
        "slug": "current-claim-1-section-4",
        "title": "Current Claim 1 — Section 4 theory",
        "file": "pages/current-claim-1-section-4/page.md",
        "children": []
      },
      {
        "slug": "current-claims-2-4-cumulative",
        "title": "Current Claims 2–4 — cumulative full-scale evidence",
        "file": "pages/current-claims-2-4-cumulative/page.md",
        "children": []
      },
      {
        "slug": "current-claim-5-backends",
        "title": "Current Claim 5 — regression versus MILP",
        "file": "pages/current-claim-5-backends/page.md",
        "children": []
      },
      {
        "slug": "current-methods",
        "title": "Current methods, environment, and provenance",
        "file": "pages/current-methods/page.md",
        "children": []
      },
      {
        "slug": "visibility-matrix",
        "title": "Evaluator visibility matrix",
        "file": "pages/visibility-matrix/page.md",
        "children": []
      },
      {
        "slug": "failure-boundaries",
        "title": "Failure boundaries and historical rejected baseline",
        "file": "pages/failure-boundaries/page.md",
        "children": []
      },
      {
        "slug": "historical-index",
        "title": "Historical evidence — judged revision ae46d4e",
        "file": "pages/index.md",
        "children": [
          {
            "slug": "historical-vanilla",
            "title": "Historical accepted evidence — vanilla and sigmoid",
            "file": "pages/claim-1-vanilla-bitwen-finds-43-80-rsrs-54-incl-sigmoid/page.md",
            "children": []
          },
          {
            "slug": "historical-agentic",
            "title": "Historical accepted evidence — agentic coverage",
            "file": "pages/claim-2-agentic-bitwen-finds-64-80-rsrs-80/page.md",
            "children": []
          },
          {
            "slug": "historical-rejected-neural",
            "title": "Historical rejected baseline — agentic versus neural",
            "file": "pages/claim-3-agentic-outperforms-neural-baselines/page.md",
            "children": []
          },
          {
            "slug": "historical-methods",
            "title": "Historical methods",
            "file": "pages/methods-and-environment/page.md",
            "children": []
          },
          {
            "slug": "historical-controls",
            "title": "Historical controls",
            "file": "pages/negative-controls-and-falsification/page.md",
            "children": []
          },
          {
            "slug": "historical-conclusion",
            "title": "Historical conclusion",
            "file": "pages/conclusion/page.md",
            "children": []
          }
        ]
      }
    ]
  },
  "agent_view_tokens": 16000,
  "revision": "five-claim-candidate"
}