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 | def aggregate_by_institution(combined_data):
"""Aggregate individual rankings by institution affiliation."""
inst_data = defaultdict(
lambda: {
"affiliation": "",
"combined_score": 0,
"artifact_score": 0,
"artifact_citations": 0,
"citation_score": 0,
"ae_score": 0,
"artifacts": 0,
"badges_functional": 0,
"badges_reproducible": 0,
"ae_memberships": 0,
"chair_count": 0,
"total_papers": 0,
"num_authors": 0,
"conferences": set(),
"years": defaultdict(int),
}
)
for person in combined_data:
affiliation = _normalize_affiliation(person.get("affiliation", "").strip())
# Skip entries with no affiliation or placeholder affiliations
if not affiliation or affiliation == "Unknown" or affiliation.startswith("_"):
affiliation = "Unknown"
inst = inst_data[affiliation]
inst["affiliation"] = affiliation
inst["combined_score"] += person.get("combined_score", 0)
inst["artifact_score"] += person.get("artifact_score", 0)
inst["artifact_citations"] += person.get("artifact_citations", 0)
inst["citation_score"] += person.get("citation_score", 0)
inst["ae_score"] += person.get("ae_score", 0)
inst["artifacts"] += person.get("artifacts", 0)
inst["badges_functional"] += person.get("badges_functional", 0)
inst["badges_reproducible"] += person.get("badges_reproducible", 0)
inst["ae_memberships"] += person.get("ae_memberships", 0)
inst["chair_count"] += person.get("chair_count", 0)
inst["total_papers"] += person.get("total_papers", 0)
inst["num_authors"] += 1
# Aggregate conferences
if person.get("conferences"):
inst["conferences"].update(person["conferences"])
# Aggregate years
if person.get("years"):
for year, count in person["years"].items():
inst["years"][year] += count
# Convert to list and calculate derived fields
institutions = []
for affiliation, data in inst_data.items():
if data["artifacts"] > data["total_papers"]:
raise ValueError(
f"Invariant violation for institution '{affiliation}': artifacts ({data['artifacts']}) > total_papers ({data['total_papers']})"
)
if data["badges_reproducible"] > data["artifacts"]:
raise ValueError(
f"Invariant violation for institution '{affiliation}': reproduced_badges ({data['badges_reproducible']}) > artifacts ({data['artifacts']})"
)
if data["badges_functional"] > data["artifacts"]:
raise ValueError(
f"Invariant violation for institution '{affiliation}': functional_badges ({data['badges_functional']}) > artifacts ({data['artifacts']})"
)
# Calculate artifact rate
artifact_rate = 0
if data["total_papers"] > 0:
artifact_rate = round((data["artifacts"] / data["total_papers"]) * 100, 1)
# Calculate A:E ratio
ae_ratio = None
if data["ae_score"] > 0:
ae_ratio = round(data["artifact_score"] / data["ae_score"], 2)
elif data["artifact_score"] > 0:
ae_ratio = None # Artifact-only, will display as ∞
else:
ae_ratio = 0.0 # Neither artifacts nor AE service
# Classify institution role based on A:E ratio
if ae_ratio is None:
# Artifact-only (ae_score == 0, artifact_score > 0) → creator
role = "Producer"
elif ae_ratio == 0.0:
# AE-only or neither (artifact_score == 0) → evaluator
role = "Consumer"
elif ae_ratio > 2.0:
role = "Producer"
elif ae_ratio < 0.5:
role = "Consumer"
else:
role = "Balanced"
# Only include institutions with meaningful contributions, excluding incomplete affiliations
if data["combined_score"] >= 3 and affiliation.strip() not in ("Univ", "University", "Unknown", "_"):
institutions.append(
{
"affiliation": data["affiliation"],
"combined_score": data["combined_score"],
"artifact_score": data["artifact_score"],
"artifact_citations": data["artifact_citations"],
"citation_score": data["citation_score"],
"ae_score": data["ae_score"],
"ae_ratio": ae_ratio,
"role": role,
"artifacts": data["artifacts"],
"badges_functional": data["badges_functional"],
"badges_reproducible": data["badges_reproducible"],
"ae_memberships": data["ae_memberships"],
"chair_count": data["chair_count"],
"total_papers": data["total_papers"],
"artifact_rate": artifact_rate,
"num_authors": data["num_authors"],
"conferences": sorted(list(data["conferences"])),
"years": dict(data["years"]),
}
)
# Sort by combined_score descending
institutions.sort(key=lambda x: x["combined_score"], reverse=True)
return institutions
|