Rifqi Hafizuddin Claude Opus 4.8 commited on
Commit
422f333
·
1 Parent(s): 92a2913

[NOTICKET] chore: track stray readiness result (17/17), clean the working tree

Browse files

`readiness_result_2026-07-23_160602.json` sat untracked since before this session — a
valid 17/17 run (8 floor / 5 delta / 1 edge / 3 alignment, accuracy 1.0) on the current
dataset. Per the eval convention (§7F) results are committed, never deleted, so tracking
it is the right cleanup and leaves the tree clean. No code or dataset change.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

eval/readiness/results/readiness_result_2026-07-23_160602.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "run": {
3
+ "timestamp": "2026-07-23T16:06:02",
4
+ "dataset": "readiness_dataset.json",
5
+ "target": "src/agents/report/readiness.is_report_ready",
6
+ "total": 17,
7
+ "passed": 17,
8
+ "accuracy": 1.0,
9
+ "runtime_avg_ms": 0.0
10
+ },
11
+ "alignment_gap": {
12
+ "count": 2,
13
+ "ids": [
14
+ "align_01",
15
+ "align_02"
16
+ ]
17
+ },
18
+ "by_group": {
19
+ "floor": {
20
+ "n": 8,
21
+ "passed": 8,
22
+ "accuracy": 1.0
23
+ },
24
+ "delta": {
25
+ "n": 5,
26
+ "passed": 5,
27
+ "accuracy": 1.0
28
+ },
29
+ "edge": {
30
+ "n": 1,
31
+ "passed": 1,
32
+ "accuracy": 1.0
33
+ },
34
+ "alignment": {
35
+ "n": 3,
36
+ "passed": 3,
37
+ "accuracy": 1.0
38
+ }
39
+ },
40
+ "cases": [
41
+ {
42
+ "id": "floor_01",
43
+ "group": "floor",
44
+ "expected_ready": false,
45
+ "got_ready": false,
46
+ "expected_missing": [
47
+ "at least one completed analysis"
48
+ ],
49
+ "got_missing": [
50
+ "at least one completed analysis"
51
+ ],
52
+ "correct": true,
53
+ "aligned": false,
54
+ "gap": false,
55
+ "latency_ms": 0.0
56
+ },
57
+ {
58
+ "id": "floor_02",
59
+ "group": "floor",
60
+ "expected_ready": false,
61
+ "got_ready": false,
62
+ "expected_missing": [
63
+ "at least one completed analysis"
64
+ ],
65
+ "got_missing": [
66
+ "at least one completed analysis"
67
+ ],
68
+ "correct": true,
69
+ "aligned": false,
70
+ "gap": false,
71
+ "latency_ms": 0.0
72
+ },
73
+ {
74
+ "id": "floor_03",
75
+ "group": "floor",
76
+ "expected_ready": false,
77
+ "got_ready": false,
78
+ "expected_missing": [
79
+ "at least one completed analysis"
80
+ ],
81
+ "got_missing": [
82
+ "at least one completed analysis"
83
+ ],
84
+ "correct": true,
85
+ "aligned": false,
86
+ "gap": false,
87
+ "latency_ms": 0.0
88
+ },
89
+ {
90
+ "id": "floor_04",
91
+ "group": "floor",
92
+ "expected_ready": true,
93
+ "got_ready": true,
94
+ "expected_missing": [],
95
+ "got_missing": [],
96
+ "correct": true,
97
+ "aligned": true,
98
+ "gap": false,
99
+ "latency_ms": 0.0
100
+ },
101
+ {
102
+ "id": "floor_05",
103
+ "group": "floor",
104
+ "expected_ready": true,
105
+ "got_ready": true,
106
+ "expected_missing": [],
107
+ "got_missing": [],
108
+ "correct": true,
109
+ "aligned": true,
110
+ "gap": false,
111
+ "latency_ms": 0.0
112
+ },
113
+ {
114
+ "id": "floor_06",
115
+ "group": "floor",
116
+ "expected_ready": true,
117
+ "got_ready": true,
118
+ "expected_missing": [],
119
+ "got_missing": [],
120
+ "correct": true,
121
+ "aligned": true,
122
+ "gap": false,
123
+ "latency_ms": 0.0
124
+ },
125
+ {
126
+ "id": "floor_07",
127
+ "group": "floor",
128
+ "expected_ready": true,
129
+ "got_ready": true,
130
+ "expected_missing": [],
131
+ "got_missing": [],
132
+ "correct": true,
133
+ "aligned": true,
134
+ "gap": false,
135
+ "latency_ms": 0.0
136
+ },
137
+ {
138
+ "id": "floor_08",
139
+ "group": "floor",
140
+ "expected_ready": true,
141
+ "got_ready": true,
142
+ "expected_missing": [],
143
+ "got_missing": [],
144
+ "correct": true,
145
+ "aligned": true,
146
+ "gap": false,
147
+ "latency_ms": 0.0
148
+ },
149
+ {
150
+ "id": "delta_01",
151
+ "group": "delta",
152
+ "expected_ready": false,
153
+ "got_ready": false,
154
+ "expected_missing": [
155
+ "a new analysis since the last report"
156
+ ],
157
+ "got_missing": [
158
+ "a new analysis since the last report"
159
+ ],
160
+ "correct": true,
161
+ "aligned": true,
162
+ "gap": false,
163
+ "latency_ms": 0.0
164
+ },
165
+ {
166
+ "id": "delta_02",
167
+ "group": "delta",
168
+ "expected_ready": true,
169
+ "got_ready": true,
170
+ "expected_missing": [],
171
+ "got_missing": [],
172
+ "correct": true,
173
+ "aligned": true,
174
+ "gap": false,
175
+ "latency_ms": 0.0
176
+ },
177
+ {
178
+ "id": "delta_03",
179
+ "group": "delta",
180
+ "expected_ready": true,
181
+ "got_ready": true,
182
+ "expected_missing": [],
183
+ "got_missing": [],
184
+ "correct": true,
185
+ "aligned": true,
186
+ "gap": false,
187
+ "latency_ms": 0.0
188
+ },
189
+ {
190
+ "id": "delta_04",
191
+ "group": "delta",
192
+ "expected_ready": false,
193
+ "got_ready": false,
194
+ "expected_missing": [
195
+ "a new analysis since the last report"
196
+ ],
197
+ "got_missing": [
198
+ "a new analysis since the last report"
199
+ ],
200
+ "correct": true,
201
+ "aligned": true,
202
+ "gap": false,
203
+ "latency_ms": 0.0
204
+ },
205
+ {
206
+ "id": "delta_05",
207
+ "group": "delta",
208
+ "expected_ready": false,
209
+ "got_ready": false,
210
+ "expected_missing": [
211
+ "a new analysis since the last report"
212
+ ],
213
+ "got_missing": [
214
+ "a new analysis since the last report"
215
+ ],
216
+ "correct": true,
217
+ "aligned": true,
218
+ "gap": false,
219
+ "latency_ms": 0.0
220
+ },
221
+ {
222
+ "id": "edge_01",
223
+ "group": "edge",
224
+ "expected_ready": false,
225
+ "got_ready": false,
226
+ "expected_missing": [
227
+ "at least one completed analysis"
228
+ ],
229
+ "got_missing": [
230
+ "at least one completed analysis"
231
+ ],
232
+ "correct": true,
233
+ "aligned": false,
234
+ "gap": false,
235
+ "latency_ms": 0.0
236
+ },
237
+ {
238
+ "id": "align_01",
239
+ "group": "alignment",
240
+ "expected_ready": true,
241
+ "got_ready": true,
242
+ "expected_missing": [],
243
+ "got_missing": [],
244
+ "correct": true,
245
+ "aligned": false,
246
+ "gap": true,
247
+ "latency_ms": 0.0
248
+ },
249
+ {
250
+ "id": "align_02",
251
+ "group": "alignment",
252
+ "expected_ready": true,
253
+ "got_ready": true,
254
+ "expected_missing": [],
255
+ "got_missing": [],
256
+ "correct": true,
257
+ "aligned": false,
258
+ "gap": true,
259
+ "latency_ms": 0.0
260
+ },
261
+ {
262
+ "id": "align_03",
263
+ "group": "alignment",
264
+ "expected_ready": true,
265
+ "got_ready": true,
266
+ "expected_missing": [],
267
+ "got_missing": [],
268
+ "correct": true,
269
+ "aligned": true,
270
+ "gap": false,
271
+ "latency_ms": 0.0
272
+ }
273
+ ]
274
+ }