# The 199 LongMemEval-S question ids behind the judged numbers in docs/BENCHMARKS.md
# ("Answer accuracy, judged, in the MemoryBench harness", seed 20260903). Copied from the
# checkpoint files of those MemoryBench runs, which all used this same list. One id per
# line, sorted. By type: 53 multi-session, 53 temporal-reasoning, 31 knowledge-update,
# 28 single-session-user, 22 single-session-assistant, 12 single-session-preference;
# 11 of the ids end in _abs and are unanswerable.
001be529
01493427
06db6396
07741c45
078150f1
0862e8bf
0862e8bf_abs
08e075c7
08f4fc43
099778bb
09d032c9
0bc8ad93
0ddfec37_abs
10d9b85a
129d1232
1568498a
157a136e
16c90bf4
184da446
1c0ddc50
1d4da289
1da05512
22d2cb42
2318644b
26bdc477
28dc39ac
29f2956b
29f2956b_abs
2b8f3739
2bf43736
2ebe6c90
2ebe6c92
3249768e
35a27287
36b9f61e
37f165cf
38146c39
3a704032
3d86fd0a
3f1e9474
3fdac837
3fe836c9
4100d0a0
41275add
41698283
42ec0761
46a3abf7
4bc144e2
4f54b7c9
5025383b
505af2f5
50635ada
51a45a95
51b23612
51c32626
54026fce
561fabcd
577d4d32
58bf7951
5a7937c8
5c40ec5b
5d3d2817
60036106
60159905
603deb26
60472f9c
618f13b2
6222b6eb
66f24dbb
6a1eabeb
6b168ec8
6cb6f249
71017277
71315a70
7401057b
75f70248
76d63226
7e00a6cb
7e974930
80ec1f4f
85fa3a3f
86b68151
86f00804
88432d0a
89527b6b
8a2466db
8aef76bc
8b9d4367
8cf51dda
8e9d538c
945e3d21
94f70d80
95bcc1c8
982b5123
982b5123_abs
993da5e2
9bbe84a2
9d25d4e0
9ea5eabc
a06e4cfe
a2f3aa27
a3332713
a346bb18
a40e080f
a4996e51
ac031881
af8d2e46
b01defab
b0479f84
b29f3365
b320f3f8
b46e15ee
b5ef892d
b759caee
ba358f49_abs
bbf86515
bcbe585f
bf659f65
c19f7a0b
c4f10528
c7dc5443
c9f37c46
cc06de0d
cc5ded98
d01c6aa8
d24813b1
d596882b
d6062bb9
dad224aa
dc439ea3
e47becba
e493bb7c
e56a43b9
e5ba910e_abs
e6041065
e9327a54
eac54add
eace081b
ec81a493
edced276
edced276_abs
eeda8a6d
efc3f7c2
f0853d11
f0e564bc
f35224e0
f4f1d8a4
f4f1d8a4_abs
f685340e
f685340e_abs
f9e8c073
fca70973
fea54f57
gpt4_0a05b494
gpt4_0b2f1d21
gpt4_1916e0ea
gpt4_194be4b3
gpt4_1a1dc16d
gpt4_1d80365e
gpt4_1e4a8aeb
gpt4_2655b836
gpt4_2ba83207
gpt4_2c50253f
gpt4_2d58bcd6
gpt4_2f56ae70
gpt4_2f8be40d
gpt4_31ff4165
gpt4_468eb064
gpt4_4929293a
gpt4_5501fe77
gpt4_59149c77
gpt4_59149c78
gpt4_68e94287
gpt4_68e94288
gpt4_6dc9b45b
gpt4_7abb270c
gpt4_7bc6cf22
gpt4_7ca326fa
gpt4_7ddcf75f
gpt4_7de946e7
gpt4_7f6b06db
gpt4_8279ba02
gpt4_85da3956
gpt4_8e165409
gpt4_93159ced_abs
gpt4_a1b77f9c
gpt4_a56e767c
gpt4_ab202e7f
gpt4_af6db32f
gpt4_c27434e8_abs
gpt4_d12ceb0e
gpt4_d84a3211
gpt4_d9af6064
gpt4_e061b84f
gpt4_e061b84g
gpt4_e072b769
gpt4_e414231e
gpt4_ec93e27f
gpt4_f420262d
