snaykey commited on
Commit
bc76e95
·
verified ·
1 Parent(s): 1af7596

Update logbook: Repro: MemoryBench

Browse files
logbook.json CHANGED
@@ -8,7 +8,7 @@
8
  "icml2026-repro",
9
  "paper-If4X4W2HWx"
10
  ],
11
- "updated_at": "2026-07-17T12:15:54+00:00",
12
  "root": {
13
  "slug": "index",
14
  "title": "Repro: MemoryBench",
@@ -94,6 +94,6 @@
94
  }
95
  ]
96
  },
97
- "agent_view_tokens": 16860,
98
- "revision": "1784290554659007000"
99
  }
 
8
  "icml2026-repro",
9
  "paper-If4X4W2HWx"
10
  ],
11
+ "updated_at": "2026-07-17T12:16:02+00:00",
12
  "root": {
13
  "slug": "index",
14
  "title": "Repro: MemoryBench",
 
94
  }
95
  ]
96
  },
97
+ "agent_view_tokens": 16902,
98
+ "revision": "1784290562492974300"
99
  }
pages/protocol-and-artifacts/page.md CHANGED
@@ -1113,3 +1113,46 @@ grep -n "implicit_feedback" src/generate_dialogs/basic.py
1113
  ]
1114
  }
1115
  ````
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1113
  ]
1114
  }
1115
  ````
1116
+
1117
+
1118
+ ---
1119
+ <!-- trackio-cell
1120
+ {"type": "figure", "id": "cell_c918cef4a06b", "created_at": "2026-07-17T12:15:57+00:00", "title": "SHA-256 inventory"}
1121
+ -->
1122
+ ````html
1123
+ <div style=font-family:system-ui;padding:16px><b>SHA-256 inventory</b><p>Download or inspect the attached raw data for exact machine-readable values.</p></div>
1124
+ ````
1125
+
1126
+ ````raw
1127
+ f1b6706ebb1dbe7a6287c9459c4f6210d01f8b65fac82bbcfa7359ce5e4534a2 artifacts\memorybench-runtime\analysis\claim3_runtime.json
1128
+ 1ada5a8e89be4bc20d3660c5ba6a9ed50257ea6fa18b613ef632c05cf6fefdd1 artifacts\memorybench-runtime\analysis\claim6_paired.csv
1129
+ 977966a438a4805195ea4280f4ec78c51e0542871288a13056de9c7d93f251bc artifacts\memorybench-runtime\analysis\completed_runs.csv
1130
+ 14f91fd115ac9fed7ef407dd21273b73f696f277d1c47b4e5934712d07ebc7ec artifacts\memorybench-runtime\analysis\summary.json
1131
+ 4f7355792a6b77d701c634202aa839bef973170c65396bded35a9f6f473f463c artifacts\memorybench-runtime\calls.jsonl
1132
+ 0dad06f6d94f48b531be674ca05f9b15ef4d6be7599d7400692d2d4bb19f40da artifacts\memorybench-runtime\cost_ledger.json
1133
+ 5b939b1ae805713ff8f6903f00691a409999469ed1579d4a58e98ca89d0293c2 artifacts\memorybench-runtime\runs\20260717T112122Z\results.json
1134
+ e9bd60e583df9e30504a46a0d85c7ed3f8a774272748be6095ac05229e95fa2c artifacts\memorybench-runtime\runs\20260717T112215Z\results.json
1135
+ 7b6afa7df9b099d0f51e7877c46a674d746e359aa87bb8423879eaceb1d9238f artifacts\memorybench-runtime\runs\20260717T112335Z\results.json
1136
+ 5067cb6adc218370be8d9e975f4928aae51f8c9e71c9d1b9803ea439efc2746d artifacts\memorybench-runtime\runs\20260717T112524Z\results.json
1137
+ 8e4ba802dd0af27ceabba86369f53477bac0823f47cd1ba60240a1031acd359f artifacts\memorybench-runtime\runs\20260717T112623Z\results.json
1138
+ bc42fbb50e45db375539fce1a69ba1b2545fe46c57ad228ad6ccd8871f38d7d2 artifacts\memorybench-runtime\runs\20260717T112816Z\results.json
1139
+ c836088be40c611702bf23529365060c0a09048e95c32d5338a1615e37f59baa artifacts\memorybench-runtime\runs\20260717T112951Z\results.json
1140
+ 5758375d0b35e9a4a4e6658da222779af8932209c82ab1b2b727d82173d9bb43 artifacts\memorybench-runtime\runs\20260717T113141Z\results.json
1141
+ 1a31bb0fb303a5e616af50651d16c8885d3eb33b704edea539dea07131576b9a artifacts\memorybench-runtime\runs\20260717T113256Z\results.json
1142
+ ba7195c184154a52d5e35a8ab1bc28f2393d4525749921b47b81478a3a2428b7 artifacts\memorybench-runtime\runs\20260717T113603Z\results.json
1143
+ 750d506baa359903b88b6d79386c82e974c19acdca82e7640d7b6edadbad8e58 artifacts\memorybench-runtime\runs\20260717T113848Z\results.json
1144
+ a2082062bab7d54166d0e844e0ab185757d17185ddce4915b11f7e5d23da8437 artifacts\memorybench-runtime\runs\20260717T114619Z\results.json
1145
+ 2faa64d2869c0e519d488beb1f5bb0add815d11c32464a800a18a2abe22f04bb artifacts\memorybench-runtime\runs\20260717T115724Z\feedback_effect.json
1146
+ 365e65e1a2963c72c297690053cbff78a786dd78cac2c648d217bcf2bfa1335e experiments\analyze_runtime.py
1147
+ 4fb33afbd8841cf4bc46af1019849f5c34a1daaf291e97379c15a5bc4fd88c55 experiments\build_repro_manifest.py
1148
+ 35716a96fa45e7f35aa263cb3bb81b8ab4b734ae119553932e908189abce1050 experiments\cost_guard.py
1149
+ ee538e89d5e732ead9aa2143840d7c3229962038a248de1fb484806a0d3b2d42 experiments\hf_budget_proxy.py
1150
+ 25e3b062ff937625187be731a77874551ae1780754fc1bacfe67f842788e5e35 experiments\hf_canary.py
1151
+ 5fab81b0153b688e6cbb8fd97b21ca4ca076bbc3f44ec7ae544ca29c0a0aba81 experiments\hf_proxy_canary.py
1152
+ 6337898ef35d1471861eb43bf1a20df936f11799246035fcb4c2d351acadd766 experiments\probe_dataset.py
1153
+ fa901afe9154ec635cb1c2ddc9c8078c07a8f4e637f0df52b0107acc3232ac74 experiments\probe_taxonomy_runtime.py
1154
+ 2bd4b4e6a483d9030125f9b0c318c2aa670ae36e168113266bca3faf5380b4e8 experiments\run_feedback_effect.py
1155
+ 59ae472e5f58d5dae2acd627d4a3d9a1dca45c1a0300ac6bdc1a27ca5f711d62 experiments\run_scaled_offpolicy.py
1156
+ 00b2aee7c582f53dadf1c3b5bf6cd7fbf3da242d1a0328edb1338b9aeb318bf8 paper.pdf
1157
+
1158
+ ````