Index 706 verified experimental models

README.md

@@ -8,7 +8,7 @@ tags:
 
 Terminal fine-tuned models for studying correctness and verified output support. Browse by study, base model, domain, method and seed; restore each export from its recorded immutable revision.
 
-**Paper artifact collection · 701 / 715 selected exports verified. Transfer is in progress.**
+**Paper artifact collection · 706 / 715 selected exports verified. Transfer is in progress.**
 
 The fixed archival selection contains admitted completed models from the source studies listed below. Counts describe archive availability, not live training progress or a replacement for the papers’ frozen analysis sets.
 
@@ -21,15 +21,15 @@ The broader paper collection is being expanded to additional baselines, ablation
 | [E78](experiments/E78/README.md) | Verified replay · Qwen2.5-0.5B | 50 / 50 |
 | [E79](experiments/E79/README.md) | Verified replay · Falcon3-1B | 49 / 49 |
 | [E80-R1](experiments/E80-R1/README.md) | Verified replay · Qwen2.5-3B | 50 / 50 |
-| [E118](experiments/E118/README.md) | MaxRL × verified replay · Level 1 | 138 / 146 |
-| [E119](experiments/E119/README.md) | Four-method factorial · Level 2 | 88 / 90 |
+| [E118](experiments/E118/README.md) | MaxRL × verified replay · Level 1 | 139 / 146 |
+| [E119](experiments/E119/README.md) | Four-method factorial · Level 2 | 89 / 90 |
 | [E120-R1](experiments/E120-R1/README.md) | Uniform versus fresh-frequency replay | 43 / 44 |
 | [E95](experiments/E95/README.md) | Plain GRPO · initial cross-scale cohort | 0 / 0 |
 | [E114](experiments/E114/README.md) | Plain GRPO · Qwen2.5-3B seed extension | 20 / 20 |
 | [E97](experiments/E97/README.md) | UCPO · Qwen2.5-0.5B initial domains | 15 / 15 |
 | [E99](experiments/E99/README.md) | UCPO · Falcon3-1B | 25 / 25 |
 | [E115](experiments/E115/README.md) | UCPO · domain and scale extension | 10 / 10 |
-| [E98-R1](experiments/E98-R1/README.md) | Sparse RLEP-Dr · Qwen2.5-0.5B | 12 / 15 |
+| [E98-R1](experiments/E98-R1/README.md) | Sparse RLEP-Dr · Qwen2.5-0.5B | 15 / 15 |
 | [E100](experiments/E100/README.md) | Sparse RLEP-Dr · Falcon3-1B | 22 / 22 |
 | [E116](experiments/E116/README.md) | Sparse RLEP-Dr · domain and scale extension | 10 / 10 |
 | [E81](experiments/E81/README.md) | Fixed semantic + replay · Qwen2.5-0.5B | 20 / 20 |
@@ -46,7 +46,7 @@ The broader paper collection is being expanded to additional baselines, ablation
 
 | Scientific records selected | Deployable model exports | Verified model exports | Model weights unavailable |
 | ---: | ---: | ---: | ---: |
-| 770 | 715 | 701 | 55 |
+| 770 | 715 | 706 | 55 |
 
 Model weights are unavailable for 55 retained scientific records: E95 (55). Their metadata and admitted results remain part of the research record; they are excluded from the downloadable-model catalog.
 

catalog.json

@@ -1,9 +1,9 @@
 {
   "schema": "experiment-model-archive-catalog-v1",
-  "updated_at_utc": "2026-09-15T18:46:20.438368+00:00",
+  "updated_at_utc": "2026-09-15T18:49:22.969319+00:00",
   "repo_id": "od2961/maxent-grpo-models",
   "expected_model_count": 715,
-  "verified_model_count": 701,
+  "verified_model_count": 706,
   "models": [
     {
       "experiment": "E100",
@@ -2885,6 +2885,18 @@
       "local_weights_retired": true,
       "export_bytes": 6187842646
     },
+    {
+      "experiment": "E118",
+      "model": "Qwen2.5-3B-Instruct",
+      "domain": "mathir",
+      "method": "maxrl",
+      "seed": 72,
+      "step": 3073,
+      "repo_prefix": "experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-72/step-03073",
+      "commit_sha": "54689d5d20dded2fc2e8259ddbfcc73810cb5f1c",
+      "local_weights_retired": false,
+      "export_bytes": 6187842646
+    },
     {
       "experiment": "E118",
       "model": "Qwen2.5-3B-Instruct",
@@ -3917,6 +3929,18 @@
       "local_weights_retired": true,
       "export_bytes": 1003977886
     },
+    {
+      "experiment": "E119",
+      "model": "Qwen2.5-0.5B-Instruct",
+      "domain": "pantry_plan",
+      "method": "replay_maxrl",
+      "seed": 43,
+      "step": 3073,
+      "repo_prefix": "experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl/seed-43/step-03073",
+      "commit_sha": "e2bd91ee47f7842a449600711c5d0aceb728a350",
+      "local_weights_retired": false,
+      "export_bytes": 1003977886
+    },
     {
       "experiment": "E119",
       "model": "Qwen2.5-0.5B-Instruct",
@@ -8117,6 +8141,42 @@
       "local_weights_retired": false,
       "export_bytes": 1003977886
     },
+    {
+      "experiment": "E98-R1",
+      "model": "Qwen2.5-0.5B-Instruct",
+      "domain": "python_factors",
+      "method": "rlep_dr_sparse",
+      "seed": 45,
+      "step": 3073,
+      "repo_prefix": "experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-45/step-03073",
+      "commit_sha": "1d29ce5219f8e339083227721e845fcd6037f272",
+      "local_weights_retired": false,
+      "export_bytes": 1003977886
+    },
+    {
+      "experiment": "E98-R1",
+      "model": "Qwen2.5-0.5B-Instruct",
+      "domain": "python_factors",
+      "method": "rlep_dr_sparse",
+      "seed": 46,
+      "step": 3073,
+      "repo_prefix": "experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-46/step-03073",
+      "commit_sha": "36ad376062f83d5e04ec468139296d2e1f99de9f",
+      "local_weights_retired": false,
+      "export_bytes": 1003977886
+    },
+    {
+      "experiment": "E98-R1",
+      "model": "Qwen2.5-0.5B-Instruct",
+      "domain": "python_factors",
+      "method": "rlep_dr_sparse",
+      "seed": 47,
+      "step": 3073,
+      "repo_prefix": "experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-47/step-03073",
+      "commit_sha": "84d3f195443ab5c387b5cdafc6864c242d3296e8",
+      "local_weights_retired": false,
+      "export_bytes": 1003977886
+    },
     {
       "experiment": "E99",
       "model": "Falcon3-1B-Instruct",

experiments/E118/README.md

@@ -18,7 +18,7 @@ These are terminal exports from the registered eight-pass training horizon. The
 
 | Registered new training cells | Scientific records selected | Deployable exports selected | Verified exports |
 | ---: | ---: | ---: | ---: |
-| 150 | 146 | 146 | 138 |
+| 150 | 146 | 146 | 139 |
 
 Scientific records preserve the admitted result identity. Deployable exports additionally have available model weights; verified exports have completed remote verification. Cells outside the fixed selection are not silently counted, and unverified model folders are not linked below.
 
@@ -26,7 +26,7 @@ Scientific records preserve the admitted result identity. Deployable exports add
 | --- | ---: | --- |
 | [Qwen2.5-0.5B-Instruct](#model-qwen05b) | 50 / 50 | 43, 44, 45, 46, 47 |
 | [Falcon3-1B-Instruct](#model-falcon1b) | 50 / 50 | 55, 56, 57, 58, 59 |
-| [Qwen2.5-3B-Instruct](#model-qwen3b) | 38 / 46 | 70, 71, 72, 73, 74 |
+| [Qwen2.5-3B-Instruct](#model-qwen3b) | 39 / 46 | 70, 71, 72, 73, 74 |
 
 ## Methods and collections
 
@@ -47,7 +47,7 @@ Binary MaxRL objective on fresh rollouts; zero replay derivative.
 - [Qwen2.5-0.5B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-0.5B-Instruct/python_factors/maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-3B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/countdown/maxrl) — 3 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-3B-Instruct · Graph Coloring](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/graph_coloring/maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
-- [Qwen2.5-3B-Instruct · MathIR](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl) — 3 verified exports. Exact immutable revisions are in the model tables below.
+- [Qwen2.5-3B-Instruct · MathIR](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl) — 4 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-3B-Instruct · PantryPlan](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/pantry_plan/maxrl) — 2 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-3B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E118/Qwen2.5-3B-Instruct/python_factors/maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
 
@@ -191,7 +191,7 @@ Browse by domain: [Countdown](#domain-countdown) · [Graph Coloring](#domain-gra
 <a id="domain-mathir"></a>
 ### MathIR
 
-**26 / 29** selected exports verified.
+**27 / 29** selected exports verified.
 
 | Model | Method | Seed | Terminal export | Immutable revision |
 | --- | --- | ---: | --- | --- |
@@ -217,6 +217,7 @@ Browse by domain: [Countdown](#domain-countdown) · [Graph Coloring](#domain-gra
 | Qwen2.5-0.5B-Instruct | Re:MaxRL | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/fb521c01c8fd0111375e899a7f8e7ba3139467b5/experiments/E118/Qwen2.5-0.5B-Instruct/mathir/replay_maxrl/seed-47/step-03073) | [`fb521c01c8fd`](https://huggingface.co/od2961/maxent-grpo-models/tree/fb521c01c8fd0111375e899a7f8e7ba3139467b5/experiments/E118/Qwen2.5-0.5B-Instruct/mathir/replay_maxrl/seed-47/step-03073) |
 | Qwen2.5-3B-Instruct | MaxRL | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/413f58dbe6962270518735139aa05f1a03893e4c/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-70/step-03073) | [`413f58dbe696`](https://huggingface.co/od2961/maxent-grpo-models/tree/413f58dbe6962270518735139aa05f1a03893e4c/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-70/step-03073) |
 | Qwen2.5-3B-Instruct | MaxRL | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/2c06d07c8af5aa76b5725eaf2d3980152ac3fb06/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-71/step-03073) | [`2c06d07c8af5`](https://huggingface.co/od2961/maxent-grpo-models/tree/2c06d07c8af5aa76b5725eaf2d3980152ac3fb06/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-71/step-03073) |
+| Qwen2.5-3B-Instruct | MaxRL | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/54689d5d20dded2fc2e8259ddbfcc73810cb5f1c/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-72/step-03073) | [`54689d5d20dd`](https://huggingface.co/od2961/maxent-grpo-models/tree/54689d5d20dded2fc2e8259ddbfcc73810cb5f1c/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-72/step-03073) |
 | Qwen2.5-3B-Instruct | MaxRL | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/fadea76b2146402772e84675d2c237a56f9136fa/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-74/step-03073) | [`fadea76b2146`](https://huggingface.co/od2961/maxent-grpo-models/tree/fadea76b2146402772e84675d2c237a56f9136fa/experiments/E118/Qwen2.5-3B-Instruct/mathir/maxrl/seed-74/step-03073) |
 | Qwen2.5-3B-Instruct | Re:MaxRL | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/36bdd48a3c8c6121b8d9d699d64194611958d7af/experiments/E118/Qwen2.5-3B-Instruct/mathir/replay_maxrl/seed-70/step-03073) | [`36bdd48a3c8c`](https://huggingface.co/od2961/maxent-grpo-models/tree/36bdd48a3c8c6121b8d9d699d64194611958d7af/experiments/E118/Qwen2.5-3B-Instruct/mathir/replay_maxrl/seed-70/step-03073) |
 | Qwen2.5-3B-Instruct | Re:MaxRL | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f3a7454cf8a004a9a9677dcf8f68ca714bcb99d2/experiments/E118/Qwen2.5-3B-Instruct/mathir/replay_maxrl/seed-71/step-03073) | [`f3a7454cf8a0`](https://huggingface.co/od2961/maxent-grpo-models/tree/f3a7454cf8a004a9a9677dcf8f68ca714bcb99d2/experiments/E118/Qwen2.5-3B-Instruct/mathir/replay_maxrl/seed-71/step-03073) |

experiments/E119/README.md

@@ -18,13 +18,13 @@ These are terminal exports from the registered eight-pass training horizon. The
 
 | Registered new training cells | Scientific records selected | Deployable exports selected | Verified exports |
 | ---: | ---: | ---: | ---: |
-| 100 | 90 | 90 | 88 |
+| 100 | 90 | 90 | 89 |
 
 Scientific records preserve the admitted result identity. Deployable exports additionally have available model weights; verified exports have completed remote verification. Cells outside the fixed selection are not silently counted, and unverified model folders are not linked below.
 
 | Model | Verified / selected | Seeds in selection |
 | --- | ---: | --- |
-| [Qwen2.5-0.5B-Instruct](#model-qwen05b) | 88 / 90 | 43, 44, 45, 46, 47 |
+| [Qwen2.5-0.5B-Instruct](#model-qwen05b) | 89 / 90 | 43, 44, 45, 46, 47 |
 
 ## Methods and collections
 
@@ -69,7 +69,7 @@ The same binary MaxRL objective plus verified canonical replay.
 - [Qwen2.5-0.5B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/countdown/replay_maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-0.5B-Instruct · Graph Coloring](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/graph_coloring/replay_maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-0.5B-Instruct · MathIR](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/mathir/replay_maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
-- [Qwen2.5-0.5B-Instruct · PantryPlan](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl) — 1 verified exports. Exact immutable revisions are in the model tables below.
+- [Qwen2.5-0.5B-Instruct · PantryPlan](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl) — 2 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-0.5B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E119/Qwen2.5-0.5B-Instruct/python_factors/replay_maxrl) — 5 verified exports. Exact immutable revisions are in the model tables below.
 
 <a id="models"></a>
@@ -192,7 +192,7 @@ Browse by domain: [Countdown](#domain-countdown) · [Graph Coloring](#domain-gra
 <a id="domain-pantry_plan"></a>
 ### PantryPlan
 
-**8 / 10** selected exports verified.
+**9 / 10** selected exports verified.
 
 | Model | Method | Seed | Terminal export | Immutable revision |
 | --- | --- | ---: | --- | --- |
@@ -203,6 +203,7 @@ Browse by domain: [Countdown](#domain-countdown) · [Graph Coloring](#domain-gra
 | Qwen2.5-0.5B-Instruct | Re:Dr.GRPO | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/8016ef10f1b351f12c1d56e69bfceb77862575fd/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-43/step-03073) | [`8016ef10f1b3`](https://huggingface.co/od2961/maxent-grpo-models/tree/8016ef10f1b351f12c1d56e69bfceb77862575fd/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-43/step-03073) |
 | Qwen2.5-0.5B-Instruct | Re:Dr.GRPO | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/b4a0819d758e2863daa35d6645db67a4290b17c4/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-46/step-03073) | [`b4a0819d758e`](https://huggingface.co/od2961/maxent-grpo-models/tree/b4a0819d758e2863daa35d6645db67a4290b17c4/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-46/step-03073) |
 | Qwen2.5-0.5B-Instruct | Re:Dr.GRPO | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/9429b7fe311605d5cfb9276ab99ccd359caa0882/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-47/step-03073) | [`9429b7fe3116`](https://huggingface.co/od2961/maxent-grpo-models/tree/9429b7fe311605d5cfb9276ab99ccd359caa0882/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_drgrpo/seed-47/step-03073) |
+| Qwen2.5-0.5B-Instruct | Re:MaxRL | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/e2bd91ee47f7842a449600711c5d0aceb728a350/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl/seed-43/step-03073) | [`e2bd91ee47f7`](https://huggingface.co/od2961/maxent-grpo-models/tree/e2bd91ee47f7842a449600711c5d0aceb728a350/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl/seed-43/step-03073) |
 | Qwen2.5-0.5B-Instruct | Re:MaxRL | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/4987bf0d721fcbabdcf23a8acf33bd5eb55747e9/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl/seed-44/step-03073) | [`4987bf0d721f`](https://huggingface.co/od2961/maxent-grpo-models/tree/4987bf0d721fcbabdcf23a8acf33bd5eb55747e9/experiments/E119/Qwen2.5-0.5B-Instruct/pantry_plan/replay_maxrl/seed-44/step-03073) |
 
 ## Model-family shortcuts

experiments/E98-R1/README.md

@@ -18,13 +18,13 @@ These are terminal exports from the registered eight-pass training horizon. The
 
 | Registered new training cells | Scientific records selected | Deployable exports selected | Verified exports |
 | ---: | ---: | ---: | ---: |
-| 15 | 15 | 15 | 12 |
+| 15 | 15 | 15 | 15 |
 
 Scientific records preserve the admitted result identity. Deployable exports additionally have available model weights; verified exports have completed remote verification. Cells outside the fixed selection are not silently counted, and unverified model folders are not linked below.
 
 | Model | Verified / selected | Seeds in selection |
 | --- | ---: | --- |
-| [Qwen2.5-0.5B-Instruct](#model-qwen05b) | 12 / 15 | 43, 44, 45, 46, 47 |
+| [Qwen2.5-0.5B-Instruct](#model-qwen05b) | 15 / 15 | 43, 44, 45, 46, 47 |
 
 ## Methods and collections
 
@@ -35,7 +35,7 @@ Sparse replay of verified successes in observed frequency, without canonical-key
 
 - [Qwen2.5-0.5B-Instruct · Graph Coloring](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E98-R1/Qwen2.5-0.5B-Instruct/graph_coloring/rlep_dr_sparse) — 5 verified exports. Exact immutable revisions are in the model tables below.
 - [Qwen2.5-0.5B-Instruct · PantryPlan](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E98-R1/Qwen2.5-0.5B-Instruct/pantry_plan/rlep_dr_sparse) — 5 verified exports. Exact immutable revisions are in the model tables below.
-- [Qwen2.5-0.5B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse) — 2 verified exports. Exact immutable revisions are in the model tables below.
+- [Qwen2.5-0.5B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse) — 5 verified exports. Exact immutable revisions are in the model tables below.
 
 <a id="models"></a>
 ## Verified models
@@ -65,12 +65,15 @@ Transfer in progress. No verified model folders are available in this subset yet
 <a id="domain-python_factors"></a>
 ### Python Factors
 
-**2 / 5** selected exports verified.
+**5 / 5** selected exports verified.
 
 | Model | Method | Seed | Terminal export | Immutable revision |
 | --- | --- | ---: | --- | --- |
 | Qwen2.5-0.5B-Instruct | Sparse RLEP-Dr | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1a4f9a67d36444083ae4ec0b08d5724f66d27b8f/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-43/step-03073) | [`1a4f9a67d364`](https://huggingface.co/od2961/maxent-grpo-models/tree/1a4f9a67d36444083ae4ec0b08d5724f66d27b8f/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-43/step-03073) |
 | Qwen2.5-0.5B-Instruct | Sparse RLEP-Dr | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/5aad6555ef4292f17c586749fd90f9fead091eac/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-44/step-03073) | [`5aad6555ef42`](https://huggingface.co/od2961/maxent-grpo-models/tree/5aad6555ef4292f17c586749fd90f9fead091eac/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-44/step-03073) |
+| Qwen2.5-0.5B-Instruct | Sparse RLEP-Dr | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1d29ce5219f8e339083227721e845fcd6037f272/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-45/step-03073) | [`1d29ce5219f8`](https://huggingface.co/od2961/maxent-grpo-models/tree/1d29ce5219f8e339083227721e845fcd6037f272/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-45/step-03073) |
+| Qwen2.5-0.5B-Instruct | Sparse RLEP-Dr | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/36ad376062f83d5e04ec468139296d2e1f99de9f/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-46/step-03073) | [`36ad376062f8`](https://huggingface.co/od2961/maxent-grpo-models/tree/36ad376062f83d5e04ec468139296d2e1f99de9f/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-46/step-03073) |
+| Qwen2.5-0.5B-Instruct | Sparse RLEP-Dr | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/84d3f195443ab5c387b5cdafc6864c242d3296e8/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-47/step-03073) | [`84d3f195443a`](https://huggingface.co/od2961/maxent-grpo-models/tree/84d3f195443ab5c387b5cdafc6864c242d3296e8/experiments/E98-R1/Qwen2.5-0.5B-Instruct/python_factors/rlep_dr_sparse/seed-47/step-03073) |
 
 <a id="domain-mathir"></a>
 ### MathIR