# E80-R1 · Verified replay · Qwen2.5-3B

Does the matched Dr.GRPO versus verified-replay comparison replicate with Qwen2.5-3B?

[Archive home](../../README.md) · [Study design](#study-design) · [Coverage](#archive-coverage) · [Models](#models) · [Comparators](#comparators)

<a id="study-design"></a>
## Study design

Level 1 · five domains · five seeds (70–74) · Dr.GRPO and Re:Dr. E80-R1 is the corrected replication and retains its own source identity; the superseded E80 is not substituted.

Experiment 1: retention across model scales. These are also the Qwen2.5-3B Dr.GRPO comparators for the Level-1 factorial.

These are terminal exports from the registered eight-pass training horizon. The stored export-step label is 3073; the papers’ audited pass-8 evaluation endpoint is optimizer step 3072. The archive preserves that original export convention and does not imply an additional evaluated training update.

<a id="archive-coverage"></a>
## Archive coverage

| Registered new training cells | Scientific records selected | Deployable exports selected | Verified exports |
| ---: | ---: | ---: | ---: |
| 50 | 50 | 50 | 50 |

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 |
| --- | ---: | --- |
| [Qwen2.5-3B-Instruct](#model-qwen3b) | 50 / 50 | 70, 71, 72, 73, 74 |

## Methods and collections

<a id="method-control"></a>
### Dr.GRPO · `control`

Compute-matched control with an exactly zero replay derivative.

- [Qwen2.5-3B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control) — 5 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/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control) — 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/E80-R1/Qwen2.5-3B-Instruct/mathir/control) — 5 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/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control) — 5 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/E80-R1/Qwen2.5-3B-Instruct/python_factors/control) — 5 verified exports. Exact immutable revisions are in the model tables below.

<a id="method-replay"></a>
### Re:Dr · `replay`

Dr.GRPO with uniform likelihood rehearsal over retained verified canonical keys.

- [Qwen2.5-3B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay) — 5 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/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay) — 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/E80-R1/Qwen2.5-3B-Instruct/mathir/replay) — 5 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/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay) — 5 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/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay) — 5 verified exports. Exact immutable revisions are in the model tables below.

<a id="models"></a>
## Verified models

Browse by domain: [Countdown](#domain-countdown) · [Graph Coloring](#domain-graph_coloring) · [Python Factors](#domain-python_factors) · [MathIR](#domain-mathir) · [PantryPlan](#domain-pantry_plan).

<a id="domain-countdown"></a>
### Countdown

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Qwen2.5-3B-Instruct | Dr.GRPO | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/0658fcd9202b8e7877a4aab58a492f4f02e5797c/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-70/step-03073) | [`0658fcd9202b`](https://huggingface.co/od2961/maxent-grpo-models/tree/0658fcd9202b8e7877a4aab58a492f4f02e5797c/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/ecbe6381739ba69e74b5d97ad78d7a26defd58aa/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-71/step-03073) | [`ecbe6381739b`](https://huggingface.co/od2961/maxent-grpo-models/tree/ecbe6381739ba69e74b5d97ad78d7a26defd58aa/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f9a9c15443d37676fc5ad0e5c4d86f1c8807e972/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-72/step-03073) | [`f9a9c15443d3`](https://huggingface.co/od2961/maxent-grpo-models/tree/f9a9c15443d37676fc5ad0e5c4d86f1c8807e972/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/88d548548e888c4f072f60a6afe8d6f397d145ad/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-73/step-03073) | [`88d548548e88`](https://huggingface.co/od2961/maxent-grpo-models/tree/88d548548e888c4f072f60a6afe8d6f397d145ad/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/db02d0f0caa086d87ef954a0ccb8552c0e686c1d/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-74/step-03073) | [`db02d0f0caa0`](https://huggingface.co/od2961/maxent-grpo-models/tree/db02d0f0caa086d87ef954a0ccb8552c0e686c1d/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/control/seed-74/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7bbeba5ed63cbe73f588fbbab21e44961e3fc2bd/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-70/step-03073) | [`7bbeba5ed63c`](https://huggingface.co/od2961/maxent-grpo-models/tree/7bbeba5ed63cbe73f588fbbab21e44961e3fc2bd/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/2129e6d9003128daafe54e4359f2ebc898132fd4/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-71/step-03073) | [`2129e6d90031`](https://huggingface.co/od2961/maxent-grpo-models/tree/2129e6d9003128daafe54e4359f2ebc898132fd4/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f14a651fb363272dc80efbd31443334f00184dd2/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-72/step-03073) | [`f14a651fb363`](https://huggingface.co/od2961/maxent-grpo-models/tree/f14a651fb363272dc80efbd31443334f00184dd2/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cb44d04a2541ba1f6f01c392737dab43d2ccba3b/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-73/step-03073) | [`cb44d04a2541`](https://huggingface.co/od2961/maxent-grpo-models/tree/cb44d04a2541ba1f6f01c392737dab43d2ccba3b/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/399aff6fb84470c26952e7d2e71a163940036906/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-74/step-03073) | [`399aff6fb844`](https://huggingface.co/od2961/maxent-grpo-models/tree/399aff6fb84470c26952e7d2e71a163940036906/experiments/E80-R1/Qwen2.5-3B-Instruct/countdown/replay/seed-74/step-03073) |

<a id="domain-graph_coloring"></a>
### Graph Coloring

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Qwen2.5-3B-Instruct | Dr.GRPO | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/d0ac4c57f193aa92970f096dae9d7ab96d4f5d32/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-70/step-03073) | [`d0ac4c57f193`](https://huggingface.co/od2961/maxent-grpo-models/tree/d0ac4c57f193aa92970f096dae9d7ab96d4f5d32/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/0019495e9c396c11c96af2db8d310f3c4a1b88ea/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-71/step-03073) | [`0019495e9c39`](https://huggingface.co/od2961/maxent-grpo-models/tree/0019495e9c396c11c96af2db8d310f3c4a1b88ea/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cf3c48d345c794b31be9c5ce2b1ed5c793614f61/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-72/step-03073) | [`cf3c48d345c7`](https://huggingface.co/od2961/maxent-grpo-models/tree/cf3c48d345c794b31be9c5ce2b1ed5c793614f61/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/387eb22bcaefd8349123c87d3786997007fd1451/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-73/step-03073) | [`387eb22bcaef`](https://huggingface.co/od2961/maxent-grpo-models/tree/387eb22bcaefd8349123c87d3786997007fd1451/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1a0f8d80b144923a1e0469d5960d80d80cba423c/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-74/step-03073) | [`1a0f8d80b144`](https://huggingface.co/od2961/maxent-grpo-models/tree/1a0f8d80b144923a1e0469d5960d80d80cba423c/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/control/seed-74/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/95c0431ea6fc6024c840e669f38ff02592828607/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-70/step-03073) | [`95c0431ea6fc`](https://huggingface.co/od2961/maxent-grpo-models/tree/95c0431ea6fc6024c840e669f38ff02592828607/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7603c335a8251b1bb5c7d491e3f5e436ca19c4d4/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-71/step-03073) | [`7603c335a825`](https://huggingface.co/od2961/maxent-grpo-models/tree/7603c335a8251b1bb5c7d491e3f5e436ca19c4d4/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/6241cde842c6c5efc3c7ef2c651a939f725a7326/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-72/step-03073) | [`6241cde842c6`](https://huggingface.co/od2961/maxent-grpo-models/tree/6241cde842c6c5efc3c7ef2c651a939f725a7326/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/28842cd104f1b8780f52e84ad6c2e5a949dd1505/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-73/step-03073) | [`28842cd104f1`](https://huggingface.co/od2961/maxent-grpo-models/tree/28842cd104f1b8780f52e84ad6c2e5a949dd1505/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/6f74f72bce13f529a9e26f5c8f2c9e4aefdbca47/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-74/step-03073) | [`6f74f72bce13`](https://huggingface.co/od2961/maxent-grpo-models/tree/6f74f72bce13f529a9e26f5c8f2c9e4aefdbca47/experiments/E80-R1/Qwen2.5-3B-Instruct/graph_coloring/replay/seed-74/step-03073) |

<a id="domain-python_factors"></a>
### Python Factors

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Qwen2.5-3B-Instruct | Dr.GRPO | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a0d9f62233619d68868cae3a6dafa9787903b5d8/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-70/step-03073) | [`a0d9f6223361`](https://huggingface.co/od2961/maxent-grpo-models/tree/a0d9f62233619d68868cae3a6dafa9787903b5d8/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1d2740de449a4c6edb033ab651c8684f67a900e1/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-71/step-03073) | [`1d2740de449a`](https://huggingface.co/od2961/maxent-grpo-models/tree/1d2740de449a4c6edb033ab651c8684f67a900e1/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/12a66418a8593e09f0dccc27f129b4ae8f955567/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-72/step-03073) | [`12a66418a859`](https://huggingface.co/od2961/maxent-grpo-models/tree/12a66418a8593e09f0dccc27f129b4ae8f955567/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/096ba803464c46fd7f42be8d740acb57f8324b55/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-73/step-03073) | [`096ba803464c`](https://huggingface.co/od2961/maxent-grpo-models/tree/096ba803464c46fd7f42be8d740acb57f8324b55/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/fb43500bdc0d9d4e84ffd1a864bc860bfb7149cd/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-74/step-03073) | [`fb43500bdc0d`](https://huggingface.co/od2961/maxent-grpo-models/tree/fb43500bdc0d9d4e84ffd1a864bc860bfb7149cd/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/control/seed-74/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f6c7ef71502bd9e7e4b62c85a976e4d47a69c9a9/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-70/step-03073) | [`f6c7ef71502b`](https://huggingface.co/od2961/maxent-grpo-models/tree/f6c7ef71502bd9e7e4b62c85a976e4d47a69c9a9/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1fc64a9db63918208f1fc9f7eb1bd2d2494365c0/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-71/step-03073) | [`1fc64a9db639`](https://huggingface.co/od2961/maxent-grpo-models/tree/1fc64a9db63918208f1fc9f7eb1bd2d2494365c0/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/35fadf75091dfd3c4f031ab8ffd368b62b6919c8/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-72/step-03073) | [`35fadf75091d`](https://huggingface.co/od2961/maxent-grpo-models/tree/35fadf75091dfd3c4f031ab8ffd368b62b6919c8/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/9a56befa527b9821d720d5b9c54fe1aef4eae4c5/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-73/step-03073) | [`9a56befa527b`](https://huggingface.co/od2961/maxent-grpo-models/tree/9a56befa527b9821d720d5b9c54fe1aef4eae4c5/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/dbb910745ca490a4d00ab7e47ac55f164adb50d3/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-74/step-03073) | [`dbb910745ca4`](https://huggingface.co/od2961/maxent-grpo-models/tree/dbb910745ca490a4d00ab7e47ac55f164adb50d3/experiments/E80-R1/Qwen2.5-3B-Instruct/python_factors/replay/seed-74/step-03073) |

<a id="domain-mathir"></a>
### MathIR

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Qwen2.5-3B-Instruct | Dr.GRPO | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/dc3c7d02c288d6fa985261cd496c77706878cc4b/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-70/step-03073) | [`dc3c7d02c288`](https://huggingface.co/od2961/maxent-grpo-models/tree/dc3c7d02c288d6fa985261cd496c77706878cc4b/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cb3d7b8fe789c7d7a810ea4eeb7da2b9dd826034/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-71/step-03073) | [`cb3d7b8fe789`](https://huggingface.co/od2961/maxent-grpo-models/tree/cb3d7b8fe789c7d7a810ea4eeb7da2b9dd826034/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/4de335e9bc7f3f829bd3f9d9f00e8863d31a186d/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-72/step-03073) | [`4de335e9bc7f`](https://huggingface.co/od2961/maxent-grpo-models/tree/4de335e9bc7f3f829bd3f9d9f00e8863d31a186d/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/4c8d8a7e9819f81a34c9a2a40a541d057f992679/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-73/step-03073) | [`4c8d8a7e9819`](https://huggingface.co/od2961/maxent-grpo-models/tree/4c8d8a7e9819f81a34c9a2a40a541d057f992679/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a56276fecfd4b9f8b26c20a5c8e57d4aea736d54/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-74/step-03073) | [`a56276fecfd4`](https://huggingface.co/od2961/maxent-grpo-models/tree/a56276fecfd4b9f8b26c20a5c8e57d4aea736d54/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/control/seed-74/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/b0c4710901f0d76a81791fe45d439f4e94b77505/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-70/step-03073) | [`b0c4710901f0`](https://huggingface.co/od2961/maxent-grpo-models/tree/b0c4710901f0d76a81791fe45d439f4e94b77505/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/d41694864f27b98f5a5b5baef0b105237780e9b2/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-71/step-03073) | [`d41694864f27`](https://huggingface.co/od2961/maxent-grpo-models/tree/d41694864f27b98f5a5b5baef0b105237780e9b2/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/ffd5386c99f9be83c6365cd91fcc8281f7dcbd12/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-72/step-03073) | [`ffd5386c99f9`](https://huggingface.co/od2961/maxent-grpo-models/tree/ffd5386c99f9be83c6365cd91fcc8281f7dcbd12/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/b9f5411a8e10fb721eb2d7d5861c8561270836c1/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-73/step-03073) | [`b9f5411a8e10`](https://huggingface.co/od2961/maxent-grpo-models/tree/b9f5411a8e10fb721eb2d7d5861c8561270836c1/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/74b0a29b6c84b86fd7f3ee700acf611c82af7f51/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-74/step-03073) | [`74b0a29b6c84`](https://huggingface.co/od2961/maxent-grpo-models/tree/74b0a29b6c84b86fd7f3ee700acf611c82af7f51/experiments/E80-R1/Qwen2.5-3B-Instruct/mathir/replay/seed-74/step-03073) |

<a id="domain-pantry_plan"></a>
### PantryPlan

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Qwen2.5-3B-Instruct | Dr.GRPO | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cef1a35dfdc72911f5bf19fc85cd88c728ef5b5c/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-70/step-03073) | [`cef1a35dfdc7`](https://huggingface.co/od2961/maxent-grpo-models/tree/cef1a35dfdc72911f5bf19fc85cd88c728ef5b5c/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f5895fd199290d6d94c8a130a3cd728566869d91/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-71/step-03073) | [`f5895fd19929`](https://huggingface.co/od2961/maxent-grpo-models/tree/f5895fd199290d6d94c8a130a3cd728566869d91/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/10edb711cea673b6e20eccd6be91c5bbd33d766e/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-72/step-03073) | [`10edb711cea6`](https://huggingface.co/od2961/maxent-grpo-models/tree/10edb711cea673b6e20eccd6be91c5bbd33d766e/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/98b7666194c47baa18c263a60c7f77cb76761dff/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-73/step-03073) | [`98b7666194c4`](https://huggingface.co/od2961/maxent-grpo-models/tree/98b7666194c47baa18c263a60c7f77cb76761dff/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Dr.GRPO | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/e0d3332d2696f114e5e4f7c464f7bdc4f770b835/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-74/step-03073) | [`e0d3332d2696`](https://huggingface.co/od2961/maxent-grpo-models/tree/e0d3332d2696f114e5e4f7c464f7bdc4f770b835/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/control/seed-74/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 70 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/3a56ca8b49345e184f51db3169ec342e31c20a15/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-70/step-03073) | [`3a56ca8b4934`](https://huggingface.co/od2961/maxent-grpo-models/tree/3a56ca8b49345e184f51db3169ec342e31c20a15/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-70/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 71 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/0be5e63f68221c63b7bb7840bb1798153273a637/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-71/step-03073) | [`0be5e63f6822`](https://huggingface.co/od2961/maxent-grpo-models/tree/0be5e63f68221c63b7bb7840bb1798153273a637/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-71/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 72 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7b690d76b9f98384848036a666030cfa4b584fb5/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-72/step-03073) | [`7b690d76b9f9`](https://huggingface.co/od2961/maxent-grpo-models/tree/7b690d76b9f98384848036a666030cfa4b584fb5/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-72/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 73 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/52f9ff9746c0fa5bbf97628ff70b9e63d01b3426/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-73/step-03073) | [`52f9ff9746c0`](https://huggingface.co/od2961/maxent-grpo-models/tree/52f9ff9746c0fa5bbf97628ff70b9e63d01b3426/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-73/step-03073) |
| Qwen2.5-3B-Instruct | Re:Dr | 74 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/32f43120734fd5c754f737ecb8dc47a8245007e4/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-74/step-03073) | [`32f43120734f`](https://huggingface.co/od2961/maxent-grpo-models/tree/32f43120734fd5c754f737ecb8dc47a8245007e4/experiments/E80-R1/Qwen2.5-3B-Instruct/pantry_plan/replay/seed-74/step-03073) |

## Model-family shortcuts

<a id="model-qwen3b"></a>
### Qwen2.5-3B-Instruct

[Browse verified collections](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E80-R1/Qwen2.5-3B-Instruct). Domain tables above provide exact model revisions.

<a id="comparators"></a>
## Comparators and analysis scope

Pair `replay` with `control` within the same base model, domain and seed. Selected replay exports also serve as uniform comparators for [E120-R1](../E120-R1/README.md#comparators); the [E118 factorial](../E118/README.md#comparators) reuses the original Dr.GRPO pairs. This archival link does not change the source experiment or analysis membership.

[Restore and verify a model](../../README.md#restoring) · [Applicable base-model licenses](../../README.md#licenses). The full `commit_sha`, source identity and file provenance are available through the root catalog and each pinned export manifest.