# E112-R1 · Verified-support semantic + proposal bundle

Which aspect of the update changes correctness and retained verified support?

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

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

Three registered model scales × five domains × five seeds. The reported two-scale contrast uses its exact common admitted intersection.

Reported exploratory bundled comparison. Semantic regularization and proposal sampling are introduced together; their individual effects are not isolated.

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 |
| ---: | ---: | ---: | ---: |
| 75 | 49 | 49 | 49 |

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) | 25 / 25 | 43, 44, 45, 46, 47 |
| [Falcon3-1B-Instruct](#model-falcon1b) | 24 / 24 | 55, 56, 57, 58, 59 |

## Methods and collections

<a id="method-verified_support_discovery"></a>
### Verified-support semantic + proposal bundle · `verified_support_discovery`

Re:Dr augmented with semantic regularization and an isolated verified proposal sampler; a bundled comparison.

- [Falcon3-1B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery) — 4 verified exports. Exact immutable revisions are in the model tables below.
- [Falcon3-1B-Instruct · Graph Coloring](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery) — 5 verified exports. Exact immutable revisions are in the model tables below.
- [Falcon3-1B-Instruct · MathIR](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery) — 5 verified exports. Exact immutable revisions are in the model tables below.
- [Falcon3-1B-Instruct · PantryPlan](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery) — 5 verified exports. Exact immutable revisions are in the model tables below.
- [Falcon3-1B-Instruct · Python Factors](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery) — 5 verified exports. Exact immutable revisions are in the model tables below.
- [Qwen2.5-0.5B-Instruct · Countdown](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery) — 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/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery) — 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/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery) — 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/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery) — 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/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery) — 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

**9 / 9** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 55 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/84e784c10b904062a75bdfd9c854b96a6a79df4d/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-55/step-03073) | [`84e784c10b90`](https://huggingface.co/od2961/maxent-grpo-models/tree/84e784c10b904062a75bdfd9c854b96a6a79df4d/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-55/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 56 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/240d248dbbb6cfa8b5dbd989de77e9f9b71b63a3/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-56/step-03073) | [`240d248dbbb6`](https://huggingface.co/od2961/maxent-grpo-models/tree/240d248dbbb6cfa8b5dbd989de77e9f9b71b63a3/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-56/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 57 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/60c7d9f383912e1969f5ecf5a38e15e998fe71a2/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-57/step-03073) | [`60c7d9f38391`](https://huggingface.co/od2961/maxent-grpo-models/tree/60c7d9f383912e1969f5ecf5a38e15e998fe71a2/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-57/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 58 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/27c3efc0ab3bf56284c60fd3965edf5c0a3e23a9/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-58/step-03073) | [`27c3efc0ab3b`](https://huggingface.co/od2961/maxent-grpo-models/tree/27c3efc0ab3bf56284c60fd3965edf5c0a3e23a9/experiments/E112-R1/Falcon3-1B-Instruct/countdown/verified_support_discovery/seed-58/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7871570da6a649ef8fb70d54e9a59941a82a0ebe/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-43/step-03073) | [`7871570da6a6`](https://huggingface.co/od2961/maxent-grpo-models/tree/7871570da6a649ef8fb70d54e9a59941a82a0ebe/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-43/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/e5904aaac84c2b559907d2bee3d3ec178528020c/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-44/step-03073) | [`e5904aaac84c`](https://huggingface.co/od2961/maxent-grpo-models/tree/e5904aaac84c2b559907d2bee3d3ec178528020c/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-44/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a44155c71dbf7c59cfe1e067436a64f576b8224e/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-45/step-03073) | [`a44155c71dbf`](https://huggingface.co/od2961/maxent-grpo-models/tree/a44155c71dbf7c59cfe1e067436a64f576b8224e/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-45/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/2fcef4be8b6aaa0e6f9a869f69f2ca859f385c19/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-46/step-03073) | [`2fcef4be8b6a`](https://huggingface.co/od2961/maxent-grpo-models/tree/2fcef4be8b6aaa0e6f9a869f69f2ca859f385c19/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-46/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/529e54efcea6f2d8893944ee2dba12436bb3e540/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-47/step-03073) | [`529e54efcea6`](https://huggingface.co/od2961/maxent-grpo-models/tree/529e54efcea6f2d8893944ee2dba12436bb3e540/experiments/E112-R1/Qwen2.5-0.5B-Instruct/countdown/verified_support_discovery/seed-47/step-03073) |

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

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 55 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/049be19138fb25ceb3f2178ad89c48937f333353/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-55/step-03073) | [`049be19138fb`](https://huggingface.co/od2961/maxent-grpo-models/tree/049be19138fb25ceb3f2178ad89c48937f333353/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-55/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 56 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/15e2f9cc9b4822cf6120dcd61500e7bb7a634a89/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-56/step-03073) | [`15e2f9cc9b48`](https://huggingface.co/od2961/maxent-grpo-models/tree/15e2f9cc9b4822cf6120dcd61500e7bb7a634a89/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-56/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 57 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/48c020abbe0da67f0f67aff9fc173aec361d85e3/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-57/step-03073) | [`48c020abbe0d`](https://huggingface.co/od2961/maxent-grpo-models/tree/48c020abbe0da67f0f67aff9fc173aec361d85e3/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-57/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 58 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/061deb59f11385625e6dcbba1c018b7964eed0d5/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-58/step-03073) | [`061deb59f113`](https://huggingface.co/od2961/maxent-grpo-models/tree/061deb59f11385625e6dcbba1c018b7964eed0d5/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-58/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 59 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/3faadf3ae614025174296e4dba06a29a7bec98ac/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-59/step-03073) | [`3faadf3ae614`](https://huggingface.co/od2961/maxent-grpo-models/tree/3faadf3ae614025174296e4dba06a29a7bec98ac/experiments/E112-R1/Falcon3-1B-Instruct/graph_coloring/verified_support_discovery/seed-59/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/930a989829844ff4907e4754e752bce98cae04d2/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-43/step-03073) | [`930a98982984`](https://huggingface.co/od2961/maxent-grpo-models/tree/930a989829844ff4907e4754e752bce98cae04d2/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-43/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7a4725edd91c4505328ecd171866fa9543933407/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-44/step-03073) | [`7a4725edd91c`](https://huggingface.co/od2961/maxent-grpo-models/tree/7a4725edd91c4505328ecd171866fa9543933407/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-44/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/96b29c6269a776bfb45869d9385f649e4199b855/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-45/step-03073) | [`96b29c6269a7`](https://huggingface.co/od2961/maxent-grpo-models/tree/96b29c6269a776bfb45869d9385f649e4199b855/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-45/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/d8d5bf42e0271fde53cde539383e1ea7f360435f/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-46/step-03073) | [`d8d5bf42e027`](https://huggingface.co/od2961/maxent-grpo-models/tree/d8d5bf42e0271fde53cde539383e1ea7f360435f/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-46/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/152c1903edd160f8f635958fefc77f4341032a44/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-47/step-03073) | [`152c1903edd1`](https://huggingface.co/od2961/maxent-grpo-models/tree/152c1903edd160f8f635958fefc77f4341032a44/experiments/E112-R1/Qwen2.5-0.5B-Instruct/graph_coloring/verified_support_discovery/seed-47/step-03073) |

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

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 55 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/7dd03c31b19e19bbccfa9aa81586f538ff692ce5/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-55/step-03073) | [`7dd03c31b19e`](https://huggingface.co/od2961/maxent-grpo-models/tree/7dd03c31b19e19bbccfa9aa81586f538ff692ce5/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-55/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 56 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/8b80bff4895b91955c91f440433f52a95997966d/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-56/step-03073) | [`8b80bff4895b`](https://huggingface.co/od2961/maxent-grpo-models/tree/8b80bff4895b91955c91f440433f52a95997966d/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-56/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 57 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/491cf084572d6d9304ce4b2ae149d7f7fb98ef49/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-57/step-03073) | [`491cf084572d`](https://huggingface.co/od2961/maxent-grpo-models/tree/491cf084572d6d9304ce4b2ae149d7f7fb98ef49/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-57/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 58 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a821a38ac2b297bbffdff8d17f2c02386e32f326/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-58/step-03073) | [`a821a38ac2b2`](https://huggingface.co/od2961/maxent-grpo-models/tree/a821a38ac2b297bbffdff8d17f2c02386e32f326/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-58/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 59 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/beaa8a21e420f1d0d6a479107083cbf0a6bf2916/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-59/step-03073) | [`beaa8a21e420`](https://huggingface.co/od2961/maxent-grpo-models/tree/beaa8a21e420f1d0d6a479107083cbf0a6bf2916/experiments/E112-R1/Falcon3-1B-Instruct/python_factors/verified_support_discovery/seed-59/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/8c0ac34a17a392ef0fa4f83c0f46a1de44249bbb/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-43/step-03073) | [`8c0ac34a17a3`](https://huggingface.co/od2961/maxent-grpo-models/tree/8c0ac34a17a392ef0fa4f83c0f46a1de44249bbb/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-43/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/8d0715ce9d1df6b0e8e618ef7ea7cdd4d4be2ee4/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-44/step-03073) | [`8d0715ce9d1d`](https://huggingface.co/od2961/maxent-grpo-models/tree/8d0715ce9d1df6b0e8e618ef7ea7cdd4d4be2ee4/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-44/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/67732dbeabb7800b9d243dbb2d0c5401d77f08b3/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-45/step-03073) | [`67732dbeabb7`](https://huggingface.co/od2961/maxent-grpo-models/tree/67732dbeabb7800b9d243dbb2d0c5401d77f08b3/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-45/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/2a1ec42e30d5e871b2a7f2dbc71290d81ab51065/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-46/step-03073) | [`2a1ec42e30d5`](https://huggingface.co/od2961/maxent-grpo-models/tree/2a1ec42e30d5e871b2a7f2dbc71290d81ab51065/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-46/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a8b38110432928ed053e12a387966d5504ff2037/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-47/step-03073) | [`a8b381104329`](https://huggingface.co/od2961/maxent-grpo-models/tree/a8b38110432928ed053e12a387966d5504ff2037/experiments/E112-R1/Qwen2.5-0.5B-Instruct/python_factors/verified_support_discovery/seed-47/step-03073) |

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

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 55 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/40c31345130c4edfb7dc48a9af7d0db310a75127/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-55/step-03073) | [`40c31345130c`](https://huggingface.co/od2961/maxent-grpo-models/tree/40c31345130c4edfb7dc48a9af7d0db310a75127/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-55/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 56 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/605b36c51fcc5f8e4181b589040a6000144b5c81/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-56/step-03073) | [`605b36c51fcc`](https://huggingface.co/od2961/maxent-grpo-models/tree/605b36c51fcc5f8e4181b589040a6000144b5c81/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-56/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 57 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/761a7591bfa62f7a636dc33795c8604a595fa356/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-57/step-03073) | [`761a7591bfa6`](https://huggingface.co/od2961/maxent-grpo-models/tree/761a7591bfa62f7a636dc33795c8604a595fa356/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-57/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 58 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/28ed4e5411bd66d607ff06058d312eb093d53cc0/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-58/step-03073) | [`28ed4e5411bd`](https://huggingface.co/od2961/maxent-grpo-models/tree/28ed4e5411bd66d607ff06058d312eb093d53cc0/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-58/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 59 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/5f83fb64df589754ef1f6b25605104eeec8521b7/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-59/step-03073) | [`5f83fb64df58`](https://huggingface.co/od2961/maxent-grpo-models/tree/5f83fb64df589754ef1f6b25605104eeec8521b7/experiments/E112-R1/Falcon3-1B-Instruct/mathir/verified_support_discovery/seed-59/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f68546ae3373fd1025b849e66c571acac63d3740/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-43/step-03073) | [`f68546ae3373`](https://huggingface.co/od2961/maxent-grpo-models/tree/f68546ae3373fd1025b849e66c571acac63d3740/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-43/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cba9a9d966c59d5ce1ded1066e8957407f2debba/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-44/step-03073) | [`cba9a9d966c5`](https://huggingface.co/od2961/maxent-grpo-models/tree/cba9a9d966c59d5ce1ded1066e8957407f2debba/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-44/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/cd9eeae075da0f21a324cf4b4039322a12d413a1/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-45/step-03073) | [`cd9eeae075da`](https://huggingface.co/od2961/maxent-grpo-models/tree/cd9eeae075da0f21a324cf4b4039322a12d413a1/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-45/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/5158c7869ff05cba262cad580aee96a4ba367c58/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-46/step-03073) | [`5158c7869ff0`](https://huggingface.co/od2961/maxent-grpo-models/tree/5158c7869ff05cba262cad580aee96a4ba367c58/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-46/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/39feaa03d5e60d1135b20b9ccd595edb6001f466/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-47/step-03073) | [`39feaa03d5e6`](https://huggingface.co/od2961/maxent-grpo-models/tree/39feaa03d5e60d1135b20b9ccd595edb6001f466/experiments/E112-R1/Qwen2.5-0.5B-Instruct/mathir/verified_support_discovery/seed-47/step-03073) |

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

**10 / 10** selected exports verified.

| Model | Method | Seed | Terminal export | Immutable revision |
| --- | --- | ---: | --- | --- |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 55 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/42b58741288b07f03061de8a0a6c2f310ca4d133/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-55/step-03073) | [`42b58741288b`](https://huggingface.co/od2961/maxent-grpo-models/tree/42b58741288b07f03061de8a0a6c2f310ca4d133/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-55/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 56 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/4946e1411850a03111fc76fd70240a55dace7fce/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-56/step-03073) | [`4946e1411850`](https://huggingface.co/od2961/maxent-grpo-models/tree/4946e1411850a03111fc76fd70240a55dace7fce/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-56/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 57 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/f44bf8dafb241226cc5c18d164491440977c60fd/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-57/step-03073) | [`f44bf8dafb24`](https://huggingface.co/od2961/maxent-grpo-models/tree/f44bf8dafb241226cc5c18d164491440977c60fd/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-57/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 58 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/ea860268eee43c4e0316ca3d4a1ff4c43ff4d15f/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-58/step-03073) | [`ea860268eee4`](https://huggingface.co/od2961/maxent-grpo-models/tree/ea860268eee43c4e0316ca3d4a1ff4c43ff4d15f/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-58/step-03073) |
| Falcon3-1B-Instruct | Verified-support semantic + proposal bundle | 59 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/c791863b330933adb0df05cb4cad50f7501a296f/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-59/step-03073) | [`c791863b3309`](https://huggingface.co/od2961/maxent-grpo-models/tree/c791863b330933adb0df05cb4cad50f7501a296f/experiments/E112-R1/Falcon3-1B-Instruct/pantry_plan/verified_support_discovery/seed-59/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 43 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a3f6bb76b2c77f4a0225f71de70f5589bd2ef669/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-43/step-03073) | [`a3f6bb76b2c7`](https://huggingface.co/od2961/maxent-grpo-models/tree/a3f6bb76b2c77f4a0225f71de70f5589bd2ef669/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-43/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 44 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/1f397ec84a34d3ca83cbbb0b5521b9f6030dd041/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-44/step-03073) | [`1f397ec84a34`](https://huggingface.co/od2961/maxent-grpo-models/tree/1f397ec84a34d3ca83cbbb0b5521b9f6030dd041/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-44/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 45 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/bb0e1a465f65e3f5fbc164c318a4103fccf329af/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-45/step-03073) | [`bb0e1a465f65`](https://huggingface.co/od2961/maxent-grpo-models/tree/bb0e1a465f65e3f5fbc164c318a4103fccf329af/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-45/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 46 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/a894509fbb98943d2fc2cc7c754b5c15ebd91ffc/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-46/step-03073) | [`a894509fbb98`](https://huggingface.co/od2961/maxent-grpo-models/tree/a894509fbb98943d2fc2cc7c754b5c15ebd91ffc/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-46/step-03073) |
| Qwen2.5-0.5B-Instruct | Verified-support semantic + proposal bundle | 47 | [step 3073](https://huggingface.co/od2961/maxent-grpo-models/tree/ba0edf50c15a5e6f53a25942481334c67767b293/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-47/step-03073) | [`ba0edf50c15a`](https://huggingface.co/od2961/maxent-grpo-models/tree/ba0edf50c15a5e6f53a25942481334c67767b293/experiments/E112-R1/Qwen2.5-0.5B-Instruct/pantry_plan/verified_support_discovery/seed-47/step-03073) |

## Model-family shortcuts

<a id="model-qwen05b"></a>
### Qwen2.5-0.5B-Instruct

[Browse verified collections](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Qwen2.5-0.5B-Instruct). Domain tables above provide exact model revisions.

<a id="model-falcon1b"></a>
### Falcon3-1B-Instruct

[Browse verified collections](https://huggingface.co/od2961/maxent-grpo-models/tree/main/experiments/E112-R1/Falcon3-1B-Instruct). Domain tables above provide exact model revisions.

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

Use original replay comparators, with E109 repaired Python sources where required. Adaptive controllers and open-bank development branches are excluded from this reported treatment, not from every historical artifact in the broader project.

[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.