bench2agent 0.3.0__tar.gz

bench2agent-0.3.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

bench2agent-0.3.0/PKG-INFO

@@ -0,0 +1,184 @@
+Metadata-Version: 2.4
+Name: bench2agent
+Version: 0.3.0
+Summary: Ask which benchmarks researchers use, how usage changes, and which new benchmarks are adopted
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/hyunyoungnam/Bench2Agent
+Project-URL: Documentation, https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md
+Project-URL: Issues, https://github.com/hyunyoungnam/Bench2Agent/issues
+Project-URL: Changelog, https://github.com/hyunyoungnam/Bench2Agent/releases
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# Bench2Agent
+
+[![Code release](https://img.shields.io/github/v/release/hyunyoungnam/Bench2Agent?filter=v*&label=release)](https://github.com/hyunyoungnam/Bench2Agent/releases)
+[![PyPI](https://img.shields.io/pypi/v/bench2agent)](https://pypi.org/project/bench2agent/)
+[![Data release](https://img.shields.io/badge/data-2026--10--07-blue)](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/data-20261007)
+[![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md)
+
+Find which benchmarks researchers evaluate on, how their use changes, and
+which new benchmarks other researchers adopt. Ask in a terminal conversation,
+or use Bench2Agent inside Claude Code or Codex.
+
+Answers include usage counts, the papers covered, and original paper evidence.
+**Usage frequency describes adoption, not benchmark quality.**
+
+[Install](#get-started) · [User guide](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md) ·
+[Releases](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/releases.md) · [License](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE)
+
+## Ask a question
+
+Two shortened answers selected after testing four English prompts through MCP
+with the **2026-10-07 data snapshot**. Counts were cross-checked against the
+returned tool results; model wording can vary.
+
+> **You:** What benchmarks are researchers using in robotics lately?
+>
+> **Bench2Agent:** Among 509 analysed papers labelled robotics,
+> [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO) appears in 80
+> evaluation papers ([introducing paper](https://arxiv.org/abs/2306.03310)),
+> [SIMPLER](https://github.com/simpler-env/SimplerEnv) in 41
+> ([introducing paper](https://arxiv.org/abs/2405.05941)), and
+> [Meta-World](https://github.com/Farama-Foundation/Metaworld) in 29. This covers
+> ICLR 2026, ICML 2026, and NeurIPS 2025. Unlabelled papers, including CoRL,
+> are outside this field filter.
+
+> **You:** How has CIFAR-10 usage changed at ICLR from 2024 to 2026?
+>
+> **Bench2Agent:** Its stated evaluation use fell from 94.3 to 64.8 to 38.9
+> per 1,000 analysed papers: 178 of 1,888 in 2024, 197 of 3,038 in 2025,
+> and 165 of 4,237 in 2026. The counts use papers with parsed full text;
+> usage in unparsed papers is unknown.
+
+You can also ask which newly introduced benchmarks other authors use, then
+ask for the evidence behind a result. In the standalone terminal, `/sources`
+shows the original sentences and paper links. Quotes and figures are checked;
+anything the checker cannot verify is marked in the answer.
+
+Answers include repository, dataset or homepage links and reviewed introducing
+papers where available. Locations are our mapping; a repository link does not
+guarantee a direct data download. Missing links mean no confirmed location.
+
+## Get started
+
+### Terminal conversation — macOS / Linux
+
+With Python 3.10+ in your environment, install and start Bench2Agent.
+Choose pip or the uv alternative below:
+
+```bash
+python -m pip install bench2agent
+bench2agent
+```
+
+<details>
+<summary>Alternative: install with uv</summary>
+
+Choose this instead of pip. With [uv installed](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md#install-uv):
+
+```bash
+uv tool install bench2agent
+bench2agent
+```
+
+</details>
+
+`uv tool install` creates a separate environment for the app. `pip` installs
+into your active Python environment; a virtual environment is recommended.
+
+The first launch downloads the **16 MB research-data snapshot** and checks
+its checksum automatically. Later launches reuse your installed data.
+This snapshot contains benchmark usage and paper evidence; external
+benchmarks' underlying questions, labels, and images are separate downloads.
+
+Choose OpenAI or Anthropic at the prompt, accept or change the model, and
+enter your API key when asked. The key is hidden and used only for that
+session. Existing `OPENAI_API_KEY` / `ANTHROPIC_API_KEY` environment variables
+also work. API access uses your provider's API billing, separately from a
+ChatGPT or Claude subscription.
+
+Once installed, just run `bench2agent` to return. No GPU is needed.
+[Windows setup, saved conversations, and data updates](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md).
+
+### Use your existing Claude Code or Codex login
+
+Bench2Agent can supply the same data to your AI client's conversation through
+MCP. The client handles model access through its own login. Bench2Agent's MCP
+server needs no separate API key.
+
+After installing Bench2Agent, open a conversation in your preferred client.
+Claude Code or Codex must already be installed and signed in:
+
+| Command | Model access |
+|---|---|
+| `bench2agent` | OpenAI or Anthropic API key, with separate API billing |
+| `bench2agent claude` | Your existing Claude Code login |
+| `bench2agent codex` | Your existing Codex login |
+
+These commands download the data if needed and open a new session with
+Bench2Agent tools available. Ask the client to **use Bench2Agent** for your
+benchmark question.
+For a fresh installation using this route, follow the
+[complete MCP setup](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md#install-for-claude-code-or-codex).
+Your client writes its answers; Bench2Agent's final-answer checks run in the
+standalone terminal interface.
+
+## Web service direction
+
+`bench2agent serve` starts the existing local browser interface. A hosted
+conversation service is planned around the same benchmark tools, with a
+relational database, per-user conversations and a separate collection worker.
+See the [database and hosting design](docs/database-and-hosting.md) for the
+terminal, web and future Mac server architecture.
+
+## Data coverage
+
+The current snapshot covers **28 editions of 10 conferences**, with
+**58,616 parsed paper-edition observations** and **9,332 benchmark and dataset
+entries**. Of those entries, 8,768 have reviewed introduction claims inside
+this corpus ([review rubric](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/introduced-review.md)).
+
+| Venue | Editions | Venue | Editions |
+|---|---|---|---|
+| ICML | 2024 · 2025 · 2026 | ICCV | 2023 · 2025 |
+| ICLR | 2024 · 2025 · 2026 | ECCV | 2024 · 2026 |
+| NeurIPS | 2023 · 2024 · 2025 | ACL | 2024 · 2025 · 2026 |
+| CVPR | 2024 · 2025 · 2026 | EMNLP | 2023 · 2024 · 2025 |
+| AAAI | 2024 · 2025 · 2026 | CoRL | 2023 · 2024 · 2025 |
+
+Counts come from explicitly stated evaluation or training use in parsed arXiv
+HTML. Each answer reports its scope and denominator. Missing full text or an
+unstated role does not establish that a benchmark was unused. Field filters
+cover papers with matching labels and can exclude unlabelled venues.
+
+“New” means a reviewed introduction claim inside this corpus, which starts
+in 2023; it does not establish the first public release. Earlier observed use,
+self-use, use by other authors, and uncertain attribution are recorded
+separately. Recent introductions have less time to accumulate adoption.
+
+Bench2Agent is a research prototype. Released snapshots have fixed identities,
+and conversations record the snapshot used for their answers.
+[Data rules and tool details](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/benchmark-chat.md).
+
+## Releases and development
+
+Code and data are distributed separately. Bench2Agent 0.3.0 is available on
+[PyPI](https://pypi.org/project/bench2agent/0.3.0/) and as a
+[GitHub release](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/v0.3.0).
+Earlier code tags retain the installation artifacts published before the
+rename. The [data-20261007 release](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/data-20261007)
+is the current research snapshot. Update code with `uv tool upgrade bench2agent`
+or `python -m pip install --upgrade bench2agent`; data updates use
+`bench2agent data install`. Existing users can follow the
+[migration guide](docs/terminal.md#switch-from-an-earlier-installation). See
+[how releases work](docs/releases.md).
+
+The earlier paper-reading interface remains available as an evidence surface:
+[browser guide](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/browser.md). Start it with `bench2agent serve`.
+Paper-view principles are in [docs/paper-view.md](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/paper-view.md).
+
+Bench2Agent's code is licensed under [Apache-2.0](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE).

bench2agent-0.3.0/README.md

@@ -0,0 +1,170 @@
+# Bench2Agent
+
+[![Code release](https://img.shields.io/github/v/release/hyunyoungnam/Bench2Agent?filter=v*&label=release)](https://github.com/hyunyoungnam/Bench2Agent/releases)
+[![PyPI](https://img.shields.io/pypi/v/bench2agent)](https://pypi.org/project/bench2agent/)
+[![Data release](https://img.shields.io/badge/data-2026--10--07-blue)](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/data-20261007)
+[![License: Apache-2.0](https://img.shields.io/badge/license-Apache--2.0-blue)](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10%2B-blue)](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md)
+
+Find which benchmarks researchers evaluate on, how their use changes, and
+which new benchmarks other researchers adopt. Ask in a terminal conversation,
+or use Bench2Agent inside Claude Code or Codex.
+
+Answers include usage counts, the papers covered, and original paper evidence.
+**Usage frequency describes adoption, not benchmark quality.**
+
+[Install](#get-started) · [User guide](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md) ·
+[Releases](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/releases.md) · [License](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE)
+
+## Ask a question
+
+Two shortened answers selected after testing four English prompts through MCP
+with the **2026-10-07 data snapshot**. Counts were cross-checked against the
+returned tool results; model wording can vary.
+
+> **You:** What benchmarks are researchers using in robotics lately?
+>
+> **Bench2Agent:** Among 509 analysed papers labelled robotics,
+> [LIBERO](https://github.com/Lifelong-Robot-Learning/LIBERO) appears in 80
+> evaluation papers ([introducing paper](https://arxiv.org/abs/2306.03310)),
+> [SIMPLER](https://github.com/simpler-env/SimplerEnv) in 41
+> ([introducing paper](https://arxiv.org/abs/2405.05941)), and
+> [Meta-World](https://github.com/Farama-Foundation/Metaworld) in 29. This covers
+> ICLR 2026, ICML 2026, and NeurIPS 2025. Unlabelled papers, including CoRL,
+> are outside this field filter.
+
+> **You:** How has CIFAR-10 usage changed at ICLR from 2024 to 2026?
+>
+> **Bench2Agent:** Its stated evaluation use fell from 94.3 to 64.8 to 38.9
+> per 1,000 analysed papers: 178 of 1,888 in 2024, 197 of 3,038 in 2025,
+> and 165 of 4,237 in 2026. The counts use papers with parsed full text;
+> usage in unparsed papers is unknown.
+
+You can also ask which newly introduced benchmarks other authors use, then
+ask for the evidence behind a result. In the standalone terminal, `/sources`
+shows the original sentences and paper links. Quotes and figures are checked;
+anything the checker cannot verify is marked in the answer.
+
+Answers include repository, dataset or homepage links and reviewed introducing
+papers where available. Locations are our mapping; a repository link does not
+guarantee a direct data download. Missing links mean no confirmed location.
+
+## Get started
+
+### Terminal conversation — macOS / Linux
+
+With Python 3.10+ in your environment, install and start Bench2Agent.
+Choose pip or the uv alternative below:
+
+```bash
+python -m pip install bench2agent
+bench2agent
+```
+
+<details>
+<summary>Alternative: install with uv</summary>
+
+Choose this instead of pip. With [uv installed](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md#install-uv):
+
+```bash
+uv tool install bench2agent
+bench2agent
+```
+
+</details>
+
+`uv tool install` creates a separate environment for the app. `pip` installs
+into your active Python environment; a virtual environment is recommended.
+
+The first launch downloads the **16 MB research-data snapshot** and checks
+its checksum automatically. Later launches reuse your installed data.
+This snapshot contains benchmark usage and paper evidence; external
+benchmarks' underlying questions, labels, and images are separate downloads.
+
+Choose OpenAI or Anthropic at the prompt, accept or change the model, and
+enter your API key when asked. The key is hidden and used only for that
+session. Existing `OPENAI_API_KEY` / `ANTHROPIC_API_KEY` environment variables
+also work. API access uses your provider's API billing, separately from a
+ChatGPT or Claude subscription.
+
+Once installed, just run `bench2agent` to return. No GPU is needed.
+[Windows setup, saved conversations, and data updates](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md).
+
+### Use your existing Claude Code or Codex login
+
+Bench2Agent can supply the same data to your AI client's conversation through
+MCP. The client handles model access through its own login. Bench2Agent's MCP
+server needs no separate API key.
+
+After installing Bench2Agent, open a conversation in your preferred client.
+Claude Code or Codex must already be installed and signed in:
+
+| Command | Model access |
+|---|---|
+| `bench2agent` | OpenAI or Anthropic API key, with separate API billing |
+| `bench2agent claude` | Your existing Claude Code login |
+| `bench2agent codex` | Your existing Codex login |
+
+These commands download the data if needed and open a new session with
+Bench2Agent tools available. Ask the client to **use Bench2Agent** for your
+benchmark question.
+For a fresh installation using this route, follow the
+[complete MCP setup](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md#install-for-claude-code-or-codex).
+Your client writes its answers; Bench2Agent's final-answer checks run in the
+standalone terminal interface.
+
+## Web service direction
+
+`bench2agent serve` starts the existing local browser interface. A hosted
+conversation service is planned around the same benchmark tools, with a
+relational database, per-user conversations and a separate collection worker.
+See the [database and hosting design](docs/database-and-hosting.md) for the
+terminal, web and future Mac server architecture.
+
+## Data coverage
+
+The current snapshot covers **28 editions of 10 conferences**, with
+**58,616 parsed paper-edition observations** and **9,332 benchmark and dataset
+entries**. Of those entries, 8,768 have reviewed introduction claims inside
+this corpus ([review rubric](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/introduced-review.md)).
+
+| Venue | Editions | Venue | Editions |
+|---|---|---|---|
+| ICML | 2024 · 2025 · 2026 | ICCV | 2023 · 2025 |
+| ICLR | 2024 · 2025 · 2026 | ECCV | 2024 · 2026 |
+| NeurIPS | 2023 · 2024 · 2025 | ACL | 2024 · 2025 · 2026 |
+| CVPR | 2024 · 2025 · 2026 | EMNLP | 2023 · 2024 · 2025 |
+| AAAI | 2024 · 2025 · 2026 | CoRL | 2023 · 2024 · 2025 |
+
+Counts come from explicitly stated evaluation or training use in parsed arXiv
+HTML. Each answer reports its scope and denominator. Missing full text or an
+unstated role does not establish that a benchmark was unused. Field filters
+cover papers with matching labels and can exclude unlabelled venues.
+
+“New” means a reviewed introduction claim inside this corpus, which starts
+in 2023; it does not establish the first public release. Earlier observed use,
+self-use, use by other authors, and uncertain attribution are recorded
+separately. Recent introductions have less time to accumulate adoption.
+
+Bench2Agent is a research prototype. Released snapshots have fixed identities,
+and conversations record the snapshot used for their answers.
+[Data rules and tool details](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/benchmark-chat.md).
+
+## Releases and development
+
+Code and data are distributed separately. Bench2Agent 0.3.0 is available on
+[PyPI](https://pypi.org/project/bench2agent/0.3.0/) and as a
+[GitHub release](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/v0.3.0).
+Earlier code tags retain the installation artifacts published before the
+rename. The [data-20261007 release](https://github.com/hyunyoungnam/Bench2Agent/releases/tag/data-20261007)
+is the current research snapshot. Update code with `uv tool upgrade bench2agent`
+or `python -m pip install --upgrade bench2agent`; data updates use
+`bench2agent data install`. Existing users can follow the
+[migration guide](docs/terminal.md#switch-from-an-earlier-installation). See
+[how releases work](docs/releases.md).
+
+The earlier paper-reading interface remains available as an evidence surface:
+[browser guide](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/browser.md). Start it with `bench2agent serve`.
+Paper-view principles are in [docs/paper-view.md](https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/paper-view.md).
+
+Bench2Agent's code is licensed under [Apache-2.0](https://github.com/hyunyoungnam/Bench2Agent/blob/main/LICENSE).

bench2agent-0.3.0/pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "bench2agent"
+version = "0.3.0"
+description = "Ask which benchmarks researchers use, how usage changes, and which new benchmarks are adopted"
+readme = "README.md"
+requires-python = ">=3.10"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+# The SERVING layer is stdlib-only by design — it must run on machines that
+# cannot run the build pipeline (Windows, no GPU). Pipeline deps live in .venv.
+dependencies = []
+
+[project.urls]
+Repository = "https://github.com/hyunyoungnam/Bench2Agent"
+Documentation = "https://github.com/hyunyoungnam/Bench2Agent/blob/main/docs/terminal.md"
+Issues = "https://github.com/hyunyoungnam/Bench2Agent/issues"
+Changelog = "https://github.com/hyunyoungnam/Bench2Agent/releases"
+
+[project.scripts]
+bench2agent = "bench2agent.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["bench2agent*"]

bench2agent-0.3.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

bench2agent-0.3.0/src/bench2agent/__init__.py

@@ -0,0 +1,3 @@
+"""Bench2Agent: conversational benchmark usage and adoption research."""
+
+__version__ = "0.3.0"

bench2agent-0.3.0/src/bench2agent/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+raise SystemExit(main())