@citeark/agent 0.3.20

package/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.

package/README.md

@@ -0,0 +1,128 @@
+# CiteArk Agent
+
+CiteArk Agent 是可独立使用的科研复现程序。它读取论文与代码，结合用户目标和可用算力规划实验，执行、收集证据、评估，再生成签名的 [CAP 科研快照](protocol/CAP.md)。本地使用不需要 CiteArk 账号；[CiteArk 网站](https://citeark.co)提供论文检索、托管运行、成果存储和展示。
+
+项目处于 alpha 阶段。签名确认产物内容与签名者，科学结论由带证据的评估记录表达。
+
+## 安装
+
+正式 npm 包名为 `@citeark/agent`。首次发布完成后，安装或升级使用：
+
+```bash
+npm install -g @citeark/agent
+citeark
+```
+
+当前版本正在准备首次 npm 发布；发布状态与维护步骤见 [npm 发布](docs/npm-release.md)。发布前可在本仓库执行 `npm run package:local`，再用 `npm install -g ./dist/cli.tgz` 安装。网站的当前安装地址为 `npm install -g https://citeark.co/cli.tgz`。安装一次后，使用 `citeark` 开始新研究或输入已有工作区路径继续研究。PowerShell 若阻止脚本，可用 `npm.cmd` 和 `citeark.cmd`。
+
+## 开始研究
+
+PDF 首次使用前运行 `citeark paper setup --python python3.12`，安装本机 CPU 解析环境并下载模型；也可用 `citeark paper parse --input paper.pdf --output ./paper-reading` 单独解析。无需 MinerU 官方密钥或 CiteArk 云资源，后续离线复用模型与摘要缓存。配置及平台集成边界见[论文阅读](docs/paper-reading.md)。
+
+需要 Node.js 22 或更新版本、Git、tar。使用本机算力时还需要 Docker；远程执行支持通用 SSH 服务器，以及通过算力目录配置的 GCP Batch 和 AutoDL。用户的服务器和 CiteArk 自有服务器使用同一套 Agent。
+
+```bash
+# 从网站论文资料开始，也适用于尚无复现结果的论文
+citeark start <论文短编号>
+
+# 完全独立地读取本地论文、代码和可选的路径说明
+citeark start --paper ./paper.pdf --repository ./code \
+  --goal '检验不同批大小下的推理性能' --guide ./REPRODUCE.md
+
+# CAP 提供来源理解、历史证据和参考代码；重新规划本次研究
+citeark start --cap ./previous.cap --paper ./paper.pdf
+```
+
+直接运行 `citeark` 会先询问论文、CAP、平台短编号或已有工作区。随后依次询问研究目标、算力目录和首次模型配置；后续复用已保存的非敏感设置。论文理解形成研究清单，规划阶段提出实验；你选择本次要运行的实验后才开始执行。`--plan-only` 停在计划阶段，`--experiments id1,id2` 明确选择实验，`--resume --work-dir <目录>` 恢复同一次研究。变更目标或资料时建立新工作区。
+
+`--compute-catalog ./compute.json` 指定自己的远程或本地资源；`--compute-policy ./policy.json` 约束可用执行器、费用和资源规格。模型密钥使用 `--api-key-env MODEL_API_KEY`，不写入工作区配置。科学评估与来源审查支持所选运行器对应的 Chat Completions、Responses 或 Messages 接口；API 评估暂不可用时保留证据与无法判断状态。托管订阅配置的所有科研模型阶段统一使用所选 Codex 账号与模型；订阅故障停止并保留现场，不切换为 API。
+
+CAP、执行说明和路径提示都是参考输入。它们不会自动确定本次实验、替代实际观测或跳过规划。确需按旧交付直接复跑时，使用显式的 `deploy <论文短编号> --replay`。
+
+## 终端会话
+
+交互界面使用英文。顶部显示与网站一致的五阶段；正文连续呈现 Agent 的正常发言、工具调用、命令与结果。鼠标滚轮或 PgUp/PgDn 翻阅历史，End 回到实时输出，Ctrl+O 展开完整工具结果。模型设置会复用，不在每次研究时重复询问。完整控件、输出接入与运行边界见 [Terminal workspace](docs/terminal.md)。
+
+工作区保留 `session.events.jsonl`。`citeark view <目录>` 只读浏览会话，`--plain` 使用普通文本输出。运行中 Ctrl+C 退出界面并保存收到的记录，不取消算力任务；工作进程继续运行，用 `citeark session attach <目录>` 重新连接。暂停、取消和资源清理结果由会话管理命令提供。
+
+## 模型、远程服务器与后台会话
+
+使用 `citeark model add` 保存模型及密钥环境变量名，`citeark compute add` 保存本机、SSH 服务器或算力目录。交互入口的 `/model`、`/compute` 切换默认配置。每项研究保存所用模型和算力目录快照，后续修改默认配置不会改变已有研究。
+
+完整配置命令、服务器部署、后台控制及恢复限制见 [配置与服务器指南](docs/configuration.md)。通用 SSH 使用服务器自己的模型配置；CiteArk 托管平台使用同一个科研引擎，账号、队列和计费仍属于网站。
+
+## 工作区与成果
+
+`workspace.json` 保存当前阶段、来源、算力配置位置和选择；论文理解与规划位于 `planning/`，执行、计划修订、原始证据与检查点位于 `execution/`。执行过程中继续允许依据来源和证据修订方法。已生成的 CAP 保持不可变，新计划与结果生成新的产物并关联来源。
+
+完成后终端列出所有 CAP 路径。签名使用本机的 Ed25519 私钥，默认位于 `~/.citeark/signing-key.pem`。可用 `--signing-key` 指定自己的密钥。
+
+上传完全可选，支持独立计划和结果，无需平台已有运行：
+
+```bash
+export CITEARK_API_KEY='<平台写入密钥>'
+citeark publish --plan ./plan.cap --cap ./result.cap
+# 关联论文并明确公开
+citeark publish --plan ./plan.cap --cap ./result.cap \
+  --repository-id '<论文ID>' --visibility public
+```
+
+不指定论文时默认仅上传者可读；`--visibility public` 明确公开。社区成果保留上传者、签名者和自身计划，不覆盖平台评估。接口与发布规则见[集成边界](docs/integration.md)。
+
+## 开发与验证
+
+```bash
+npm ci
+npm run check
+npm test
+npm run package:local
+npm run test:package
+# 无模型、无实验的输入准备检查
+node src/cli.mjs start --paper examples/toy-evaluation/paper.md \
+  --work-dir /tmp/citeark-example --dry-run
+```
+
+`npm link` 后可直接使用 `citeark`。完整选项见 `citeark --help`；低层的 `compile`、`pipeline`、`cap` 和只读 `dashboard` 命令继续可用。
+
+| 路径 | 职责 |
+| --- | --- |
+| `src/workspace/` | 独立研究入口、资料接收、实验选择和恢复 |
+| `src/research/`、`src/pipeline/` | 来源理解、规划和科研流水线 |
+| `src/reproduction/`、`src/compute/` | 自主执行、本机及远程算力 |
+| `src/verification/`、`src/evidence/` | 原始证据解析与独立评估 |
+| `src/cap/v2/`、`protocol/`、`schemas/` | CAP 生成、验证和开放规范 |
+| `src/deployment/` | 显式历史复跑和可选平台上传 |
+| `src/public/` | 宿主集成接口与轻量 CAP 接口 |
+
+打包生成 `cli.tgz`、手动安装包 `citeark-agent.tgz` 和轻量协议包 `cap.tgz`。网站固定提交与包摘要；GitHub Actions 检查源码、Linux/macOS/Windows 命令行和本机 CPU 环境。网站专用队列、租约、收费策略、页面生成及服务镜像构建在 CiteArk 仓库维护。
+
+## 许可
+
+代码采用 [Apache License 2.0](LICENSE)。CAP 规范、模式和一致性向量采用 [CC0 1.0](protocol/LICENSE)。引用的论文、数据、模型与代码沿用原有许可。npm 安装包按明确文件清单发布；GitHub 仓库可见性单独管理。
+
+## ArkGraph 与 CAP 2
+
+当前协议是 CAP `2.0.0-alpha.2`，使用 Entity、Activity、Assertion、Agent、Relation 五类科研对象；旧 CAP 不再接收。论文可选，关系与端点版本独立验证，签名仍是分离式证明。协议规范及四类合成样例见 [CAP](protocol/CAP.md)。
+
+`citeark graph --cap result.cap --operation subgraph` 可在本地读取科研图；`--query query.json` 支持精确对象、路线、比较和来源追踪。平台查询使用 `--server https://citeark.co`，凭据从 `CITEARK_API_KEY` 读取。多个本地 CAP 用逗号分隔。范围之外的依赖保持未知，不由摘要推断实验独立性。
+
+### 细化研究对象
+
+`researchObjects` 为数据集、具体划分、模型架构、检查点、代码、方法和来源观测集合保留稳定身份及来源。主张表达可以独立支持或质疑的科学命题，不按表格单元格、指标列或曲线点机械拆分。矩阵、表格和曲线族可以是一个观测集合；每条数值仍保留独立测量身份、条件、单位和来源，通过 `observationId` 关联集合。机制解释单列为 `hypotheses`，不能冒充已验证结论，也不自动成为复现目标。
+
+规划按科研方法阶段和结果集合组织：检查点、种子、数据集、模型层等完整参数维度保留在批次规格中，不提前展开为每个组合的步骤或未来产物。计算条目按可复用的完整批次计价；只有不同实验选择确实需要部分共享时，才拆成共享子集和不重叠余集，并完整计入所有成员。执行阶段再记录实际成员、产出和证据。
+
+实验的 `steps` 描述共享的训练、评估等步骤，`inputIds` / `outputIds` 连接对象；未执行的产出只保留待生成规格。步骤只关联显式 `claimIds`，省略时不继承实验包的全部主张；共享准备工作仍保留输入、产出和依赖。论文声明、实际观测和逐项科学判断保持区别。详见 [规划粒度与批次复用](docs/research-plan-granularity.md)和 [CAP 对象与步骤语义](protocol/CAP.md#research-object-granularity-alpha2)。
+
+
+## 规划前的 GCP 资源发现
+
+宿主可以通过 `@citeark/agent/host` 的 `discoverGcpResources` 读取项目可见的全部机型、加速器、区域与全局配额，以及官方标准供应价格。请求只包含列表、读取和 IAM 权限探测，不创建计算资源。快照记录时间、有效期、摘要与各来源状态；分页失败、权限不足或未知显存不会伪装成零值或已验证的资源。平台规格和剩余配额均不保证即时容量。
+
+`gcpDiscoverySummary` 为规划器生成完整机型家族与加速器概览；详细规格保存在原快照。`discoveredGcpPrice` 只合成已明确匹配地区、供应模式、CPU、内存和 GPU 的官方 SKU；缺价或匹配歧义返回未知。宿主在自己的地区、预算与运行时约束内生成可执行目录，并将同一份目录用于规划、调度和费用预留。独立库不管理宿主 IAM 或放宽科研契约。
+
+规划提示要求将 CPU、内存、显存最低需求与依据单独说明，区分来源事实、推导和待探测假设；不能把库存机型的规格直接写成科研最低需求。设备性能测量仍遵守原论文的硬件绑定。
+
+## ArkGraph 预览（开发中）
+
+来源清单可以生成完整科研对象图与阅读主线；实验计划直接绑定图中的来源对象和目标。`npm run build:arkgraph` 构建通用预览，`npm run preview:arkgraph -- plan.cap ./preview paper.pdf` 从真实签名产物生成本地页面。当前仍在真实论文验收阶段，尚未替换网站生产界面；语义、集成状态与验证范围见 [ArkGraph 研究概览](docs/arkgraph-reading.md)。

package/data/dataset-source-registry.v1.json

@@ -0,0 +1,300 @@
+{
+  "schemaVersion": "1.0",
+  "registryId": "citeark-dataset-source-registry-v1",
+  "observedAt": "2026-08-29T01:27:54Z",
+  "purpose": "Candidate download transports and identity checks for scientific datasets whose historical URLs may be unavailable.",
+  "policy": {
+    "candidateOnly": true,
+    "requireRuntimeAcquisitionManifest": true,
+    "requireRuntimeDigestVerification": true,
+    "equivalenceRule": "A catalog entry is a candidate transport, not proof that it is scientifically equivalent to the declared input.",
+    "confidenceLevels": {
+      "primary-content-bridge": "A still-reachable primary archive and the candidate archive have identical extracted scientific members.",
+      "catalog-plus-structural-validation": "The candidate matches a pinned framework catalog entry, archive checksums, schema, split sizes, label sets, and member digests, but no direct primary-content bridge was available.",
+      "primary-catalog-plus-runtime-digest": "The primary resource catalog publishes the archive and checksum. Runtime must repeat the checksum, compute SHA-256, and verify the exact scientific member count and format before use."
+    }
+  },
+  "catalogs": [
+    {
+      "id": "fastai1-datasets",
+      "name": "fastai v1 dataset catalog",
+      "repository": "https://github.com/fastai/fastai1",
+      "commit": "15bc02c61673400178fbdaf3417485755c299561",
+      "path": "fastai/datasets.py",
+      "sourceUrl": "https://raw.githubusercontent.com/fastai/fastai1/15bc02c61673400178fbdaf3417485755c299561/fastai/datasets.py",
+      "checksumSemantics": "The catalog tuple is the archive byte size followed by the MD5 digest of the first MiB."
+    },
+    {
+      "id": "openslr",
+      "name": "Open Speech and Language Resources",
+      "sourceUrl": "https://www.openslr.org/resources.php",
+      "checksumSemantics": "Each resource page publishes complete-archive MD5 checksums. Runtime must also compute SHA-256 and validate the extracted scientific members."
+    }
+  ],
+  "datasets": [
+    {
+      "id": "ag_news",
+      "aliases": ["AG News", "ag_news_csv"],
+      "identity": {
+        "version": "3",
+        "fields": ["class_index", "title", "description"],
+        "labels": ["1", "2", "3", "4"],
+        "splits": {"train": 120000, "test": 7600}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "AG_NEWS",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/ag_news_csv.tgz",
+        "archiveBytes": 11784419,
+        "catalogPrefixMiBMd5": "b86f328f4dbd072486591cb7a5644dcd",
+        "archiveSha256": "9a8c300eabb45750237fcc669f61cb8a3448f3ef6f6098e1ce340e444f6872be",
+        "members": {
+          "train.csv": {"bytes": 29470338, "rows": 120000, "sha256": "76a0a2d2f92b286371fe4d4044640910a04a803fdd2538e0f3f29a5c6f6b672e"},
+          "test.csv": {"bytes": 1857427, "rows": 7600, "sha256": "521465c2428ed7f02f8d6db6ffdd4b5447c1c701962353eb2c40d548c3c85699"}
+        }
+      },
+      "confidence": "primary-content-bridge",
+      "bridgeEvidence": {
+        "primaryUrl": "https://drive.google.com/uc?export=download&id=0Bz8a_Dbh9QhbUDNpeUdjb0wxRms",
+        "primaryArchiveSha256": "4e2fc37d369e6e317a8b62d0d2f11d379f8c3dde60c07c35a46b069a246498ad",
+        "note": "The archives were repacked, but train.csv, test.csv, readme.txt, and classes.txt are byte-identical after extraction.",
+        "memberSha256": {
+          "train.csv": "76a0a2d2f92b286371fe4d4044640910a04a803fdd2538e0f3f29a5c6f6b672e",
+          "test.csv": "521465c2428ed7f02f8d6db6ffdd4b5447c1c701962353eb2c40d548c3c85699",
+          "readme.txt": "779c2e6bbf93dd810d9c7b318006daef7a4bfc34062002461d251dc10fb9f58c",
+          "classes.txt": "612dbfa932f07a6ed837295a7d5746ce7412e7bb4bc32ba919fdb3cda3a1b9b5"
+        }
+      }
+    },
+    {
+      "id": "sogou_news",
+      "aliases": ["Sogou News", "sogou_news_csv"],
+      "identity": {
+        "version": "3",
+        "fields": ["class_index", "title", "content"],
+        "labels": ["1", "2", "3", "4", "5"],
+        "splits": {"train": 450000, "test": 60000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "SOGOU_NEWS",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/sogou_news_csv.tgz",
+        "archiveBytes": 384269937,
+        "catalogPrefixMiBMd5": "950f1366d33be52f5b944f8a8b680902",
+        "archiveSha256": "6b77fc935561d339b82aa552d7e31ea59eff492a494920579b3ce70604efb5c2",
+        "members": {
+          "train.csv": {"bytes": 1256996576, "rows": 450000, "sha256": "19400f8e4578c0dbfb336ed5160aa6b993c49a40462f11b9a69d27b260dca3ce"},
+          "test.csv": {"bytes": 168524375, "rows": 60000, "sha256": "8cb8e6e207928601459b23ac79aa0de4a58d7b2a969b4c2ae3f82dc0e271cf9d"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "dbpedia",
+      "aliases": ["DBPedia", "DBpedia", "dbpedia_csv"],
+      "identity": {
+        "version": "2",
+        "fields": ["class_index", "title", "content"],
+        "labels": ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14"],
+        "splits": {"train": 560000, "test": 70000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "DBPEDIA",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/dbpedia_csv.tgz",
+        "archiveBytes": 68341743,
+        "catalogPrefixMiBMd5": "239c7837b9e79db34486f3de6a00e38e",
+        "archiveSha256": "42db5221ddedddb673a4cabcc5f3a7d869714c878bcfe4ba94b29d14aa38e417",
+        "members": {
+          "train.csv": {"bytes": 174148970, "rows": 560000, "sha256": "3fea0c8c6ae73d0911f9cf37ec68606d169c4edd9214c6443b035649a3fb38ce"},
+          "test.csv": {"bytes": 21775285, "rows": 70000, "sha256": "3d7b5fc00870e3446e322479af553629f55e313dd3b4249c08b68132d1230804"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "yelp_review_polarity",
+      "aliases": ["Yelp Review Polarity", "yelp_review_polarity_csv"],
+      "identity": {
+        "version": "1",
+        "fields": ["class_index", "review_text"],
+        "labels": ["1", "2"],
+        "splits": {"train": 560000, "test": 38000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "YELP_REVIEWS_POLARITY",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/yelp_review_polarity_csv.tgz",
+        "archiveBytes": 166373201,
+        "catalogPrefixMiBMd5": "48c8451c1ad30472334d856b5d294807",
+        "archiveSha256": "528f22e286cad085948acbc3bea7e58188416546b0e364d0ae4ca0ce666abe35",
+        "members": {
+          "train.csv": {"bytes": 410758837, "rows": 560000, "sha256": "d9eec04a8dd4bdbf1e66c02e6faaee580a5c3c37ce14f1b67d48f397dfcc88bc"},
+          "test.csv": {"bytes": 27772097, "rows": 38000, "sha256": "a88e001a30bfa4c996cab473e9c9afd0fcfb01e94bef3c52002a167c2bff0b51"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "yelp_review_full",
+      "aliases": ["Yelp Review Full", "yelp_review_full_csv"],
+      "identity": {
+        "version": "1",
+        "fields": ["class_index", "review_text"],
+        "labels": ["1", "2", "3", "4", "5"],
+        "splits": {"train": 650000, "test": 50000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "YELP_REVIEWS",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/yelp_review_full_csv.tgz",
+        "archiveBytes": 196146755,
+        "catalogPrefixMiBMd5": "1efd84215ea3e30d90e4c33764b889db",
+        "archiveSha256": "56006b0a17a370f1e366504b1f2c3e3754e4a3dda17d3e718a885c552869a559",
+        "members": {
+          "train.csv": {"bytes": 480951174, "rows": 650000, "sha256": "f9147e1f0ac66a2bc561c8b717b023d484eea474188b74ae5d2710062a227270"},
+          "test.csv": {"bytes": 37051348, "rows": 50000, "sha256": "9676cbe482467fad25a07bacb2ac8b4910f03bab20f00455eb99525036be2894"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "yahoo_answers",
+      "aliases": ["Yahoo Answers", "Yahoo! Answers", "yahoo_answers_csv"],
+      "identity": {
+        "version": "2",
+        "fields": ["class_index", "question_title", "question_content", "best_answer"],
+        "labels": ["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"],
+        "splits": {"train": 1400000, "test": 60000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "YAHOO_ANSWERS",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/yahoo_answers_csv.tgz",
+        "archiveBytes": 319476345,
+        "catalogPrefixMiBMd5": "0632a0d236ef3a529c0fa4429b339f68",
+        "archiveSha256": "2d4277855faf8b35259009425fa8f7fe1888b5644b47165508942d000f4c96ae",
+        "members": {
+          "train.csv": {"bytes": 745966378, "rows": 1400000, "sha256": "763d20fa20349ac923cc8f6c04a369dfaf795a0954e5227a86ec672d59461c5b"},
+          "test.csv": {"bytes": 32040847, "rows": 60000, "sha256": "17e3b145efde81a4cb6c5b3cab2e58bbc2dd195bc5a1bdcaff22ea283adc4304"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "amazon_review_full",
+      "aliases": ["Amazon Review Full", "amazon_review_full_csv"],
+      "identity": {
+        "version": "3",
+        "fields": ["class_index", "review_title", "review_text"],
+        "labels": ["1", "2", "3", "4", "5"],
+        "splits": {"train": 3000000, "test": 650000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "AMAZON_REVIEWS",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/amazon_review_full_csv.tgz",
+        "archiveBytes": 643695014,
+        "catalogPrefixMiBMd5": "4a1196cf0adaea22f4bc3f592cddde90",
+        "archiveSha256": "4af62eeee139d0142e0747340b68646d23483d9475c33ea0641ee9175b423443",
+        "members": {
+          "train.csv": {"bytes": 1348342434, "rows": 3000000, "sha256": "16017c5a392e5fcda67c251b692d5711038e2e49375de1c9351e81e73210232f"},
+          "test.csv": {"bytes": 292412008, "rows": 650000, "sha256": "76016eefd4b35ed534a3163bc8bcfc2a01ae8f4a19ea801fad7d132bac1ac28e"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "amazon_review_polarity",
+      "aliases": ["Amazon Review Polarity", "amazon_review_polarity_csv"],
+      "identity": {
+        "version": "3",
+        "fields": ["class_index", "review_title", "review_text"],
+        "labels": ["1", "2"],
+        "splits": {"train": 3600000, "test": 400000}
+      },
+      "candidateTransport": {
+        "catalogId": "fastai1-datasets",
+        "catalogKey": "AMAZON_REVIEWS_POLARITY",
+        "url": "https://s3.amazonaws.com/fast-ai-nlp/amazon_review_polarity_csv.tgz",
+        "archiveBytes": 688339454,
+        "catalogPrefixMiBMd5": "676f7e5208ec343c8274b4bb085bc938",
+        "archiveSha256": "d2a3ee7a214497a5d1b8eaed7c8d7ba2737de00ada3b0ec46243983efa100361",
+        "members": {
+          "train.csv": {"bytes": 1585200224, "rows": 3600000, "sha256": "46ab0cfd4de8da74fd7b8f3ab72bdd2163ade4c11db057b22c5f39ab58be7ccf"},
+          "test.csv": {"bytes": 176046679, "rows": 400000, "sha256": "6ac6d882446c84adf0d3ce02ac7798e7932cb0a440ca683195e303d59c3f065e"}
+        }
+      },
+      "confidence": "catalog-plus-structural-validation"
+    },
+    {
+      "id": "librispeech_test_clean",
+      "aliases": ["LibriSpeech test-clean", "LibriSpeech test clean", "librispeech/test-clean"],
+      "identity": {
+        "version": "SLR12",
+        "modality": "speech",
+        "sampleRateHz": 16000,
+        "fields": ["audio", "transcript", "speaker_id", "chapter_id", "utterance_id"],
+        "splits": {"test-clean": 2620},
+        "license": "CC BY 4.0"
+      },
+      "candidateTransport": {
+        "catalogId": "openslr",
+        "catalogKey": "SLR12/test-clean.tar.gz",
+        "resourcePage": "https://www.openslr.org/12",
+        "url": "https://www.openslr.org/resources/12/test-clean.tar.gz",
+        "mirrors": [
+          "https://openslr.trmal.net/resources/12/test-clean.tar.gz",
+          "https://openslr.elda.org/resources/12/test-clean.tar.gz",
+          "https://openslr.magicdatatech.com/resources/12/test-clean.tar.gz"
+        ],
+        "archiveBytes": 346663984,
+        "archiveMd5": "32fa31d27d2e1cad72775fee3f4849a9",
+        "checksumUrl": "https://www.openslr.org/resources/12/md5sum.txt",
+        "archiveFormat": "tar.gz",
+        "memberValidation": {
+          "audioExtension": ".flac",
+          "audioFiles": 2620,
+          "transcriptSuffix": ".trans.txt",
+          "requiredTopLevelDirectory": "LibriSpeech/test-clean",
+          "requiredChecks": ["all audio decodes", "all utterance ids are unique", "every audio member has one transcript record", "every decoded sample rate is 16000 Hz"]
+        }
+      },
+      "confidence": "primary-catalog-plus-runtime-digest"
+    },
+    {
+      "id": "libritts_r_test_clean",
+      "aliases": ["LibriTTS-R test", "LibriTTS-R test-clean", "LibriTTS-R test clean", "libritts_r/test_clean"],
+      "identity": {
+        "version": "SLR141",
+        "modality": "speech",
+        "sampleRateHz": 24000,
+        "fields": ["audio", "original_text", "normalized_text", "speaker_id", "chapter_id", "utterance_id"],
+        "splits": {"test-clean": 4837},
+        "license": "CC BY 4.0",
+        "lineage": "LibriTTS-R contains the same constituent samples as LibriTTS with restored audio quality."
+      },
+      "candidateTransport": {
+        "catalogId": "openslr",
+        "catalogKey": "SLR141/test_clean.tar.gz",
+        "resourcePage": "https://www.openslr.org/141",
+        "url": "https://www.openslr.org/resources/141/test_clean.tar.gz",
+        "mirrors": [
+          "https://openslr.trmal.net/resources/141/test_clean.tar.gz",
+          "https://openslr.elda.org/resources/141/test_clean.tar.gz",
+          "https://openslr.magicdatatech.com/resources/141/test_clean.tar.gz"
+        ],
+        "archiveBytes": 1294768623,
+        "archiveMd5": "4d373d453eb96c0691e598061bbafab7",
+        "checksumUrl": "https://www.openslr.org/resources/141/md5sum.txt",
+        "archiveFormat": "tar.gz",
+        "memberValidation": {
+          "audioExtension": ".wav",
+          "audioFiles": 4837,
+          "requiredChecks": ["all audio decodes", "all utterance ids are unique", "every audio member has its paired text metadata", "every decoded sample rate is 24000 Hz"]
+        }
+      },
+      "confidence": "primary-catalog-plus-runtime-digest"
+    }
+  ]
+}

package/dist/arkgraph/boot.js

@@ -0,0 +1,6 @@
+(() => {
+ const english=!new URL(location.href).searchParams.get('locale')?.startsWith('zh');
+ document.documentElement.lang=english?'en':'zh-CN';
+ const style=document.createElement('link');style.rel='stylesheet';style.href=english?'viewer.en.css':'viewer.css';document.head.append(style);
+ const script=document.createElement('script');script.src=english?'viewer.en.js':'viewer.js';document.body.append(script);
+})();

package/dist/arkgraph/index.html

@@ -0,0 +1 @@
+<!doctype html><html><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><title>ArkGraph</title></head><body><div id="root"></div><script src="boot.js"></script></body></html>