frontier-scholar 0.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- frontier_scholar-0.1.0/LICENSE +201 -0
- frontier_scholar-0.1.0/PKG-INFO +183 -0
- frontier_scholar-0.1.0/README.md +161 -0
- frontier_scholar-0.1.0/pyproject.toml +38 -0
- frontier_scholar-0.1.0/setup.cfg +4 -0
- frontier_scholar-0.1.0/src/frontier_scholar/__init__.py +10 -0
- frontier_scholar-0.1.0/src/frontier_scholar/__main__.py +3 -0
- frontier_scholar-0.1.0/src/frontier_scholar/cli.py +381 -0
- frontier_scholar-0.1.0/src/frontier_scholar/client.py +226 -0
- frontier_scholar-0.1.0/src/frontier_scholar.egg-info/PKG-INFO +183 -0
- frontier_scholar-0.1.0/src/frontier_scholar.egg-info/SOURCES.txt +13 -0
- frontier_scholar-0.1.0/src/frontier_scholar.egg-info/dependency_links.txt +1 -0
- frontier_scholar-0.1.0/src/frontier_scholar.egg-info/entry_points.txt +2 -0
- frontier_scholar-0.1.0/src/frontier_scholar.egg-info/top_level.txt +1 -0
- frontier_scholar-0.1.0/tests/test_frontier_scholar.py +132 -0
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1,183 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: frontier-scholar
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: FrontierScholar (知沿学术): a research-frontier wiki of the scientific literature for agents - Python client and CLI
|
|
5
|
+
Author: FrontierScholar
|
|
6
|
+
License-Expression: Apache-2.0
|
|
7
|
+
Project-URL: Homepage, https://frontier-scholar.com
|
|
8
|
+
Project-URL: Documentation, https://frontier-scholar.com/docs/
|
|
9
|
+
Project-URL: Repository, https://github.com/FrontierScholar/FrontierScholar
|
|
10
|
+
Project-URL: Issues, https://github.com/FrontierScholar/FrontierScholar/issues
|
|
11
|
+
Keywords: research,literature,arxiv,agents,wiki,survey,llm
|
|
12
|
+
Classifier: Development Status :: 4 - Beta
|
|
13
|
+
Classifier: Environment :: Console
|
|
14
|
+
Classifier: Intended Audience :: Science/Research
|
|
15
|
+
Classifier: Operating System :: OS Independent
|
|
16
|
+
Classifier: Programming Language :: Python :: 3
|
|
17
|
+
Classifier: Topic :: Scientific/Engineering
|
|
18
|
+
Requires-Python: >=3.8
|
|
19
|
+
Description-Content-Type: text/markdown
|
|
20
|
+
License-File: LICENSE
|
|
21
|
+
Dynamic: license-file
|
|
22
|
+
|
|
23
|
+
<p align="center">
|
|
24
|
+
<img src="https://raw.githubusercontent.com/FrontierScholar/FrontierScholar/main/assets/logo.png" width="148" alt="FrontierScholar logo">
|
|
25
|
+
</p>
|
|
26
|
+
|
|
27
|
+
<h1 align="center">FrontierScholar 知沿学术</h1>
|
|
28
|
+
<p align="center"><em>The scientific literature, organised into a wiki agents can walk - down to the research frontier of every subtopic.</em></p>
|
|
29
|
+
|
|
30
|
+
<p align="center">
|
|
31
|
+
<a href="https://frontier-scholar.com">Website</a> ·
|
|
32
|
+
<a href="https://frontier-scholar.com/docs/">API documentation</a> ·
|
|
33
|
+
<a href="https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md">Agent skill</a> ·
|
|
34
|
+
<a href="https://github.com/FrontierScholar/FrontierScholar/blob/main/README.zh.md">中文</a>
|
|
35
|
+
</p>
|
|
36
|
+
|
|
37
|
+
---
|
|
38
|
+
|
|
39
|
+
## What it is
|
|
40
|
+
|
|
41
|
+
A read-only JSON API over a wiki of the scientific literature, with a Python SDK and CLI (`pip install frontier-scholar`) and skills for coding agents. The goal is every field of science; the first release covers about **870k arXiv computer-science papers**, organised into 20 domains, 1,593 topics and 19,304 subtopics. Every subtopic has pages on its research problems, method families, datasets and benchmarks, plus a frontier page - and every claim on those pages cites the papers it comes from.
|
|
42
|
+
|
|
43
|
+
| | Command | |
|
|
44
|
+
|---|---|---|
|
|
45
|
+
| **Walk the field** | `nav` / `locate` | Domain → topic → subtopic, or let the service's model find the page for a request |
|
|
46
|
+
| **Read in layers** | `read` / `read-id` | A subtopic's index first, then only the pages you pick, within a token budget |
|
|
47
|
+
| **See the frontier** | `frontier` | Current approaches with their trend, open gaps with when they were first raised |
|
|
48
|
+
| **Compare results** | `bench` | One benchmark's result tables from every subtopic that reports it |
|
|
49
|
+
| **Check at the source** | `paper` / `dates` | A paper's problem, method, evaluation and mechanism; first-version arXiv dates |
|
|
50
|
+
| **Search** | `grep` / `search` | Literal and ranked keyword search inside a topic or subtopic |
|
|
51
|
+
|
|
52
|
+
## What problem it solves
|
|
53
|
+
|
|
54
|
+
Ask an agent "what is the state of the art in adaptive retrieval, and what is still open?" and it has two bad options. It can search and read abstracts, which name papers but never compare them. Or it can read dozens of full papers, which costs hundreds of thousands of tokens before any synthesis starts.
|
|
55
|
+
|
|
56
|
+
FrontierScholar does the reading ahead of time. Each subtopic's papers have already been read, compared and written up as problem, method and resource pages, so an agent can spend a few thousand tokens on the synthesis and then open only the papers it needs to verify. Every subtopic also has a frontier page: which approaches are rising, which gaps are open, and which paper first raised each one.
|
|
57
|
+
|
|
58
|
+
## Install
|
|
59
|
+
|
|
60
|
+
```bash
|
|
61
|
+
pip install frontier-scholar # the `frontier-scholar` CLI and the Python SDK (Python 3.8+, no dependencies)
|
|
62
|
+
npx skills add FrontierScholar/FrontierScholar # the agent skills
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
The skills can also come from the [GitHub CLI](https://cli.github.com/) v2.90.0 or later:
|
|
66
|
+
|
|
67
|
+
```bash
|
|
68
|
+
gh skill install FrontierScholar/FrontierScholar # choose interactively
|
|
69
|
+
gh skill install FrontierScholar/FrontierScholar frontier-scholar # one skill
|
|
70
|
+
gh skill install FrontierScholar/FrontierScholar --agent claude-code # or codex, cursor, gemini
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
The API needs a key, issued by the FrontierScholar team. Keep it in an environment variable, never in a command line or a repository:
|
|
74
|
+
|
|
75
|
+
```bash
|
|
76
|
+
export FRONTIER_SCHOLAR_API_KEY="wiki_…"
|
|
77
|
+
frontier-scholar nav # lists the domains when the key works
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
The CLI and the SDK talk to `https://frontier-scholar.com`; set `FRONTIER_SCHOLAR_BASE` if you were given another address.
|
|
81
|
+
|
|
82
|
+
## Usage
|
|
83
|
+
|
|
84
|
+
One investigation, start to finish: what is the frontier of adaptive retrieval - deciding when a RAG system should retrieve at all?
|
|
85
|
+
|
|
86
|
+
**1. Find the subtopic.** Walk down from a domain:
|
|
87
|
+
|
|
88
|
+
```bash
|
|
89
|
+
frontier-scholar nav information-retrieval
|
|
90
|
+
frontier-scholar nav information-retrieval/agentic-search
|
|
91
|
+
```
|
|
92
|
+
|
|
93
|
+
**2. Read its frontier.** One call returns the current approaches and the open gaps, each tied to papers and dated (output trimmed):
|
|
94
|
+
|
|
95
|
+
```bash
|
|
96
|
+
frontier-scholar frontier information-retrieval/agentic-search/adaptive-retrieval
|
|
97
|
+
```
|
|
98
|
+
|
|
99
|
+
```
|
|
100
|
+
== Adaptive Retrieval — Research Frontier | as of 2025-12-22 | 75 papers of 90 assigned
|
|
101
|
+
Approaches:
|
|
102
|
+
- Training-free prefix-logit and margin gating [rising] papers: 2509.06472 2511.09803
|
|
103
|
+
- Learned evidence-sufficiency and stopping control [rising] papers: 2505.02811 2508.17862 …
|
|
104
|
+
- Cost-aware RL search agents with adaptive depth [rising] papers: 2505.17281 2510.00568 …
|
|
105
|
+
Gaps:
|
|
106
|
+
- No universal threshold or calibration rule across models, datasets, and corpora
|
|
107
|
+
[method, open, 6 papers; first 2024-02-26 2402.16457, latest 2025-12-18 2512.16883]
|
|
108
|
+
- Cost and latency accounting is inconsistent and rarely end-to-end
|
|
109
|
+
[efficiency, open, 6 papers; first 2024-10-22 2410.18141, latest 2025-10-17 2510.15719]
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
Give a topic or domain instead to survey every subtopic below it, and filter: `frontier-scholar frontier information-retrieval --trend rising --status open --query retrieval`. `--page` prints the full page, with its timeline and evidence.
|
|
113
|
+
|
|
114
|
+
**3. Read the pages behind it.** A folder's index lists every page with its size, so you choose what to spend tokens on:
|
|
115
|
+
|
|
116
|
+
```bash
|
|
117
|
+
frontier-scholar read information-retrieval/agentic-search/adaptive-retrieval/Methods
|
|
118
|
+
frontier-scholar read information-retrieval/agentic-search/adaptive-retrieval/Methods/confidence-gated-retrieval.md
|
|
119
|
+
```
|
|
120
|
+
|
|
121
|
+
**4. Verify at the source, and respect a cut-off.** Read only the facet you need, and check publication dates:
|
|
122
|
+
|
|
123
|
+
```bash
|
|
124
|
+
frontier-scholar paper 2511.09803 --facet evaluation
|
|
125
|
+
frontier-scholar dates 1706.03762 2511.09803 --before 2025-01-01
|
|
126
|
+
```
|
|
127
|
+
|
|
128
|
+
```
|
|
129
|
+
1706.03762 2017-06-12 before 2025-01-01: True
|
|
130
|
+
2511.09803 2025-11-12 before 2025-01-01: False
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
**5. Compare results on a benchmark.** The same benchmark has a Resources page in every subtopic that uses it; `bench` collects them:
|
|
134
|
+
|
|
135
|
+
```bash
|
|
136
|
+
frontier-scholar bench MIRACL --location information-retrieval
|
|
137
|
+
```
|
|
138
|
+
|
|
139
|
+
Scores from different splits or settings are not comparable, so each table keeps its protocol and the paper behind every number.
|
|
140
|
+
|
|
141
|
+
**In Python**, the same steps are methods of `Client`:
|
|
142
|
+
|
|
143
|
+
```python
|
|
144
|
+
from frontier_scholar import Client
|
|
145
|
+
|
|
146
|
+
client = Client() # reads FRONTIER_SCHOLAR_API_KEY
|
|
147
|
+
frontier = client.frontier("information-retrieval/agentic-search/adaptive-retrieval")
|
|
148
|
+
for gap in frontier["subtopics"][0]["gaps"]:
|
|
149
|
+
print(gap["name"], gap["status"], gap["first_raised"])
|
|
150
|
+
|
|
151
|
+
page = client.read_page("information-retrieval/agentic-search/adaptive-retrieval/Methods/confidence-gated-retrieval.md")
|
|
152
|
+
evaluation = client.paper("2511.09803", facets=["evaluation"])
|
|
153
|
+
dates = client.paper_dates(["1706.03762", "2511.09803"], before="2025-01-01")
|
|
154
|
+
miracl = client.benchmark_results("MIRACL", location="information-retrieval")
|
|
155
|
+
```
|
|
156
|
+
|
|
157
|
+
Every method returns the tool's `data`; errors raise `FrontierScholarError` with the API's `code`, `details` and `request_id`. `client.call(tool, arguments)` reaches any tool by name.
|
|
158
|
+
|
|
159
|
+
**Over HTTP**, every tool is the same call:
|
|
160
|
+
|
|
161
|
+
```bash
|
|
162
|
+
curl -sS https://frontier-scholar.com/api/v1/api/invoke \
|
|
163
|
+
-H "X-API-Key: $FRONTIER_SCHOLAR_API_KEY" -H "Content-Type: application/json" \
|
|
164
|
+
-d '{"tool": "retrieval.frontier", "arguments": {"location": "information-retrieval/agentic-search/adaptive-retrieval"}}'
|
|
165
|
+
```
|
|
166
|
+
|
|
167
|
+
## Agent skills
|
|
168
|
+
|
|
169
|
+
| Skill | |
|
|
170
|
+
|---|---|
|
|
171
|
+
| [`frontier-scholar`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md) | The `frontier-scholar` commands and how to work with the wiki. Load this one first. |
|
|
172
|
+
| [`frontier-scholar-benchmark-sota`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar-benchmark-sota/SKILL.md) | A ranked, verified results table for one benchmark, with a date cut-off. |
|
|
173
|
+
| [`frontier-scholar-frontier-report`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar-frontier-report/SKILL.md) | A research-frontier report: approaches and trends, open gaps and since when, stated coverage. |
|
|
174
|
+
|
|
175
|
+
## Documentation
|
|
176
|
+
|
|
177
|
+
- **[frontier-scholar.com/docs](https://frontier-scholar.com/docs/)**: every tool with its parameters, a real response, and request examples in curl, Python and the CLI; errors and limits. In English and Chinese.
|
|
178
|
+
- **[skills/frontier-scholar/SKILL.md](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md)**: the operating instructions agents load.
|
|
179
|
+
- **`frontier-scholar -h`** and **`help(frontier_scholar.Client)`**: the CLI and SDK reference.
|
|
180
|
+
|
|
181
|
+
## License
|
|
182
|
+
|
|
183
|
+
Apache 2.0 - see [LICENSE](https://github.com/FrontierScholar/FrontierScholar/blob/main/LICENSE). Issues and questions: [github.com/FrontierScholar/FrontierScholar/issues](https://github.com/FrontierScholar/FrontierScholar/issues).
|
|
@@ -0,0 +1,161 @@
|
|
|
1
|
+
<p align="center">
|
|
2
|
+
<img src="https://raw.githubusercontent.com/FrontierScholar/FrontierScholar/main/assets/logo.png" width="148" alt="FrontierScholar logo">
|
|
3
|
+
</p>
|
|
4
|
+
|
|
5
|
+
<h1 align="center">FrontierScholar 知沿学术</h1>
|
|
6
|
+
<p align="center"><em>The scientific literature, organised into a wiki agents can walk - down to the research frontier of every subtopic.</em></p>
|
|
7
|
+
|
|
8
|
+
<p align="center">
|
|
9
|
+
<a href="https://frontier-scholar.com">Website</a> ·
|
|
10
|
+
<a href="https://frontier-scholar.com/docs/">API documentation</a> ·
|
|
11
|
+
<a href="https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md">Agent skill</a> ·
|
|
12
|
+
<a href="https://github.com/FrontierScholar/FrontierScholar/blob/main/README.zh.md">中文</a>
|
|
13
|
+
</p>
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## What it is
|
|
18
|
+
|
|
19
|
+
A read-only JSON API over a wiki of the scientific literature, with a Python SDK and CLI (`pip install frontier-scholar`) and skills for coding agents. The goal is every field of science; the first release covers about **870k arXiv computer-science papers**, organised into 20 domains, 1,593 topics and 19,304 subtopics. Every subtopic has pages on its research problems, method families, datasets and benchmarks, plus a frontier page - and every claim on those pages cites the papers it comes from.
|
|
20
|
+
|
|
21
|
+
| | Command | |
|
|
22
|
+
|---|---|---|
|
|
23
|
+
| **Walk the field** | `nav` / `locate` | Domain → topic → subtopic, or let the service's model find the page for a request |
|
|
24
|
+
| **Read in layers** | `read` / `read-id` | A subtopic's index first, then only the pages you pick, within a token budget |
|
|
25
|
+
| **See the frontier** | `frontier` | Current approaches with their trend, open gaps with when they were first raised |
|
|
26
|
+
| **Compare results** | `bench` | One benchmark's result tables from every subtopic that reports it |
|
|
27
|
+
| **Check at the source** | `paper` / `dates` | A paper's problem, method, evaluation and mechanism; first-version arXiv dates |
|
|
28
|
+
| **Search** | `grep` / `search` | Literal and ranked keyword search inside a topic or subtopic |
|
|
29
|
+
|
|
30
|
+
## What problem it solves
|
|
31
|
+
|
|
32
|
+
Ask an agent "what is the state of the art in adaptive retrieval, and what is still open?" and it has two bad options. It can search and read abstracts, which name papers but never compare them. Or it can read dozens of full papers, which costs hundreds of thousands of tokens before any synthesis starts.
|
|
33
|
+
|
|
34
|
+
FrontierScholar does the reading ahead of time. Each subtopic's papers have already been read, compared and written up as problem, method and resource pages, so an agent can spend a few thousand tokens on the synthesis and then open only the papers it needs to verify. Every subtopic also has a frontier page: which approaches are rising, which gaps are open, and which paper first raised each one.
|
|
35
|
+
|
|
36
|
+
## Install
|
|
37
|
+
|
|
38
|
+
```bash
|
|
39
|
+
pip install frontier-scholar # the `frontier-scholar` CLI and the Python SDK (Python 3.8+, no dependencies)
|
|
40
|
+
npx skills add FrontierScholar/FrontierScholar # the agent skills
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
The skills can also come from the [GitHub CLI](https://cli.github.com/) v2.90.0 or later:
|
|
44
|
+
|
|
45
|
+
```bash
|
|
46
|
+
gh skill install FrontierScholar/FrontierScholar # choose interactively
|
|
47
|
+
gh skill install FrontierScholar/FrontierScholar frontier-scholar # one skill
|
|
48
|
+
gh skill install FrontierScholar/FrontierScholar --agent claude-code # or codex, cursor, gemini
|
|
49
|
+
```
|
|
50
|
+
|
|
51
|
+
The API needs a key, issued by the FrontierScholar team. Keep it in an environment variable, never in a command line or a repository:
|
|
52
|
+
|
|
53
|
+
```bash
|
|
54
|
+
export FRONTIER_SCHOLAR_API_KEY="wiki_…"
|
|
55
|
+
frontier-scholar nav # lists the domains when the key works
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
The CLI and the SDK talk to `https://frontier-scholar.com`; set `FRONTIER_SCHOLAR_BASE` if you were given another address.
|
|
59
|
+
|
|
60
|
+
## Usage
|
|
61
|
+
|
|
62
|
+
One investigation, start to finish: what is the frontier of adaptive retrieval - deciding when a RAG system should retrieve at all?
|
|
63
|
+
|
|
64
|
+
**1. Find the subtopic.** Walk down from a domain:
|
|
65
|
+
|
|
66
|
+
```bash
|
|
67
|
+
frontier-scholar nav information-retrieval
|
|
68
|
+
frontier-scholar nav information-retrieval/agentic-search
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
**2. Read its frontier.** One call returns the current approaches and the open gaps, each tied to papers and dated (output trimmed):
|
|
72
|
+
|
|
73
|
+
```bash
|
|
74
|
+
frontier-scholar frontier information-retrieval/agentic-search/adaptive-retrieval
|
|
75
|
+
```
|
|
76
|
+
|
|
77
|
+
```
|
|
78
|
+
== Adaptive Retrieval — Research Frontier | as of 2025-12-22 | 75 papers of 90 assigned
|
|
79
|
+
Approaches:
|
|
80
|
+
- Training-free prefix-logit and margin gating [rising] papers: 2509.06472 2511.09803
|
|
81
|
+
- Learned evidence-sufficiency and stopping control [rising] papers: 2505.02811 2508.17862 …
|
|
82
|
+
- Cost-aware RL search agents with adaptive depth [rising] papers: 2505.17281 2510.00568 …
|
|
83
|
+
Gaps:
|
|
84
|
+
- No universal threshold or calibration rule across models, datasets, and corpora
|
|
85
|
+
[method, open, 6 papers; first 2024-02-26 2402.16457, latest 2025-12-18 2512.16883]
|
|
86
|
+
- Cost and latency accounting is inconsistent and rarely end-to-end
|
|
87
|
+
[efficiency, open, 6 papers; first 2024-10-22 2410.18141, latest 2025-10-17 2510.15719]
|
|
88
|
+
```
|
|
89
|
+
|
|
90
|
+
Give a topic or domain instead to survey every subtopic below it, and filter: `frontier-scholar frontier information-retrieval --trend rising --status open --query retrieval`. `--page` prints the full page, with its timeline and evidence.
|
|
91
|
+
|
|
92
|
+
**3. Read the pages behind it.** A folder's index lists every page with its size, so you choose what to spend tokens on:
|
|
93
|
+
|
|
94
|
+
```bash
|
|
95
|
+
frontier-scholar read information-retrieval/agentic-search/adaptive-retrieval/Methods
|
|
96
|
+
frontier-scholar read information-retrieval/agentic-search/adaptive-retrieval/Methods/confidence-gated-retrieval.md
|
|
97
|
+
```
|
|
98
|
+
|
|
99
|
+
**4. Verify at the source, and respect a cut-off.** Read only the facet you need, and check publication dates:
|
|
100
|
+
|
|
101
|
+
```bash
|
|
102
|
+
frontier-scholar paper 2511.09803 --facet evaluation
|
|
103
|
+
frontier-scholar dates 1706.03762 2511.09803 --before 2025-01-01
|
|
104
|
+
```
|
|
105
|
+
|
|
106
|
+
```
|
|
107
|
+
1706.03762 2017-06-12 before 2025-01-01: True
|
|
108
|
+
2511.09803 2025-11-12 before 2025-01-01: False
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
**5. Compare results on a benchmark.** The same benchmark has a Resources page in every subtopic that uses it; `bench` collects them:
|
|
112
|
+
|
|
113
|
+
```bash
|
|
114
|
+
frontier-scholar bench MIRACL --location information-retrieval
|
|
115
|
+
```
|
|
116
|
+
|
|
117
|
+
Scores from different splits or settings are not comparable, so each table keeps its protocol and the paper behind every number.
|
|
118
|
+
|
|
119
|
+
**In Python**, the same steps are methods of `Client`:
|
|
120
|
+
|
|
121
|
+
```python
|
|
122
|
+
from frontier_scholar import Client
|
|
123
|
+
|
|
124
|
+
client = Client() # reads FRONTIER_SCHOLAR_API_KEY
|
|
125
|
+
frontier = client.frontier("information-retrieval/agentic-search/adaptive-retrieval")
|
|
126
|
+
for gap in frontier["subtopics"][0]["gaps"]:
|
|
127
|
+
print(gap["name"], gap["status"], gap["first_raised"])
|
|
128
|
+
|
|
129
|
+
page = client.read_page("information-retrieval/agentic-search/adaptive-retrieval/Methods/confidence-gated-retrieval.md")
|
|
130
|
+
evaluation = client.paper("2511.09803", facets=["evaluation"])
|
|
131
|
+
dates = client.paper_dates(["1706.03762", "2511.09803"], before="2025-01-01")
|
|
132
|
+
miracl = client.benchmark_results("MIRACL", location="information-retrieval")
|
|
133
|
+
```
|
|
134
|
+
|
|
135
|
+
Every method returns the tool's `data`; errors raise `FrontierScholarError` with the API's `code`, `details` and `request_id`. `client.call(tool, arguments)` reaches any tool by name.
|
|
136
|
+
|
|
137
|
+
**Over HTTP**, every tool is the same call:
|
|
138
|
+
|
|
139
|
+
```bash
|
|
140
|
+
curl -sS https://frontier-scholar.com/api/v1/api/invoke \
|
|
141
|
+
-H "X-API-Key: $FRONTIER_SCHOLAR_API_KEY" -H "Content-Type: application/json" \
|
|
142
|
+
-d '{"tool": "retrieval.frontier", "arguments": {"location": "information-retrieval/agentic-search/adaptive-retrieval"}}'
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
## Agent skills
|
|
146
|
+
|
|
147
|
+
| Skill | |
|
|
148
|
+
|---|---|
|
|
149
|
+
| [`frontier-scholar`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md) | The `frontier-scholar` commands and how to work with the wiki. Load this one first. |
|
|
150
|
+
| [`frontier-scholar-benchmark-sota`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar-benchmark-sota/SKILL.md) | A ranked, verified results table for one benchmark, with a date cut-off. |
|
|
151
|
+
| [`frontier-scholar-frontier-report`](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar-frontier-report/SKILL.md) | A research-frontier report: approaches and trends, open gaps and since when, stated coverage. |
|
|
152
|
+
|
|
153
|
+
## Documentation
|
|
154
|
+
|
|
155
|
+
- **[frontier-scholar.com/docs](https://frontier-scholar.com/docs/)**: every tool with its parameters, a real response, and request examples in curl, Python and the CLI; errors and limits. In English and Chinese.
|
|
156
|
+
- **[skills/frontier-scholar/SKILL.md](https://github.com/FrontierScholar/FrontierScholar/blob/main/skills/frontier-scholar/SKILL.md)**: the operating instructions agents load.
|
|
157
|
+
- **`frontier-scholar -h`** and **`help(frontier_scholar.Client)`**: the CLI and SDK reference.
|
|
158
|
+
|
|
159
|
+
## License
|
|
160
|
+
|
|
161
|
+
Apache 2.0 - see [LICENSE](https://github.com/FrontierScholar/FrontierScholar/blob/main/LICENSE). Issues and questions: [github.com/FrontierScholar/FrontierScholar/issues](https://github.com/FrontierScholar/FrontierScholar/issues).
|
|
@@ -0,0 +1,38 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=77"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "frontier-scholar"
|
|
7
|
+
dynamic = ["version"]
|
|
8
|
+
description = "FrontierScholar (知沿学术): a research-frontier wiki of the scientific literature for agents - Python client and CLI"
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
requires-python = ">=3.8"
|
|
11
|
+
license = "Apache-2.0"
|
|
12
|
+
license-files = ["LICENSE"]
|
|
13
|
+
authors = [{ name = "FrontierScholar" }]
|
|
14
|
+
keywords = ["research", "literature", "arxiv", "agents", "wiki", "survey", "llm"]
|
|
15
|
+
classifiers = [
|
|
16
|
+
"Development Status :: 4 - Beta",
|
|
17
|
+
"Environment :: Console",
|
|
18
|
+
"Intended Audience :: Science/Research",
|
|
19
|
+
"Operating System :: OS Independent",
|
|
20
|
+
"Programming Language :: Python :: 3",
|
|
21
|
+
"Topic :: Scientific/Engineering",
|
|
22
|
+
]
|
|
23
|
+
dependencies = []
|
|
24
|
+
|
|
25
|
+
[project.urls]
|
|
26
|
+
Homepage = "https://frontier-scholar.com"
|
|
27
|
+
Documentation = "https://frontier-scholar.com/docs/"
|
|
28
|
+
Repository = "https://github.com/FrontierScholar/FrontierScholar"
|
|
29
|
+
Issues = "https://github.com/FrontierScholar/FrontierScholar/issues"
|
|
30
|
+
|
|
31
|
+
[project.scripts]
|
|
32
|
+
frontier-scholar = "frontier_scholar.cli:main"
|
|
33
|
+
|
|
34
|
+
[tool.setuptools.dynamic]
|
|
35
|
+
version = { attr = "frontier_scholar.__version__" }
|
|
36
|
+
|
|
37
|
+
[tool.setuptools.packages.find]
|
|
38
|
+
where = ["src"]
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
"""FrontierScholar (知沿学术): a research-frontier wiki of the scientific literature, for agents.
|
|
2
|
+
|
|
3
|
+
``Client`` is the Python API; the ``frontier-scholar`` command is the CLI (see ``frontier-scholar -h``).
|
|
4
|
+
"""
|
|
5
|
+
|
|
6
|
+
__version__ = "0.1.0"
|
|
7
|
+
|
|
8
|
+
from .client import DEFAULT_BASE, Client, FrontierScholarError # noqa: E402
|
|
9
|
+
|
|
10
|
+
__all__ = ["Client", "FrontierScholarError", "DEFAULT_BASE", "__version__"]
|