KNOWME / PAPER RADAR

Free to install

Paper Radar

Discover papers.See the evidence.

Filter arXiv papers by your research interests.
Inspect author, institution and source evidence as you build a reading list.

No model key needed · Saved papers and cache stay local

01 Discover 02 Inspect

Evidence behind your reading list
KnowMe · Research toolsInterface example

Multiple dimensions · Weighted to your research

Reading list · RRSIView original

Current Chinese interface · Full English UI planned.

Localized interface preview · Swipe to explore. Papers and scores use public metadata.

PAPER RADAR / MULTIDIMENSIONAL SCORING

Ranking evidence
and preferences

Scores combine topic matching, source evidence for authors and institutions, publication age and your research interests. Inspect the contributing evidence when deciding what to read.

Topic relevanceAuthor evidenceInstitutional evidenceRecencyYour interests
Layered weightingYour reading order

Scores depend on the selected research interests and available source evidence. Inspect the links between papers, authors and institutions in Radar.

Compare research perspectives
01

Multidimensional scores

Combine relevance, author and institutional evidence, and recency through layered weighting.

02

Inspect the evidence

Explore scores, author contributions and source records.

03

Stay with the paper

View annotations on arXiv and save papers for your next read.

PAPER RADAR / SELECTED EXPERIMENTS

Research behind the tool

Measurements on a snapshot of 174,640 acquired records inform two choices in Paper Radar: keep abstracts with their sources, and reuse the source graph when reading priorities change.

Coverage from abstracts

64.5%

Of the focused topic-matched cohort, 37,495 of 58,094 papers had no matching title signal.

Lexical topic matching · 16 LLM-related directions · thirteen months

External retrieval relevance

0.412 → 0.598

NDCG@10 for titles alone versus titles plus abstracts, using the same fixed relevance scorer.

CSFCube · 50 retrieval tasks · 6,242 expert-judged pairs · Qwen3.8-27B

Retained-graph preparation

3.03–3.64×

Faster response preparation with a retained source graph, for 1,000 returned papers per request.

Elapsed response time (s) · six directions · three paired runs per direction

Populations and measurement conditions

Library. The acquisition through 3 November 2026 contains 174,640 unique in-scope paper identifiers, with versions and cross-listings merged.

Coverage. The same direction definitions admit 20,599 papers from titles and 58,094 from titles plus cached abstracts. The 64.5% is calculated within this focused cohort.

Retrieval. The external CSFCube benchmark contains 34 distinct query papers across 50 query–facet tasks. The model, prompts and candidate pools stay fixed; expert grades are withheld from scoring. This evaluates the information supplied to a fixed relevance scorer.

Preparation. Mean fresh-source times span 151.04–168.27 seconds; retained-graph times span 41.77–55.47 seconds. Ratios compare unrounded means within each direction. All 18 matched pairs return identical scores and source bindings; the target direction is uncached in both modes.

Preparation timing covers the native response call through complete serialization from loaded inputs, on an Intel Xeon Platinum 8369B CPU host with 800 GiB memory and Node.js v26.4.0. Initial loading and worker setup are excluded. These timings apply to retained state in a persistent local service; independent CLI processes prepare their own contexts.

Inspect in the browser. Reuse through the CLI.

The browser makes the reading list and its supporting evidence inspectable. A local command-line interface returns JSON or JSONL with source identifiers, abstracts, score components and missing-evidence states for downstream tools.

Explore the public Research Atlas
System view: from a reading profile to shared evidence
Four-column Paper Radar architecture: profile and canonical sources feed typed author–paper evidence; author and institution context feed a shared engine with source and context caches, browser output and JSONL output. A return loop reuses versioned sources and profile fingerprints.
Source and context caches support the browser and structured agent outputs. The public atlas retains a separate fixed snapshot. Open the full diagram

PAPER RADAR / LOCAL CLI

Use paper evidence in your own tools

Rank supplied metadata and export JSONL for a reading assistant, retrieval pipeline or research agent. The toolkit requires Node.js 22.13 or newer, with no npm installation. It is separate from the Chrome extension.

Download CLI 1.2.7 (.zip)

201 KB · Offline ranking + JSONL conversion · No model key required

Extract the ZIP and open a terminal in its knowme-cli-1.2.7 folder. The included three-paper example is synthetic interface data, not a research result.

node scripts/rank-research-papers.mjs --list-topics

node scripts/rank-research-papers.mjs \
  --input examples/frozen-papers.json --profile examples/profile.json \
  --from 2026-09-01 --to 2026-09-30 \
  --exclude survey --limit 20 --format jsonl > ranked.jsonl

node examples/jsonl-to-rag.mjs \
  ranked.jsonl rag-documents.jsonl selected-ids.json

JSONL begins with a manifest, followed by paper records using schema knowme-ranked-evidence-v1. Installing the Chrome extension does not install these terminal commands. Graph export and citation refresh are not included in this download.

Use your own records, profile or stdin

Replace the synthetic example with {"records":[{"paper":{...}}]}. Each paper carries its ID, title, abstract in summary, author list, dates and categories. Supply your complete relevant bibliography: the date window selects candidates while context uses all supplied records.

Use --profile profile.json with {"name":"My research","topics":{"rag":1,"reasoning":2}}, or use --topics rag:1,reasoning:2 instead. Priority 1 is highest and 4 is lowest. --exclude matches literal title/abstract text and can be repeated.

--input - accepts the same JSON via stdin. Check the process exit status, parse stdout and retain stderr for diagnostics. Keep the returned snapshotId with downstream documents. The ZIP's README contains the complete flag and output reference.

Package checksum and verification

SHA-256: 938dbcff7ddc508bf8305c30bce24cf5b73760f5b8e87cf4e399eb99bcb00a3c

The extracted package was checked with Node.js v26.4.0 using the included synthetic input. File, stdin and inline-topic results matched the current source implementation at the same clock; the check made no network or database calls. The package manifest lists its files and source provenance.

Read the score with its evidence

Scores express reading priority under the selected profile and supplied records. Inspect the abstracts and supporting sources to decide how a paper informs your research.

Each fresh CLI process prepares its own context. The retained-graph speedup above applies to a persistent local service; a small output limit does not remove preparation work.

GET STARTED

Start here.

Install. Set up. Start reading.
Find answers as you go.

1

Install from the storePin Paper Radar to the toolbar for easy access.

2

Choose your interestsStart with 1–3 topics and run an online refresh.

3

Inspect and saveExplore scores and author evidence, then save papers worth reading.

How do I build my first paper cache?

Choose your topics and run an online refresh. Then use cache-only mode to revisit the same date range and filters. Cache-only mode does not contact arXiv; refresh online for the latest papers.

How do I set up page annotations?

Author profiles and Scholar search / arXiv details have separate controls. Compact mode keeps the KnowMe button and hides long status text and author coloring. Annotations use local records and a limited bundled index; a missing match does not imply a paper is unimportant.

Does my data sync automatically?

Saved papers, cache, personal terms and history stay in the current browser and do not sync through your Google account. Export a backup before changing devices, browser profiles or uninstalling. Your chosen model service processes translations and connection tests.

VERSION UPDATES

Version updates

2026.11.18
1.2.7

Paper Radar · 1.2.6 published, 1.2.7 submitted

Version 1.2.7 updates institution attribution, direction-specific context and score explanations. The extension update has been submitted for Chrome Web Store review. The separate CLI 1.2.7 toolkit and usage guide are available on this site.

Public store version checked on 2026-11-18: 1.2.6. The store controls extension availability; the CLI download is separate. Interface examples keep their recorded versions and scores.

PRIVACY, IN PLAIN WORDS

Your data, explained.

This page uses public papers and prewritten examples. Interactions affect only this page, with no model calls or access to extension data, your clipboard or browsing history.

Paper Radar

Cache, saved papers and settings stay in the current browser. Searches and updates you start access public scholarly sources such as arXiv. Page annotations use local records and a limited bundled index.

AI Translate

Model connections, personal terms and translation history stay locally. Translations and connection tests send requests to your chosen model service and use its allowance. Export important memory regularly.

See each privacy policy for data uses, permissions and controls.