deepxiv/deepxiv_sdk/deepxiv-fa-appraise

DeepXiv · Appraise (appraise)

Academic appraisal: which academicians and society fellows have cited a paper, and what they actually said. 112k arXiv papers authored by 5,427 fellows and academicians (Chinese Academies, US NAS/NAE, Royal Society / RAEng, ACM / IEEE / AAAI / ACL / AAAS / IAPR / CCF), with 5.26M parsed references and 8.3M citing sentences, each classified by type and stance. The id is the paper being appraised (arXiv id / DOI / title). ask turns the matched sentences into a Chinese appraisal paragraph for grant reports and promotion dossiers, with the English original attached to every claim.

Corpus: 284,124 documents.

Setup

pip install -U deepxiv-sdk      # deepxiv registers a token on first use

With a registered key (https://data.rag.ac.cn/register), search and read are fair use: 60/min, 5 at once, 5,000/day; on the auto-registered token they spend the deepxiv daily limit at the credits listed below. ask draws on the daily ask allowance (resets 00:00 UTC; a site-wide daily total can run out early at peak times), or 3 lifetime trial asks on the auto-registered token. On 429, back off for Retry-After seconds. Data goes to stdout; cost, quota and sources go to stderr. Exit 0 ok, 1 API error, 2 usage error. The general CLI guide is the deepxiv-cli skill.

Start here

deepxiv fa search appraise "DeepSeek-R1" -k 3   # → arxiv:2501.12948
deepxiv fa read appraise arxiv:2501.12948 -l brief   # counts and stance breakdown
deepxiv fa read appraise arxiv:2501.12948 -p stance=positive -p org=CAS,CAE   # positive sentences from Chinese academicians
deepxiv fa ask "DeepSeek-R1 得到了哪些院士的正面评价" -d appraise -p paper=arxiv:2501.12948

Free samples: ids arxiv:2402.03216; queries BGE-M3.

Search

deepxiv fa search appraise "query" [-F FILTER]... [-k N] [--offset N] [--mode M] [--head] [--json]

Modes: hybrid, title. Up to 20 hits. Cost 3 (with --head: 4). An empty query is rejected; use "*" to list by filters only. Filters combine with AND; an undeclared field exits 2.

Advanced filters (see deepxiv fa spec appraise): affiliation, section, mentions_name, annotated.

Read

deepxiv fa read appraise ID [ID...] [-l brief|detail|full] [-e EXTRA] [-p k=v]... [-f json|md|html]

At -l full, -p section=NAME reads one section and -p characters=N the first N characters.

Facets

deepxiv fa facets appraise FIELD lists the legal values and counts, free. Use it instead of guessing a spelling. Fields: org, bucket, type, stance.

Ask

deepxiv fa ask "question" -d appraise [-e low|medium|high] [-p k=v]... [--no-stream] [--json]

Turns "who of note has evaluated this paper" into Chinese appraisal text: resolves the paper (semantic search over papers → arXiv id), pulls the fellows' citing sentences, then writes one paragraph per person. Wording may be positive but must not exceed what the original says; every paragraph carries the English original and its source. effort sets how many people are written up (low 5 / medium 10 / high 20)

Always pass -d appraise: automatic domain picking is still early.

What this corpus will and will not tell you

• Coverage: Covers only arXiv full texts authored by these 5,427 fellows and academicians; their journal-only papers and citations by anyone else are not included. No hit means this set of papers does not cite it — not that the work is uncited.
• Three id forms: arxiv:2402.03216 (bare ids accepted), doi:10.1145/…, and title:<paper title>. The first two are exact lookups (~40ms); title: is a substring match over normalised bibliography text — 3–6 seconds, and papers with similar titles can collide, so the response carries warnings.
• search has no vector index: the query first goes through the papers domain's semantic search to identify the paper (so a title, a model name or a one-line description all work), then the arXiv id is used for lookup. If it picks the wrong paper, read by id instead: read arxiv:<id>.
• type / stance / about_target / claim / zh are model-assigned; the sentence itself is the evidence. Quote the sentence in anything formal. Sentences with annotated=false have not been classified yet.
• level=detail returns only opinionated citation types by default; background citations are more than half the total — use level=full or pass type= to get them.
• How ask writes: early work may become 'early pioneering work' and a baseline 'widely adopted as a comparison baseline', but nothing may be asserted that the original sentence does not say. Every paragraph carries the English original so a reader can check it.
• people[].person_id is the talent domain's id — read talent <person_id> for that person's full profile.
• Attribution: author-year references ('Li et al., 2025') can match several bibliography entries; such sentences are marked ambiguous=true.

Citing

Cite records as [appraise:<honoree_id> <name>]. Say plainly when the corpus has nothing.

Generated by scripts/gen_fa_skills.py from deepxiv fa spec appraise --json on 2026-10-19. Field names and prices can change; deepxiv fa spec appraise is the live source.