/deepxiv-fa-appraise

name: deepxiv-fa-appraise
description: Find which academicians and society fellows (CAS, CAE, NAS, NAE, Royal Society, ACM, IEEE, AAAI …) cited a paper and what they actually said, with the citing sentence, type and stance. Use for grant reports, promotion dossiers, or any 'who of note praised this paper' question.

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.

| filter | type | `-F` syntax | meaning | |---|---|---|---| | `org` | keyword | `k=v`, `k=a,b` | Honour body: CAS / CAE (Chinese academies), NAS / NAE (US), ROYALSOC / RAENG (UK), ACM / IEEE / AAAI / ACL / AAAS / IAPR / CCF (fellows); several allowed Values: `CAS`, `CAE`, `NAS`, `NAE`, `ROYALSOC`, `RAENG`, `ACM`, `IEEE` …. | | `bucket` | keyword | `k=v`, `k=a,b` | Weight class: academy (academicians) / major (ACM, IEEE … fellows) / other Values: `academy`, `major`, `other`. | | `stance` | keyword | `k=v`, `k=a,b` | Stance of the citing sentence (model-assigned): positive / neutral / negative Values: `positive`, `neutral`, `negative`. | | `type` | keyword | `k=v`, `k=a,b` | Citation type (model-assigned): endorse / buildon / exemplar / baseline / resource / critique / motivate / background Values: `endorse`, `buildon`, `exemplar`, `baseline`, `critique`, `resource`, `motivate`, `background`. | | `about_target` | bool | `k=v` | Whether the sentence is about this paper itself rather than a passing mention | | `min_h_index` | integer | `k=v` | Only people with at least this h-index | | `honoree` | text | `k~text` | Filter by name (zh/en, substring) | | `citing_year` | integer | `k=v`, `k>=n`, `k=n..m` | Year of the citing paper; ranges allowed |

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]

| level | credits | returns | |---|---|---| | `brief` | 1 | Summary card: how many fellows, citing papers and sentences, the stance and type breakdown, and the single strongest sentence | | `detail` (default) | 3 | The list plus the sentences (the default, level=detail): per citation the type, stance, whether it is about this paper, the model's one-line claim, a Chinese translation, the English original, the section and the citing paper. Only opinionated types by default (no background); pass type= for everything | | `full` | 5 | All the evidence (level=full): background citations included, every sentence with its neighbouring sentences and the raw bibliography entry — for verification |

| `-e` extra | credits | returns | |---|---|---| | `honorees` | 2 | The list: each fellow's Chinese titles, affiliation, h-index, talent person_id, how many times they cited it and in which papers (no sentences) |

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.

| `-p` param | type | meaning | |---|---|---| | `paper` | string | name the paper directly (arXiv id / DOI / title) and skip resolution | | `filters` | object | restrict which citations are used (same DSL as search filters) |

What this corpus will and will not tell you

• Coverage: Covers only arXiv full texts authored by these