Open Research Opportunity Miner

$1.50 USDC per call · Research integrity · POST /api/v1/mine-future-work · Id future-work-miner

Leads with a verdict (OPEN_GAPS_FOUND, NO_CLEAR_OPEN_GAPS or NO_GAPS_EXTRACTED), a confidence, a headline naming the top gap with its quoted evidence, and the next step. Collects papers for a topic or seed list (arXiv ids or URLs, DOIs, PMIDs; arXiv and OpenAlex search), reads full text from ar5iv or Europe PMC, and extracts future-work, limitation and open-question sentences in code with exact section spans. Near-duplicates are clustered across papers, then each cluster is checked against later citing works (OpenAlex cites, Semantic Scholar citation contexts) and marked OPEN, POSSIBLY_ADDRESSED or ADDRESSED. Scores combine recurrence across independent author groups, recency, citation momentum and openness with documented formulas. mode "fast" makes zero model calls; the default makes two (cluster wording, addressed judgment) and lets them move a status at most one level. OPEN means no scanned citing paper covered the theme, not that nobody has: the check reads titles, abstracts and citation contexts of up to a few hundred citing works, not their full text. Papers without open full text contribute only abstracts.

What you get

Turns a topic or reading list into ranked research gaps, each backed by the authors' own quoted future-work sentence and checked against later citing papers, so a lab or R&D team starts from a gap nobody has visibly filled.

Call it

Send the JSON body below to https://agents.writerslogic.com/api/v1/mine-future-work. An unpaid request answers 402 with the price and how to pay; a request that fails with a 5xx status is not charged.

curl -i -X POST https://agents.writerslogic.com/api/v1/mine-future-work \
  -H 'content-type: application/json' \
  -d '{"query":"parameter-efficient fine-tuning of large language models","maxPapers":8,"mode":"fast"}'

Input

Field	Type	Required	Description
`query`	string; length 3..300	no	Research topic, e.g. "parameter-efficient fine-tuning of language models".
`seeds`	array<string; length 5..200>; max 25 items	no	Seed papers you already have: arXiv ids or URLs (2106.09685, arXiv:1706.03762, arxiv.org/abs/...), DOIs or doi.org URLs, or PMIDs (PMID:12345678 or a PubMed URL). Always analysed, not date-filtered.
`fromDate`	string; length 10..10	no	Only topic-search papers published on or after this date (YYYY-MM-DD).
`toDate`	string; length 10..10	no	Only topic-search papers published on or before this date (YYYY-MM-DD).
`maxPapers`	integer; 1..25	no	Papers to analyse, at most 25 (default 10); seeds count toward it.
`field`	string; length 2..80	no	Field or discipline keyword added to the topic search, e.g. "machine learning".
`mode`	string; one of "fast", "full"	no	fast: zero model calls (lexical clustering and lexical addressed-check). full (default): one clustering call and one judging call, bounded to one status level.

Example request body

{
  "query": "parameter-efficient fine-tuning of large language models",
  "maxPapers": 8,
  "mode": "fast"
}

Result

The response is { "data": ..., "_provenance": ... }. data carries these fields; _provenance is a signed W3C Verifiable Credential with a C2PA-style manifest, checked free at POST /api/v1/verify-provenance.

Field	Type	Required	Description
`verdict`	string; one of "OPEN_GAPS_FOUND", "NO_CLEAR_OPEN_GAPS", "NO_GAPS_EXTRACTED"	no	OPEN_GAPS_FOUND: at least one theme no scanned citing paper covers. NO_CLEAR_OPEN_GAPS: themes found but each looks addressed. NO_GAPS_EXTRACTED: no future-work statements found.
`confidence`	integer	no	0-100 = 50 x share of papers read in full text + 50 x mean share of each theme's source papers whose citing works were retrieved. Evidence depth, not the odds a gap is real.
`headline`	string	no	One-sentence human summary led by the top opportunity.
`nextStep`	string	no	The concrete next action.
`topOpportunity`	one of	no
`partial`	boolean	no	True when the request deadline was reached or citing works could not be retrieved for most themes; see coverage.failures.
`query`	object	no	Echo of query, seeds, field and date range.
`mode`	string; one of "fast", "full"	no
`papers`	array<object>	no	Analysed source papers with where their text came from (ar5iv, europepmc or abstract only) and how many statements each yielded.
`opportunities`	array<object>	no	Clusters of future-work statements, best score first.
`llmCalls`	integer	no	Model requests issued: 0 in fast mode, at most 2 in full mode.
`decidedBy`	string; one of "code", "code+model"	no	code+model when a verified model output (clustering or judgment) was used.
`coverage`	object	no	Papers analysed, full-text count, statements, clusters, citing works scanned, quote verification, upstream call budget, failures.

Pay and connect

Available through: x402 (USDC on Base), MCP, RapidAPI, Apify.

Machine-readable

This agent as JSON (schemas, example, OpenAPI operation)
Free signed sample response
OpenAPI 3.1 · Catalog · Index of every agent