Ranker API & Inference Endpoint

How it works

Given a research intent, a query-specific relevance checklist, and a candidate paper's metadata, abstract, and retrieved evidence, the Ranker:

scores each checklist criterion from 1 to 5;
provides evidence-grounded rationales and flags weak matches;
estimates holistic relevance and reranks verified papers.

This design ranks authentic, traceable paper records instead of generating citations. The model was trained through multidisciplinary knowledge distillation on 42,762 query–paper pairs spanning 19 disciplines and 97 fine-grained topics, including positive, partial-match, and hard-negative examples.

PaSaMaster results

The following are end-to-end PaSaMaster system results using this Ranker, measured on PaSaMaster-Bench (244 expert-curated tasks across 38 disciplines):

Table with columns: Method, NDCG@20, Recall@20, Precision@20, F1@20, Hallucination, Cost/query
Method	NDCG@20	Recall@20	Precision@20	F1@20	Hallucination	Cost/query
Google Scholar	2.07	1.69	1.48	1.39	0%	—
OpenScholar	14.61	11.68	8.52	7.92	0%	—
Bohrium Science Navigator	22.39	19.37	12.50	12.26	0%	—
DeepSeek-v3.2	35.82

PaSaMaster achieves 16.5× the F1@20 of Google Scholar and 37.8% higher F1@20 than GPT-5.2 in the reported evaluation, at approximately $0.05 per query.

Intended use

Use this checkpoint within the PaSaMaster pipeline or a compatible evidence-grounded literature-ranking workflow. Supply retrieved paper evidence and treat its outputs as relevance judgments, not as independent proof that a citation is valid.

Resources

How it works

Given a research intent, a query-specific relevance checklist, and a candidate paper's metadata, abstract, and retrieved evidence, the Ranker:

scores each checklist criterion from 1 to 5;
provides evidence-grounded rationales and flags weak matches;
estimates holistic relevance and reranks verified papers.

PaSaMaster results

The following are end-to-end PaSaMaster system results using this Ranker, measured on PaSaMaster-Bench (244 expert-curated tasks across 38 disciplines):

Table with columns: Method, NDCG@20, Recall@20, Precision@20, F1@20, Hallucination, Cost/query
Method	NDCG@20	Recall@20	Precision@20	F1@20	Hallucination	Cost/query
Google Scholar	2.07	1.69	1.48	1.39	0%	—
OpenScholar	14.61	11.68	8.52	7.92	0%	—
Bohrium Science Navigator	22.39	19.37	12.50	12.26	0%	—
DeepSeek-v3.2	35.82

PaSaMaster achieves 16.5× the F1@20 of Google Scholar and 37.8% higher F1@20 than GPT-5.2 in the reported evaluation, at approximately $0.05 per query.

Ranker

README

How it works

PaSaMaster results

Intended use

Resources

Explore FriendliAI today

README

How it works

PaSaMaster results

Intended use

Resources