Who leads the scidocs-(mag) benchmark?

SPECTER currently leads scidocs-(mag) with a score of 82 on F1 Micro.

What is the state-of-the-art score on scidocs-(mag)?

The state-of-the-art result on scidocs-(mag) is 82 (F1 Micro), achieved by SPECTER as of 2022.

How many models are tracked on scidocs-(mag)?

Codesota tracks 2 models on scidocs-(mag).

When was the scidocs-(mag) leaderboard last updated?

The scidocs-(mag) leaderboard on Codesota includes results through 2022, with the earliest tracked result from 2020.

Codesota · Benchmark · scidocs-(mag)Home/Leaderboards/Vision & Documents/Document OCR/scidocs-(mag)

Unknown

scidocs-(mag).

Name: scidocs-(mag) Benchmark Results
Creator: Unknown
Published: 2020-01-01
License: https://creativecommons.org/licenses/by/4.0/

scidocs-(mag) is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for scidocs-(mag).

Paper ↗Leaderboard ↓

§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Only 2 models on this benchmark

Help build the community leaderboard — submit your model results.

Found a wrong score or missing run?

Use row edits to send a sourced correction into moderation.

Add / edit result ↗Report issue ↗

F1 Micro

F1 Micro is the reported evaluation metric for scidocs-(mag). Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for F1 Microverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	SPECTER From paper: SPECTER: Document-level Representation Learning using Citation-informed Transformers	verified	82	2020	Paper ↗Code ↗	Looks wrong?
02	SciNCL From paper: Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings	verified	81.4	2022	Paper ↗Code ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR