SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.21489 · ACL · 2024

Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends

Roberto Navigli, Edoardo Barba, Giuliano Martinelli

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 5 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.21489.json · badge: /api/ran/2407.21489.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
SapienzaNLP/maverick-coref canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
flatten Ran
ran, honoured the contract we drafted
SapienzaNLP/maverick-coref/maverick/common/util.py
pointer only (licence: NONE) · get_code("20922c79a0929bbf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SapienzaNLP/maverick-coref when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

A_and_B_corefs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SapienzaNLP/maverick-coref/maverick/evaluate.py
pointer only (licence: NOASSERTION) · get_code("6b7799612a72d501")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

b_cubed Ran
ran, honoured the contract we drafted
SapienzaNLP/maverick-coref/maverick/common/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from sapienzanlp/bookcoref, is pointer only (licence: NONE) · get_code("e8ce0142bdf8a593")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SapienzaNLP/maverick-coref when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

candidate_pronoun_clustered Ran
ran, violated the contract we drafted
SapienzaNLP/maverick-coref/maverick/evaluate.py
pointer only (licence: NOASSERTION) · get_code("fef6da1366efc239")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

f1 Ran
ran, honoured the contract we drafted
SapienzaNLP/maverick-coref/maverick/common/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from sapienzanlp/bookcoref, is pointer only (licence: NONE) · get_code("5dc251a1bb16c94f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SapienzaNLP/maverick-coref when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_offsets_in_clusters Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SapienzaNLP/maverick-coref/maverick/evaluate.py
pointer only (licence: NOASSERTION) · get_code("197c9d892060fc72")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

identity Ran
ran, honoured the contract we drafted
SapienzaNLP/maverick-coref/maverick/utils/sampler.py
pointer only (licence: NONE); the stored copy get_code serves, from dholzmueller/universal_double_descent, is pointer only (licence: NONE) · get_code("9910e2fc297f8665")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SapienzaNLP/maverick-coref when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

muc Ran
ran, honoured the contract we drafted
SapienzaNLP/maverick-coref/maverick/common/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from sapienzanlp/bookcoref, is pointer only (licence: NONE) · get_code("8b30464b3ec47d85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SapienzaNLP/maverick-coref when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_category_id Not yet run
unverified (harvested, no recorded run)
SapienzaNLP/maverick-coref/maverick/common/util.py
pointer only (licence: NOASSERTION) · get_code("f2c593891a325316")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_logger Not yet run
unverified (harvested, no recorded run)
SapienzaNLP/maverick-coref/maverick/utils/logging.py
pointer only (licence: NOASSERTION) · get_code("00efd68da46bd738")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_pronoun_id Not yet run
unverified (harvested, no recorded run)
SapienzaNLP/maverick-coref/maverick/common/util.py
pointer only (licence: NOASSERTION) · get_code("72038039c3ad8d52")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, SapienzaNLP/maverick-coref (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 6 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
identity 69 other papers
54 dated earlier, 2 the same month, 13 later · 5 only as an assembly brick
1706.07296 (2017-06)
A Minimal Developmental Model Can Increase Evolvability in Soft Robots
1802.09419 (2018-02)
Stochastic Hyperparameter Optimization through Hypernetworks
1804.06055 (2018-04)
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
and 66 more not named here
flatten 21 other papers
20 dated earlier, 1 same year, order not determinable
1609.08675 (2016-09)
YouTube-8M: A Large-Scale Video Classification Benchmark
1802.04821 (2018-02)
Evolved Policy Gradients
1811.05014 (2018-11)
NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification
and 18 more not named here
f1 12 other papers
10 dated earlier, 1 later, 1 same year, order not determinable
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1907.10529 (2019-07)
SpanBERT: Improving Pre-training by Representing and Predicting Spans
2021.naacl-main.125 (2021 (year only))
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network
and 9 more not named here
muc 3 other papers
1 dated earlier, 1 later, 1 same year, order not determinable
2205.12644 (2022-05)
LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
2024.acl-srw.56 (2024 (year only))
Z-coref: Thai Coreference and Zero Pronoun Resolution
2507.12075 (2025-07)
BOOKCOREF: Coreference Resolution at Book Scale
b_cubed 1 other paper
1 later
2507.12075 (2025-07)
BOOKCOREF: Coreference Resolution at Book Scale
get_category_id 1 other paper
1 later
2604.17108 (2026-04)
Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text
get_pronoun_id 1 other paper
1 later
2604.17108 (2026-04)
Beyond Word Boundaries: A Hebrew Coreference Benchmark and an Evaluation Protocol for Morphologically Complex Text

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks. However, the urge to attain superior results has, at times, led to the premature replacement of carefully designed task-specific approaches without exhaustive experimentation. The Coreference Resolution task is no exception; all recent stateof-the-art solutions adopt large generative autoregressive models that outperform encoderbased discriminative systems. In this work, we challenge this recent trend by introducing Maverick, a carefully designed -yet simple -pipeline, which enables running a state-ofthe-art Coreference Resolution system within the constraints of an academic budget, outperforming models with up to 13 billion parameters with as few as 500 million parameters. Maverick achieves state-of-the-art performance on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining a 170x faster inference compared to previous state-of-the-art systems. We extensively validate the robustness of the Maverick framework with an array of diverse experiments, reporting improvements over prior systems in data-scarce, long-document, and out-of-domain settings. We release our code and models for research purposes at https: //github.com/SapienzaNLP/maverick-coref.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.21489")
get_code_for_paper("2407.21489")
have("2407.21489")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.21489.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.21489.svg)](https://syntology.ai/paper/2407.21489)

Connect an agent — have() is free.