SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.26401 · 2026

Word Alignment-Based Evaluation of Uniform Meaning Representations

Daniel Zeman, Federica Gamba

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2603.26401.json · badge: /api/ran/2603.26401.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
snowblink14/smatch canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
ufal/umrtools canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_pool Ran
ran; our contract draft was wrong, not the code
snowblink14/smatch/smatch.py
pointer only (licence: MIT); the stored copy get_code serves, from mdtux89/amr-evaluation, is pointer only (licence: NONE) · get_code("7843ac3f9290adb5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mdtux89/amr-evaluation, and GitHub detected no licence in that repository 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.

debugnode Ran
ran; our contract draft was wrong, not the code
ufal/umrtools/validate.py
pointer only (licence: NONE) · get_code("bd34562bd1e0db37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ufal/umrtools 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_max_width Ran
ran, honoured the contract we drafted
snowblink14/smatch/smatch-table.py
code served (permissive licence) · get_code("e414246ae8b8248d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Construct a simple table (list of rows, where each row is a list/tuple)
table = [
    ["apple", "banana", "cherry"],
    ["dog", "cat", "bird"],
    ["x", "longer_string", "y"]
]

# The function accesses row[index], so index must be a valid integer
# within the range of row lengths
index = 1

ARGS = {
    "table": table,
    "index": index
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_names Ran
ran; our contract draft was wrong, not the code
snowblink14/smatch/smatch-table.py
code served (permissive licence) · get_code("b61a85a3d0fb39e3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create subdirectories representing annotators/users
user1 = os.path.join(temp_dir, 'user1')
user2 = os.path.join(temp_dir, 'user2')
user3 = os.path.join(temp_dir, 'user3')

os.makedirs(user1)
os.makedirs(user2)
os.makedirs(user3)

# Create test files
# user1 and user2 have both files
with open(os.path.join(user1, 'nw_wsj_0001_1.txt'), 'w') as f:
    f.write('test')
with open(os.path.join(user1, 'nw_wsj_0002_1.txt'), 'w') as f:
    f.write('test')

with open(os.path.join(user2, 'nw_wsj_0001_1.txt'), 'w') as f:
    f.write('test')
with open(os.path.join(user2, 'nw_wsj_0002_1.txt'), 'w') as f:
    f.write('test')

# user3 only has one file
with open(os.path.join(user3, 'nw_wsj_0001_1.txt'), 'w') as f:
    f.write('test')

ARGS = {
    'file_dir': temp_dir + '/',
    'files': ['nw_wsj_0001_1', 'nw_wsj_0002_1']
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
has_trailing_whitespace Ran
ran; our contract draft was wrong, not the code
ufal/umrtools/validate.py
pointer only (licence: NONE) · get_code("1179bd79c6b8c4a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ufal/umrtools 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.

is_whitespace Ran
ran; our contract draft was wrong, not the code
ufal/umrtools/validate.py
pointer only (licence: NONE) · get_code("191d21062eeb81cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ufal/umrtools 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.

normalize Ran
ran; our contract draft was wrong, not the code
snowblink14/smatch/smatch.py
pointer only (licence: MIT); the stored copy get_code serves, from mdtux89/amr-evaluation, is pointer only (licence: NONE) · get_code("dcb0eab734135916")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mdtux89/amr-evaluation, and GitHub detected no licence in that repository 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_best_match Not yet run
unverified (harvested, no recorded run)
snowblink14/smatch/smatch.py
code served (permissive licence) · get_code("ed0a63fdc1a50789")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
compute_pool 1 other paper
1 dated earlier
1608.06111 (2016-08)
An Incremental Parser for Abstract Meaning Representation
get_best_match 1 other paper
1 dated earlier
1608.06111 (2016-08)
An Incremental Parser for Abstract Meaning Representation
normalize 1 other paper
1 dated earlier
1608.06111 (2016-08)
An Incremental Parser for Abstract Meaning Representation

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

Comparison and evaluation of graph-based representations of sentence meaning is a challenge because competing representations of the same sentence may have different number of nodes, and it is not obvious which nodes should be compared to each other. Existing approaches favor node mapping that maximizes F1 score over node relations and attributes, regardless whether the similarity is intentional or accidental; consequently, the identified mismatches in values of node attributes are not useful for any detailed error analysis. We propose a node-matching algorithm that allows comparison of multiple Uniform Meaning Representations (UMR) of one sentence and that takes advantage of node-word alignments, inherently available in UMR. We compare it with previously used approaches, in particular smatch (the de-facto standard in AMR evaluation), and argue that sensitivity to word alignment makes the comparison of meaning representations more intuitive and interpretable, while avoiding the NP-hard search problem inherent in smatch. A script implementing the method is freely available.

For agents

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

get_harvested_code_for_paper("2603.26401")
get_code_for_paper("2603.26401")
have("2603.26401")

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

curl https://syntology.ai/api/ran/2603.26401.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.26401.svg)](https://syntology.ai/paper/2603.26401)

Connect an agent — have() is free.