SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.17653 · 2026

Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking

Shane Steinert-Threlkeld, Iskar Deng, Nathalia Xu

arXiv · PDF · Open in the Atlas

Code that ran

17 of 21 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; 0 honoured the contract we drafted, 4 violated it and 0 have no contract verdict; 13 failures of our instrument; 4 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/2602.17653.json · badge: /api/ran/2602.17653.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
Iskar-Deng/DAM-learning canonical (classifier label)
classifier basis: census
17 ran · 4 no recorded run
FunctionStatusWhere it lives
apply_spans Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/build_rule_mastery_minpairs.py
pointer only (licence: NONE) · get_code("1f1207a846290637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

build_children Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/perturb_blimp.py
pointer only (licence: NONE) · get_code("db96d499009c324e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

build_children_index Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/data_processing/extract_verb.py
pointer only (licence: NONE) · get_code("8a2e1b777686a6e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

clean_text Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/data_processing/parse.py
pointer only (licence: NONE) · get_code("42072772adaf6878")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

detokenize_with_word_spans Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/build_probe_heads.py
pointer only (licence: NONE) · get_code("99cdd5650420e311")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

extract_clause_span Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/data_processing/extract_verb.py
pointer only (licence: NONE) · get_code("f881a892ec7b2914")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

extract_np_span Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/data_processing/extract_verb.py
pointer only (licence: NONE) · get_code("d49c21e2219c0107")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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_input_file Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/classifiers/generate_data.py
pointer only (licence: NONE) · get_code("2ccef013f8b92023")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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_valid_structure Ran
ran, violated the contract we drafted
Iskar-Deng/DAM-learning/evaluation/build_marker_placement_minpairs.py
pointer only (licence: NONE) · get_code("748689a591e3b9a6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

load_model Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/eval_minpairs_acc.py
pointer only (licence: NONE) · get_code("0af832420874c823")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

parse_run_id Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/build_marker_placement_minpairs.py
pointer only (licence: NONE) · get_code("bf4e689139a6db82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

read_minipairs Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/eval_minpairs_acc.py
pointer only (licence: NONE) · get_code("86b24d26a70e41e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

regex_sentencize Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/data_processing/filter_sentences.py
pointer only (licence: NONE) · get_code("eeaabd1ad6f9d0a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

should_mark_global Ran
ran, violated the contract we drafted
Iskar-Deng/DAM-learning/utils.py
pointer only (licence: NONE) · get_code("8625d141a1dc7dc4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

should_mark_local_A Ran
ran, violated the contract we drafted
Iskar-Deng/DAM-learning/utils.py
pointer only (licence: NONE) · get_code("dbdb4bac7d1f9188")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

should_mark_local_P Ran
ran, violated the contract we drafted
Iskar-Deng/DAM-learning/utils.py
pointer only (licence: NONE) · get_code("1e2f9a2f7f4cf052")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

span_to_head_word_id Ran
ran; our contract draft was wrong, not the code
Iskar-Deng/DAM-learning/evaluation/build_probe_heads.py
pointer only (licence: NONE) · get_code("129c46987ade7562")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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.

annotate_doc Not yet run
unverified (harvested, no recorded run)
Iskar-Deng/DAM-learning/data_processing/parse.py
pointer only (licence: NONE) · get_code("fd30a104ef419866")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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. No invocation recorded.

annotate_first_sentence Not yet run
unverified (harvested, no recorded run)
Iskar-Deng/DAM-learning/evaluation/perturb_blimp.py
pointer only (licence: NONE) · get_code("a724969085731ad3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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. No invocation recorded.

count_nonempty_lines Not yet run
unverified (harvested, no recorded run)
Iskar-Deng/DAM-learning/data_processing/parse.py
pointer only (licence: NONE) · get_code("9a5746186457b6ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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. No invocation recorded.

load_tokenizer Not yet run
unverified (harvested, no recorded run)
Iskar-Deng/DAM-learning/evaluation/eval_minpairs_acc.py
pointer only (licence: NONE) · get_code("4bb1111352e82926")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Iskar-Deng/DAM-learning 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. No invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 21 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.

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

Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble crosslinguistic regularities in human languages, particularly for syntactic phenomena such as word order. In this paper, we extend this paradigm to differential argument marking (DAM), a semantic licensing system in which morphological marking depends on semantic prominence. Using a controlled synthetic learning method, we train GPT-2 models on 18 corpora implementing distinct DAM systems and evaluate their generalization using minimal pairs. Our results reveal a dissociation between two typological dimensions of DAM. Models reliably exhibit human-like preferences for natural markedness direction, favoring systems in which overt marking targets semantically atypical arguments. In contrast, models do not reproduce the strong object preference in human languages, in which overt marking in DAM more often targets objects rather than subjects. These findings suggest that different typological tendencies may arise from distinct underlying sources. 1

For agents

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

get_harvested_code_for_paper("2602.17653")
get_code_for_paper("2602.17653")
have("2602.17653")

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

curl https://syntology.ai/api/ran/2602.17653.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.17653.svg)](https://syntology.ai/paper/2602.17653)

Connect an agent — have() is free.