SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.07175 · EMNLP · 2024

Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing

U Berkeley, Gopala Anumanchipalli, Akshat Gupta, Sidharth Baskaran

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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 2 have no contract verdict; 10 failures of our instrument; 2 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/2403.07175.json · badge: /api/ran/2403.07175.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
scalable-model-editing/rebuilding-rome canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
upd_matrix_match_shape Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
scalable-model-editing/rebuilding-rome/rome/rome_main.py
code served (permissive licence) · get_code("3a7359734df0b9a0")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:20:19Z). 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

torch.manual_seed(0)

# Create a small matrix tensor with shape (4, 3)
matrix = torch.randn(4, 3)

# Create a target shape that matches the matrix
shape = torch.Size([4, 3])

ARGS = {
    "matrix": matrix,
    "shape": shape,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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
binary_log_probs Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from MemEIC/MemEIC, is pointer only (licence: NONE) · get_code("27659a9c234ffb11")
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 MemEIC/MemEIC, 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.

dict_to_ Ran
ran on a synthesized input
scalable-model-editing/rebuilding-rome/rome/tok_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("4b87278bcf65e54d")
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 keltin13/concept-rot, and GitHub could not classify the licence of that repository (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.

get_inv_cov Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
scalable-model-editing/rebuilding-rome/rome/compute_u.py
code served (permissive licence) · get_code("65f71b871888c246")
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 Tensor, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
from transformers import AutoModelForCausalLM, AutoTokenizer

torch.manual_seed(0)

# Stand-in classes for mock objects
class MockConfig:
    def __init__(self):
        self._name_or_path = "gpt2-small"

class MockStatObject:
    def __init__(self):
        self.mom2 = MockMoment()

class MockMoment:
    def __init__(self):
        self._data = torch.randn(4, 4)
    
    def moment(self):
        return self._data

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.config = MockConfig()
        self.layer_name_test = nn.Linear(4, 4)
    
    def forward(self, x):
        return x

class MockTokenizer:
    def __init__(self):
        self.vocab_size = 50257
    
    def encode(self, text):
        return [1, 2, 3]
    
    def decode(self, tokens):
        return "text"

# Patch the layer_stats function that's called in get_inv_cov
def mock_layer_stats(model, tok, layer_name, stats_dir, dataset, to_collect, sample_size, precision):
    return MockStatObject()

# Monkey patch for testing
import sys
current_module = sys.modules[__name__]
current_module.layer_stats = mock_layer_stats
current_module.STATS_DIR = "/tmp/stats"

# Create instances
model = MockModel()
tok = MockTokenizer()

ARGS = {
    "model": model,
    "tok": tok,
    "layer_name": "layer_name_test",
    "mom2_dataset": "wikitext",
    "mom2_n_samples": "1000",
    "mom2_dtype": "float32"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (fixture:KeyError)
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_words_idxs_in_templates Ran
ran, honoured the contract we drafted
scalable-model-editing/rebuilding-rome/rome/repr_tools.py
code served (permissive licence) · get_code("ae1a86ff8a89d505")
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 2, dtype family int; 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.

from transformers import AutoTokenizer
from unittest.mock import MagicMock

# Create a minimal tokenizer mock that behaves like AutoTokenizer
class MinimalTokenizer:
    def __call__(self, texts):
        """
        Mock tokenizer that returns token IDs.
        For a list of texts, returns a BatchFeature-like object
        where we can index by position and get token lists.
        """
        if isinstance(texts, str):
            texts = [texts]
        
        # Simple mock: each word gets 1-2 tokens
        result = []
        for text in texts:
            # Very simple tokenization: split by spaces, each token gets an ID
            words = text.split()
            tokens = list(range(len(words)))
            result.append(tokens)
        
        # Return a dict-like object that supports indexing
        return BatchFeatureMock(result)

class BatchFeatureMock:
    def __init__(self, token_lists):
        self.token_lists = token_lists
        self.data = {i: tokens for i, tokens in enumerate(token_lists)}
    
    def __getitem__(self, idx):
        if isinstance(idx, slice):
            start, stop, step = idx.indices(len(self.token_lists))
            return [self.token_lists[i] for i in range(start, stop, step or 1)]
        return self.token_lists[idx]
    
    def __len__(self):
        return len(self.token_lists)

tok = MinimalTokenizer()

# Test with simple templates and words
context_templates = [
    "{} plays basketball",
    "{} eats pizza"
]

words = [
    "Michael",
    "John"
]

subtoken = "last"

ARGS = {
    "tok": tok,
    "context_templates": context_templates,
    "words": words,
    "subtoken": subtoken
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family int — 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
hierarchical_subsequence Ran
ran on a synthesized input
scalable-model-editing/rebuilding-rome/util/nethook.py
code served (permissive licence) · get_code("920b394e7ad80c53")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type 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
import torch.nn as nn
from collections import OrderedDict

torch.manual_seed(0)

# Create a nested Sequential model to test hierarchical_subsequence
layer1 = nn.Linear(4, 3)
layer2 = nn.Linear(3, 2)
layer3 = nn.Linear(2, 5)

nested_seq = nn.Sequential(
    OrderedDict([
        ('linear1', layer1),
        ('linear2', layer2),
        ('linear3', layer3)
    ])
)

# Test case 1: No parameters (should return full sequential)
ARGS = {
    'sequential': nested_seq,
    'first': None,
    'last': None,
    'after': None,
    'upto': None,
    'share_weights': False,
    'depth': 0
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
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
kl_loc_loss Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("8b02eb3a3733d653")
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 Wangzzzzzzzz/OTE-SE-Alignment, 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.

length_collation Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/rome/tok_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("feecc08837987d77")
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 keltin13/concept-rot, and GitHub could not classify the licence of that repository (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.

make_padded_batch Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/rome/tok_dataset.py
pointer only (licence: MIT); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("59ff38281d7c12b8")
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 keltin13/concept-rot, and GitHub could not classify the licence of that repository (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.

moving_average Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
scalable-model-editing/rebuilding-rome/experiments/current_edit_scores.py
pointer only (licence: MIT); the stored copy get_code serves, from scalable-model-editing/unified-model-editing, is pointer only (licence: NONE) · get_code("6a33727392194b2c")
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 scalable-model-editing/unified-model-editing, 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.

multiclass_log_probs Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/baselines/mend/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("8ccc8886c554a1ce")
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 Wangzzzzzzzz/OTE-SE-Alignment, 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.

recursive_copy Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/util/nethook.py
pointer only (licence: MIT); the stored copy get_code serves, from TrustedLLM/UnKE, is pointer only (licence: NONE) · get_code("70f6ab8bde55420e")
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 TrustedLLM/UnKE, 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.

subsequence Ran
ran; our contract draft was wrong, not the code
scalable-model-editing/rebuilding-rome/util/nethook.py
code served (permissive licence) · get_code("440ff98c2b1ae1aa")
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 Sequential. The image it ran in was not recorded. If your copy returns the same type 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
import torch.nn as nn
import copy
from collections import OrderedDict

torch.manual_seed(0)

# Build a nested Sequential model with multiple layers
sequential = nn.Sequential(
    OrderedDict([
        ('layer1', nn.Linear(4, 3)),
        ('layer2', nn.ReLU()),
        ('layer3', nn.Linear(3, 2)),
        ('nested', nn.Sequential(
            OrderedDict([
                ('sublayer1', nn.Linear(2, 2)),
                ('sublayer2', nn.ReLU()),
            ])
        )),
        ('layer4', nn.Linear(2, 1)),
    ])
)

ARGS = {
    'sequential': sequential,
    'first_layer': None,
    'last_layer': None,
    'after_layer': None,
    'upto_layer': None,
    'single_layer': None,
    'share_weights': False,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated
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_model Not yet run
unverified (harvested, no recorded run)
scalable-model-editing/rebuilding-rome/baselines/mend/models.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("d9a5bcaef451668f")
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 Wangzzzzzzzz/OTE-SE-Alignment, 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. No invocation recorded.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
scalable-model-editing/rebuilding-rome/baselines/mend/models.py
pointer only (licence: MIT); the stored copy get_code serves, from Wangzzzzzzzz/OTE-SE-Alignment, is pointer only (licence: NONE) · get_code("87e77d8c9c3620e1")
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 Wangzzzzzzzz/OTE-SE-Alignment, 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 14 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 9 the same month, 14 later) and 1 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
subsequence 49 other papers
13 dated earlier, 4 the same month, 31 later, 1 same year, order not determinable
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2009.05041 (2020-09)
Understanding the Role of Individual Units in a Deep Neural Network
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 46 more not named here
recursive_copy 48 other papers
11 dated earlier, 4 the same month, 32 later, 1 same year, order not determinable
2207.02774 (2022-07)
Local Relighting of Real Scenes
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
and 45 more not named here
hierarchical_subsequence 46 other papers
10 dated earlier, 4 the same month, 31 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 43 more not named here
binary_log_probs 28 other papers
7 dated earlier, 2 the same month, 18 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2310.10322 (2023-10)
Evaluating the Reversal Curse in Model Editing
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 25 more not named here
multiclass_log_probs 10 other papers
3 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
and 7 more not named here
kl_loc_loss 9 other papers
3 dated earlier, 1 the same month, 5 later
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
and 6 more not named here
get_model 8 other papers
3 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
and 5 more not named here
get_tokenizer 8 other papers
3 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
2024.acl-long.732 (2024 (year only))
MULFE: A Multi-Level Benchmark for Free Text Model Editing
and 5 more not named here
dict_to_ 3 other papers
3 later
2408.07413 (2024-08)
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
2410.12299 (2024-10)
Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
make_padded_batch 3 other papers
3 later
2408.07413 (2024-08)
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
2410.12299 (2024-10)
Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
upd_matrix_match_shape 3 other papers
1 dated earlier, 2 later
2202.05262 (2022-02)
Locating and Editing Factual Associations in GPT
2406.11263 (2024-06)
Understanding the Collapse of LLMs in Model Editing
2502.10438 (2025-02)
Injecting Universal Jailbreak Backdoors into LLMs in Minutes
get_inv_cov 2 other papers
1 the same month, 1 later
2403.13355 (2024-03)
BadEdit: Backdooring large language models by model editing
2025.findings-acl.598 (2025 (year only))
DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
length_collation 2 other papers
2 later
2410.12299 (2024-10)
Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
moving_average 2 other papers
1 dated earlier, 1 later
2401.07453 (2024-01)
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
2405.00664 (2024-05)
Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

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 using Rank-One Model Editing (ROME), a popular model editing method, has shown that there are certain facts that the algorithm is unable to edit without breaking the model. Such edits have previously been called disabling edits (Gupta et al., 2024a). These disabling edits cause immediate model collapse and limits the use of ROME for sequential editing. In this paper, we show that disabling edits are an artifact of irregularities in the implementation of ROME. With this paper, we provide a more stable implementation ROME, which we call r-ROME and show that model collapse is no longer observed when making large scale sequential edits with r-ROME, while further improving generalization and locality of model editing compared to the original implementation of ROME.

For agents

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

get_harvested_code_for_paper("2403.07175")
get_code_for_paper("2403.07175")
have("2403.07175")

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

curl https://syntology.ai/api/ran/2403.07175.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.07175.svg)](https://syntology.ai/paper/2403.07175)

Connect an agent — have() is free.