Papers › Persistent Topological Features in Large Language Models

Persistent Topological Features in Large Language Models

14 Oct 2024arXiv:2410.11042archive 2025-07-28

Yuri Gardinazzi, Karthik Viswanathan, Giada Panerai, Alessio Ansuini, Alberto Cazzaniga, Matteo Biagetti

Understanding the decision-making processes of large language models is critical given their widespread applications. To achieve this, we aim to connect a formal mathematical framework - zigzag persistence from topological data analysis - with practical and easily applicable algorithms. Zigzag persistence is particularly effective for characterizing data as it dynamically transforms across model layers. Within this framework, we introduce topological descriptors that measure how topological features, p-dimensional holes, persist and evolve throughout the layers. Unlike methods that assess each layer individually and then aggregate the results, our approach directly tracks the full evolutionary path of these features. This offers a statistical perspective on how prompts are rearranged and their relative positions changed in the representation space, providing insights into the system's operation as an integrated whole. To demonstrate the expressivity and applicability of our framework, we highlight how sensitive these descriptors are to different models and a variety of datasets. As a showcase application to a downstream task, we use zigzag persistence to establish a criterion for layer pruning, achieving results comparable to state-of-the-art methods while preserving the system-level perspective.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 9 ran (5 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 9 samples that ran have no recorded date.

RitAreaSciencePark/ZigZagLLMs officialmentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (4 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
2ran; the contract check could not run
3ran
1unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from RitAreaSciencePark/ZigZagLLMs. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

RitAreaSciencePark/ZigZagLLMs official repository 10 samples, 9 ran (4 instrument-failed) · 1 unverified
check_dir in 7 papers src/benchmark/benchmark.py ran · our draft was wrong MIT (permissive) · d8f3a9f76735c093 · report fixture: signature path:str/0/str, model_name:str/0/str · returned str · level recorded, date not recorded
div in 13 papers src/benchmark/post_process.py ran fingerprinted MIT (permissive) · d1af30de1d59a5a9 · report fixture: signature num:int/0/int, den:int/0/int · returned float · level recorded 2026-09-24
flattening_for_zigzag_ver src/zigzag/run_fast_zigzag.py ran · our draft was wrong MIT (permissive) · 8360fa8b0b26a936 · report fixture: signature times:list/1/list, f:dict/0/? · returned tuple · level recorded, date not recorded
get_embdims src/representation/rep-extraction/intrinsic_dimension/compute_distances.py ran MIT (permissive) · 4a6302d7905ab810 · report fixture: signature model:callable/0/?, dataloader:list/1/dict, target_layers:list/1/str · returned tuple · level recorded 2026-09-24
get_intersection src/zigzag/utils/fclaux.py ran MIT (permissive) · d925e138f4a79f89 · report fixture: signature list1:ndarray/2/int, list2:ndarray/2/int · returned ndarray · level recorded 2026-09-24
get_isin src/zigzag/utils/fclaux.py ran · violated contract MIT (permissive) · 29437b95d5fb999a · report fixture: signature list1:list/1/list, list2:list/1/list · returned ndarray · level recorded 2026-09-24
iord src/zigzag/run_fast_zigzag.py ran · honoured contract fingerprinted MIT (permissive) · e0c72a9bd230cf23 · report fixture: signature c:str/0/str · returned int · level recorded, date not recorded
layers_to_cut_given_r src/benchmark/benchmark.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted MIT (permissive) · ed4aa8002a88c246 · report fixture: signature r:list/1/float, p:float/0/float, layer_norm_added:bool/0/bool · returned list · level recorded, date not recorded
similarity_persistance src/benchmark/benchmark.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · b063c470e47070c8 · report fixture: signature betti:ndarray/1/int, ph_sim_betti:ndarray/2/float · returned ndarray · level recorded, date not recorded
read_pd_from_csv src/benchmark/post_process.py unverified MIT (permissive) · 5df05607e799aec8 · report

Tasks

Decision MakingTopological Data Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections