Papers › Revisiting Semi-Supervised Learning with Graph Embeddings

Revisiting Semi-Supervised Learning with Graph Embeddings

29 Mar 2016arXiv:1603.08861archive 2025-07-28

Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov

We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. On a large and diverse set of benchmark tasks, including text classification, distantly supervised entity extraction, and entity classification, we show improved performance over many of the existing models.

PaperPDFCodeCode Syntology ranMethod as code

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 28 code samples harvested from 10 repositories linked to this paper: 15 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 28 samples from 10 repositories, 15 ran (13 with no instrument failure; 2 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 15 samples that ran has no recorded date.

26 repositories listed; official and paper-mentioned ones first.

BingYu94860/HGNN-Node-Classification mentioned on GitHubtfSyntology: not harvested report
DeepGraphLearning/GMNN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GMNN: Graph Markov Neural Networks (arXiv:1905.06214; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Maysir/GRCN mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
ZhuangCY/Coding-NN mentioned on GitHubSyntology: not harvested report
ZhuangCY/DGCN mentioned on GitHubSyntology: not harvested report
agiresearch/InstructGLM mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Language is All a Graph Needs (arXiv:2308.07134; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ajbisberg/gcn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (arXiv:1606.09375; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
asarigun/la-gcn-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
asarigun/la-gcn-tensorflow mentioned on GitHubtfMITSyntology: 9 samples, 5 ran (1 instrument-failed) · 4 unverified report
asarigun/nfc mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
asarigun/nfc-gcn mentioned on GitHubtfSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
bepping/non-oversmoothing-gcns mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Classification with Graph Convolutional Networks (arXiv:1609.02907; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 34 with no instrument failure: 0 honoured, 1 violated, 33 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified); nothing checks that they implement this paper's method. report
dfdazac/dgi mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Graph Infomax (arXiv:1809.10341; that paper's own run record: 26 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
firojalam/domain-adaptation mentioned on GitHubtfSyntology: not harvested report
iMoonLab/DHGNN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
jiangboahu/glcn-tf mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Classification with Graph Convolutional Networks (arXiv:1609.02907; that paper's own run record: 39 ran (of which 13 constructed an object rather than computing a result; 34 with no instrument failure: 0 honoured, 1 violated, 33 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified); nothing checks that they implement this paper's method. report
kimiyoung/planetoid mentioned on GitHubMITSyntology: not harvested report
meliketoy/graph-cnn.pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mipot101/GNM-Implementations mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
plusross/grcn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Graph-Revised Convolutional Network (arXiv:1911.07123; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tkipf/gcn mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs (arXiv:2006.11468; that paper's own run record: 16 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
tkipf/ica mentioned on GitHubSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
venomouscyanide/S3GRL_OGB mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
venomouscyanide/s3grl mentioned on GitHubpytorchSyntology: not harvested report
venomouscyanide/s3grl_ogb mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
wokas36/DFNets mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters (arXiv:1910.10866; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

28 samples harvested: 15 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
8ran
13unverified

Licence: 11 of the 28 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 10 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Maysir/GRCN community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
GCNConv_dense models/GRCN.py ran MIT (permissive) · ec355dcbf751cc7a · report fixture: signature input:Tensor/2/float, A:Tensor/2/float, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-24
GCNConv_diag models/GRCN.py ran MIT (permissive) · 270166c76b26a9ee · report fixture: signature input:Tensor/2/float, A:Tensor/2/float, sparse:bool/0/bool · returned Tensor · level recorded 2026-09-24
Model in 227 papers models/GRCN.py ran MIT (permissive) · bcdba8daf230043b · report fixture: returned Model · level recorded 2026-09-22
asarigun/la-gcn-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
GCN_MASK models.py unverified MIT (permissive) · 05d312950dfb243b · report
asarigun/la-gcn-tensorflow community (archive-listed) 9 samples, 5 ran (1 instrument-failed) · 4 unverified
dot in 68 papers layers.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · bc3a2072a2a9cca3 · report fixture: signature x:EagerTensor/2/float, y:EagerTensor/2/float, sparse:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
get_layer_uid in 30 papers layers.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · b82968db452628fd · report fixture: signature layer_name:str/0/str · returned int · level recorded 2026-09-22
parse_index_file in 54 papers utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · c1d6392f89c5e495 · report fixture: signature filename:str/0/str · returned list · level recorded, date not recorded
sample_mask in 39 papers
census: 4 implementations from 5 papers, 4 distinct outputs on one shared input
utils.py ran · violated contract fingerprinted MIT (permissive) · b32fd748b4bbe3bf · report fixture: signature idx:int/0/int, l:int/0/int · returned ndarray · level recorded 2026-09-22
zeros in 26 papers inits.py ran MIT (permissive) here; the stored copy is pointer only · b190ef9c60b2629a · report fixture: signature shape:tuple/1/int, name:str/0/str · returned ResourceVariable · level recorded 2026-09-24
glorot in 26 papers inits.py unverified MIT (permissive) here; the stored copy is pointer only · 1b491f3f784b7cb0 · report
load_data in 700 papers utils.py unverified MIT (permissive) · 73af867b964476a6 · report
sparse_dropout in 30 papers layers.py unverified MIT (permissive) here; the stored copy is pointer only · 81be8a5f4732fe52 · report
uniform in 58 papers inits.py unverified MIT (permissive) here; the stored copy is pointer only · b0d1b78daecde7e9 · report
asarigun/nfc community (archive-listed) 1 sample, 0 ran · 1 unverified
load_data in 700 papers utils.py unverified MIT (permissive) · ae7971ec194c0050 · report
asarigun/nfc-gcn community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
Model in 227 papers models.py ran MIT (permissive) · 79092f3060750964 · report fixture: returned Model · level recorded 2026-09-22
masked_accuracy in 14 papers models.py ran · violated contract MIT (permissive) · b89d4728d3c8578d · report fixture: signature preds:EagerTensor/2/float, labels:EagerTensor/2/float, mask:EagerTensor/1/int · returned EagerTensor · level recorded 2026-09-22
masked_softmax_cross_entropy in 11 papers models.py ran · honoured contract MIT (permissive) · d103f29cc58337a2 · report fixture: signature preds:EagerTensor/2/float, labels:EagerTensor/2/float, mask:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-22
GCN in 41 papers models.py unverified MIT (permissive) · 0da98822521f5a66 · report
iMoonLab/DHGNN community (archive-listed) 1 sample, 0 ran · 1 unverified
DHGNN_v1 models/models.py unverified MIT (permissive) · 1aded806aefeb35f · report
meliketoy/graph-cnn.pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GCN in 41 papers models.py ran · metamorphic tier: deterministic MIT (permissive) · f224b63a7a7463d9 · report fixture: returned GCN · level recorded 2026-09-22
GraphConvolution in 36 papers models.py ran MIT (permissive) · ff277e8dd110b334 · report fixture: returned Tensor · level recorded 2026-09-24
mipot101/GNM-Implementations community (archive-listed) 3 samples, 0 ran · 3 unverified
train_modelr GNM_Toolbox/gnm.py unverified no licence file found · pointer only · 2d1711104178d07b · report
train_modely GNM_Toolbox/gnm.py unverified no licence file found · pointer only · 7744934903a62303 · report
train_net_with_gnm GNM_Toolbox/gnm.py unverified no licence file found · pointer only · 560fe1ad9ba4b948 · report
tkipf/ica community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
ICA ica/classifiers.py ran MIT (permissive) · bf9e124488a3ad49 · report fixture: returned ICA · level recorded 2026-09-22
get_class in 12 papers ica/classifiers.py ran · our draft was wrong MIT (permissive) · b8337cff1a162df4 · report fixture: signature kls:str/0/str · returned type · level recorded 2026-09-22
Classifier in 72 papers ica/classifiers.py unverified MIT (permissive) · c3f22105f96e8f5a · report
venomouscyanide/S3GRL_OGB community (archive-listed) 1 sample, 0 ran · 1 unverified
S3GRLLight models.py unverified no licence file found · pointer only · e6be015d5b6f544a · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

8 sibling assemblies for semi-supervised learning framework based on graph embeddings (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. GCN entry · level 1 · ran · f224b63a7a7463d9
  2. GraphConvolution model · level 1 · ran · ff277e8dd110b334

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. ICA entry · level 1 · ran · bf9e124488a3ad49
  2. Classifier helper · level 0 · unverified · c3f22105f96e8f5a
  3. get_class helper · level 1 · ran · our draft was wrong · b8337cff1a162df4

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. train_net_with_gnm entry · level 0 · unverified · 560fe1ad9ba4b948
  2. train_modelr model · level 0 · unverified · 2d1711104178d07b
  3. train_modely model · level 0 · unverified · 7744934903a62303

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. GCN_MASK entry · level 0 · unverified · 05d312950dfb243b

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 3 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Model entry · level 1 · ran · bcdba8daf230043b
  2. GCNConv_dense model · level 1 · ran · ec355dcbf751cc7a
  3. GCNConv_diag model · level 1 · ran · 270166c76b26a9ee

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 4 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. GCN entry · level 0 · unverified · 0da98822521f5a66
  2. Model helper · level 1 · ran · 79092f3060750964
  3. masked_accuracy helper · level 1 · ran · violated contract · b89d4728d3c8578d
  4. masked_softmax_cross_entropy helper · level 1 · ran · honoured contract · d103f29cc58337a2

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. DHGNN_v1 entry · level 0 · unverified · 1aded806aefeb35f

harvested Assembly for semi-supervised learning framework based on graph embeddings (graph method: semi-supervised learning framework based on graph embeddings). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. S3GRLLight entry · level 0 · unverified · e6be015d5b6f544a

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1603.08861") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document ClassificationEntity Extraction using GANGeneral ClassificationNode ClassificationText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Classification Cora Planetoid* Accuracy 75.7% #5 of 6 Archive leaderboard report
Node Classification Citeseer Planetoid* Accuracy 64.7% #65 of 71 Archive leaderboard report
Node Classification Cora Planetoid* Accuracy 75.7% #70 of 73 Archive leaderboard report
Node Classification NELL Planetoid* Accuracy 61.9% #4 of 4 Archive leaderboard report
Node Classification Pubmed Planetoid* Accuracy 77.2% #61 of 70 Archive leaderboard report
Node Classification USA Air-Traffic Planetoid* Accuracy 64.7 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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