Papers › Equivariant message passing for the prediction of tensorial properties and molecular spectra

Equivariant message passing for the prediction of tensorial properties and molecular spectra

5 Feb 2021arXiv:2102.03150archive 2025-07-28

Kristof T. Schütt, Oliver T. Unke, Michael Gastegger

Message passing neural networks have become a method of choice for learning on graphs, in particular the prediction of chemical properties and the acceleration of molecular dynamics studies. While they readily scale to large training data sets, previous approaches have proven to be less data efficient than kernel methods. We identify limitations of invariant representations as a major reason and extend the message passing formulation to rotationally equivariant representations. On this basis, we propose the polarizable atom interaction neural network (PaiNN) and improve on common molecule benchmarks over previous networks, while reducing model size and inference time. We leverage the equivariant atomwise representations obtained by PaiNN for the prediction of tensorial properties. Finally, we apply this to the simulation of molecular spectra, achieving speedups of 4-5 orders of magnitude compared to the electronic structure reference.

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 33 code samples harvested from 1 repository linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 8 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): 33 samples from 1 repository, 22 ran (13 with no instrument failure; 9 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 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.

learningmatter-mit/NeuralForceField mentioned on GitHubpytorchSyntology: 33 samples, 22 ran (9 instrument-failed) · 11 unverified report
gerkone/painn-jax jaxSyntology: not harvested 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

33 samples harvested: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 11 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.

2ran · honoured contract
8ran · our draft was wrong
1ran; the contract check could not run
11ran
11unverified

Licence: 0 of the 33 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 learningmatter-mit/NeuralForceField. “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.

learningmatter-mit/NeuralForceField community (archive-listed) 33 samples, 22 ran (9 instrument-failed) · 11 unverified
CosineEnvelope nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 8ac6bce450fc85e3 · report fixture: signature d:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Dense in 22 papers nff/nn/models/painn.py ran · metamorphic tier: invariant MIT (permissive) · dc349a5755ad2883 · report fixture: signature inputs:Tensor/2/float · returned Tensor · level recorded 2026-09-22
DistanceEmbed nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 6af9e88a6c54be01 · report fixture: signature dist:Tensor/1/float · returned Tensor · level recorded 2026-09-22
EmbeddingBlock nff/nn/models/painn.py ran · metamorphic tier: deterministic MIT (permissive) · 952ca748b3f1516e · report fixture: signature z_number:Tensor/1/int · returned tuple · level recorded 2026-09-22
InvariantDense nff/nn/models/painn.py ran · metamorphic tier: invariant MIT (permissive) · 7f75d01bd99cc6dd · report fixture: signature s_j:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnableSwish nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 0d21a7509e419d0b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MolFpPool nff/nn/models/painn.py ran MIT (permissive) · 398bfbf43b702ff8 · report fixture: signature batch:dict/0/?, xyz:Tensor/2/float, atomwise_output:dict/0/?, grad_keys:list/1/empty, out_keys:list/1/str · returned dict · level recorded 2026-09-24
PainnRadialBasis nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · b65822c621376024 · report fixture: signature dist:Tensor/1/float · returned Tensor · level recorded 2026-09-22
ScaleShift nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 802d844e902371ef · report fixture: signature inp:Tensor/2/float, key:str/0/str · returned Tensor · level recorded 2026-09-22
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 7f836403bedf830d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
add_embedding nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · 5cfab56ad64af6fe · report fixture: signature atomwise_out:dict/0/?, all_results:dict/0/? · returned dict · level recorded 2026-09-24
att_readout_probs nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · 2eece0db59be49c0 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-22
compute_grad in 10 papers nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · 2ac65d5ac1bf4b38 · report fixture: signature inputs:Tensor/2/float, output:Tensor/0/float, allow_unused:bool/0/bool · returned Tensor · level recorded 2026-09-22
gen in 18 papers nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · 07fc732b54bba7cd · report fixture: signature src:Tensor/2/float, index:Tensor/1/int, dim:int/0/int, out:NoneType/0/?, dim_size:NoneType/0/?, fill_value:int/0/int · returned tuple · level recorded 2026-09-24
get_offsets nff/nn/models/painn.py ran · honoured contract MIT (permissive) · 18fd70ccb86319a7 · report fixture: signature batch:dict/0/?, key:str/0/str · returned Tensor · level recorded 2026-09-24
get_rij nff/nn/models/painn.py ran; the contract check could not run (RAISES) MIT (permissive) · 2cfb01eec4fba085 · report fixture: signature xyz:Tensor/2/float, batch:dict/0/?, nbrs:Tensor/2/int, cutoff:Tensor/0/float · returned tuple · level recorded 2026-09-24
make_directed nff/nn/models/painn.py ran · our draft was wrong fingerprinted MIT (permissive) · 3e1aa28156810aba · report fixture: signature nbr_list:Tensor/2/int · returned tuple · level recorded 2026-09-22
norm in 120 papers
census: 23 implementations from 26 papers, 15 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 2, kind float, dtype float32
nff/nn/models/painn.py ran · honoured contract fingerprinted MIT (permissive) · 3df02af32c33da5a · report fixture: signature vec:Tensor/2/float · returned Tensor · level recorded 2026-09-22
preprocess_r nff/nn/models/painn.py ran · our draft was wrong fingerprinted MIT (permissive) · 6565f4a40973667d · report fixture: signature r_ij:Tensor/2/float · returned tuple · level recorded 2026-09-22
scatter_add in 10 papers nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · 04e4a832f331db07 · report fixture: signature src:Tensor/2/float, index:Tensor/1/int, dim:int/0/int, out:NoneType/0/?, dim_size:NoneType/0/?, fill_value:int/0/int · returned Tensor · level recorded 2026-09-24
shifted_softplus in 7 papers nff/nn/models/painn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 42c43fca053545ea · report fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
to_module nff/nn/models/painn.py ran · our draft was wrong MIT (permissive) · a929e9679ef4134f · report fixture: signature activation:str/0/str · returned Swish · level recorded 2026-09-22
AttentionPool nff/nn/models/painn.py unverified MIT (permissive) · 55d8c70e377b4a86 · report
InvariantMessage nff/nn/models/painn.py unverified MIT (permissive) · f09c070242efedbf · report
MeanPool nff/nn/models/painn.py unverified MIT (permissive) · 670901a6573e1934 · report
MessageBase nff/nn/models/painn.py unverified MIT (permissive) · 573a7b800820d725 · report
MessageBlock nff/nn/models/painn.py unverified MIT (permissive) · 9f1980fc08094e16 · report
Painn nff/nn/models/painn.py unverified MIT (permissive) · 450568a63ba4bedb · report
ReadoutBlock nff/nn/models/painn.py unverified MIT (permissive) · 05495644c9588ed2 · report
SumPool nff/nn/models/painn.py unverified MIT (permissive) · 4b3ac9cd9d28db18 · report
UpdateBlock nff/nn/models/painn.py unverified MIT (permissive) · 1418df20e13d6afe · report
add_stress nff/nn/models/painn.py unverified MIT (permissive) · d31febe9a5aa1b51 · report
sum_and_grad nff/nn/models/painn.py unverified MIT (permissive) · 5d9228f747be613d · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for PaiNN (graph method: PaiNN). 33 bricks; individually on a fixture: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 9 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. Painn entry · level 0 · unverified · 450568a63ba4bedb
  2. EmbeddingBlock model · level 1 · ran · 952ca748b3f1516e
  3. MessageBlock model · level 0 · unverified · 9f1980fc08094e16
  4. ReadoutBlock model · level 0 · unverified · 05495644c9588ed2
  5. SumPool helper · level 0 · unverified · 4b3ac9cd9d28db18
  6. UpdateBlock model · level 0 · unverified · 1418df20e13d6afe
  7. add_embedding helper · level 1 · ran · our draft was wrong · 5cfab56ad64af6fe
  8. add_stress helper · level 0 · unverified · d31febe9a5aa1b51
  9. get_rij helper · level 1 · ran; the contract check could not run (RAISES) · 2cfb01eec4fba085
  10. make_directed helper · level 1 · ran · our draft was wrong · 3e1aa28156810aba
  11. scatter_add helper · level 1 · ran · our draft was wrong · 04e4a832f331db07
  12. InvariantMessage model · level 0 · unverified · f09c070242efedbf
  13. MessageBase helper · level 0 · unverified · 573a7b800820d725
  14. preprocess_r helper · level 1 · ran · our draft was wrong · 6565f4a40973667d
  15. Dense helper · level 1 · ran · dc349a5755ad2883
  16. ScaleShift helper · level 1 · ran · 802d844e902371ef
  17. to_module helper · level 1 · ran · our draft was wrong · a929e9679ef4134f
  18. sum_and_grad helper · level 0 · unverified · 5d9228f747be613d
  19. norm helper · level 1 · ran · honoured contract · 3df02af32c33da5a
  20. compute_grad helper · level 1 · ran · our draft was wrong · 2ac65d5ac1bf4b38
  21. get_offsets helper · level 1 · ran · honoured contract · 18fd70ccb86319a7
  22. gen helper · level 1 · ran · our draft was wrong · 07fc732b54bba7cd
  23. DistanceEmbed model · level 1 · ran · 6af9e88a6c54be01
  24. InvariantDense model · level 1 · ran · 7f75d01bd99cc6dd
  25. CosineEnvelope helper · level 1 · ran · 8ac6bce450fc85e3
  26. PainnRadialBasis helper · level 1 · ran · b65822c621376024
  27. AttentionPool helper · level 0 · unverified · 55d8c70e377b4a86
  28. LearnableSwish helper · level 1 · ran · 0d21a7509e419d0b
  29. MeanPool helper · level 0 · unverified · 670901a6573e1934
  30. MolFpPool helper · level 1 · ran · 398bfbf43b702ff8
  31. Swish helper · level 1 · ran · 7f836403bedf830d
  32. att_readout_probs helper · level 1 · ran · our draft was wrong · 2eece0db59be49c0
  33. shifted_softplus helper · level 1 · ran · 42c43fca053545ea

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="2102.03150") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Drug Discovery

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Drug Discovery QM9 PaiNN Error ratio 0.411 #6 of 11 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