Configuration

Molecular GNN, SMILES implementation (ATOM3D baseline)

Two-dimensional graph neural network on the chemical bond graph, as the ATOM3D text describes it.

Identified as Molecular GNN of Tsubaki et al.. The source table prints [Tsubaki et al., 2019].

Configuration: 2D baseline for SMP using the SMILES-only implementation in masashitsubaki/molecularGNN_smiles.

ATOM3D App. F.1 chooses 'molecular GNNs [Tsubaki et al., 2019]' and uses 'an implementation that only uses the SMILES representation', linking masashitsubaki/molecularGNN_smiles. The repository describes a GNN over r-radius subgraphs from the authors' Bioinformatics paper. The method has no product name, so the display name is descriptive.

Input: SMILES representation of the molecular graph only.

Not established: Checkpoint and settings. No hyperparameters, checkpoint or implementation revision are identified.

ATOM3D: Tasks On Molecules in Three Dimensions; Molecular GNN, SMILES implementation README (masashitsubaki/molecularGNN_smiles) · ATOM3D arXiv:2012.04035v4 §5.1 and Table 3, p.7; App. F.1 with footnote 7, p.23; Table 8 SMP rows, p.28. github.com/masashitsubaki/molecularGNN_smiles README at 0fdd327ef4c0278e86619c370101706e5c6c506f.. AI-assisted source review on 2026-09-24; no human scientific review.

3 evaluations · 3 results

Overview

Two-dimensional graph neural network on the chemical bond graph, as the ATOM3D text describes it.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

3 evaluations · 3 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Molecular GNN, SMILES implementation (ATOM3D baseline) (cited as [Tsubaki et al., 2019])	Task: ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap Dataset subset: ATOM3D SMP (ATOM3D split)	0.154 mae error · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Molecular GNN, SMILES implementation (ATOM3D baseline) on ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(SMP εgap [eV]), column([Tsubaki et al., 2019])
Configuration: Molecular GNN, SMILES implementation (ATOM3D baseline) (cited as [Tsubaki et al., 2019])	Task: ATOM3D SMP-MU: Small molecule properties, dipole moment Dataset subset: ATOM3D SMP (ATOM3D split)	0.496 mae error · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Molecular GNN, SMILES implementation (ATOM3D baseline) on ATOM3D SMP-MU: Small molecule properties, dipole moment Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(µ [D]), column([Tsubaki et al., 2019])
Configuration: Molecular GNN, SMILES implementation (ATOM3D baseline) (cited as [Tsubaki et al., 2019])	Task: ATOM3D SMP-U0AT: Small molecule properties, atomization energy Dataset subset: ATOM3D SMP (ATOM3D split)	0.182 mae error · lower Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Molecular GNN, SMILES implementation (ATOM3D baseline) on ATOM3D SMP-U0AT: Small molecule properties, atomization energy Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(U0at [eV]), column([Tsubaki et al., 2019])

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Use this model

How it works, versions and access

Strengths, limitations and unresolved questions

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

2 source records and release history

ATOM3D: Tasks On Molecules in Three Dimensions · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Molecular GNN, SMILES implementation README (masashitsubaki/molecularGNN_smiles) · Original source · 0fdd327ef4c0278e86619c370101706e5c6c506f

Download this release

Technical metadata and extraction receipts

Stable ID: atom3d-method-tsubaki-et-al-2019

areas: molecular-interactions
source locator: Table 3, column([Tsubaki et al., 2019])
missing metadata: checkpoint revision: unreported; parameters: unextracted
source label: [Tsubaki et al., 2019]
source identity: status: resolved; label form: bracketed_citation; display name: Molecular GNN, SMILES implementation (ATOM3D baseline); identity: Molecular GNN of Tsubaki et al.; configuration: 2D baseline for SMP using the SMILES-only implementation in masashitsubaki/molecularGNN_smiles.; basis: ATOM3D App. F.1 chooses 'molecular GNNs [Tsubaki et al., 2019]' and uses 'an implementation that only uses the SMILES representation', linking masashitsubaki/molecularGNN_smiles. The repository describes a GNN over r-radius subgraphs from the authors' Bioinformatics paper. The method has no product name, so the display name is descriptive.; source ids: evidence-expansion-atom3d-92656c20; source-label-molecular-gnn-readme-0fdd327e; source locator: ATOM3D arXiv:2012.04035v4 §5.1 and Table 3, p.7; App. F.1 with footnote 7, p.23; Table 8 SMP rows, p.28. github.com/masashitsubaki/molecularGNN_smiles README at 0fdd327ef4c0278e86619c370101706e5c6c506f.; known details: label: Input; value: SMILES representation of the molecular graph only.; source ids: evidence-expansion-atom3d-92656c20; source locator: ATOM3D App. F.1, p.23; unknown: label: Checkpoint and settings; note: No hyperparameters, checkpoint or implementation revision are identified.; original name: [Tsubaki et al., 2019]; original description: Two-dimensional graph neural network on the chemical bond graph, as the ATOM3D text describes it.; review: method: automated_source_review; date: 2026-09-24; note: AI-assisted review against the cited primary sources. No human scientific review. Values, locators and comparison conditions are unchanged.

Related records

Suggest a correction