phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | modeling quantum interactions in molecules— “We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules.” | |
| claim-type | method— “Thus, we propose to use continuousfilter convolutional layers to be able to model local correlations without requiring the data to lie on a grid.” | |
| method — evidence | — “We propose SchNet: a neural network specifically designed to respect essential quantumchemical constraints.” | |
| transfer | from artificial intelligence (deep learning): deep convolutional neural networks applied to model quantum interactions in molecules— “Deep learning has the potential to revolutionize quantum chemistry” | transfers[0] |
| mechanism | continuous-filter convolutions over continuous atom positions (not a grid), preserving the physical information in molecular geometry— “their precise locations contain essential physical information, that would get lost if discretized” | mechanisms[0] |
| extends | grid-based convolutional neural networks— “the atoms in molecules are not restricted to a grid” | claim_relations[0] |
| extends | dynamic filter networks [34]— “While dynamic filter networks generate weights restricted to a grid structure, our approach generalizes this to arbitrary position and number of objects.” | claim_relations[1] |
| extends | deep tensor neural networks (DTNN), Schütt et al. [20]— “Even though the DTNN shares the invariances with our proposed architecture, its interaction layers lack the continuous-filter convolution interpretation.” | claim_relations[2] |
| builds-on | gradient-domain machine learning (GDML), Chmiela et al. [19]— “Chmiela et al. [19] pointed out that this leads to an energy-conserving force-field by construction.” | claim_relations[3] |
| builds-on | ResNet [36] residual connections— “The blocks use a residual connection inspired by ResNet [36]:” | claim_relations[4] |
| sense | the invariances - BY CONSTRUCTION, not measured: rotational equivariance of the forces follows from rotational invariance of the energy plus the architecture, so it is a guarantee rather than an empirical result, and must not be compared with a model's measured conservation— “As SchNet yields rotationally invariant energy predictions, the force predictions are rotationally equivariant by construction” | senses[0] |
| sense | QM9 - AS A BENCHMARK OF THE SPECIAL CASE: equilibrium molecules only, which is precisely where the forces vanish, so the benchmark omits the regime the architecture was built for— “Models such as circular fingerprints [17], molecular graph convolutions or message-passing neural networks[21] for property prediction across chemical compound space are only concerned with equilibrium molecules, i.e., the special case where the forces are vanishing” | senses[1] |
| sense | the filter - CONTINUOUS RATHER THAN DISCRETE, because atom positions do not lie on a grid and their precise locations carry physical information that discretising destroys— “Instead, their precise locations contain essential physical information, that would get lost if discretized” | senses[2] |
| control | comparison of force and energy prediction against a mean predictor as a baseline, on held-out MD trajectories — held— “Table 3: Mean absolute errors on C7O2H10 isomers in kcal/mol.” — rules out that SchNet's reported accuracy could be obtained by predicting the dataset mean, and that it comes from memorising conformations rather than generalising— “We predict forces and energies in both cases and compare to the mean predictor as a baseline.” | controls[0] |
| audit | continuous-filter convolution —causes→ potential energy surface — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span writes 'continuous-filter convolutional layers', not 'continuous-filter convolution'.— “In contrast, SchNet does not use such features and yields a continuous potential energy surface by using continuous-filter convolutional layers” | concept_edges[0] |
| relation | continuous-filter convolution —causes→ potential energy surface — the continuous-filter layers are what YIELD a continuous energy surface— “In contrast, SchNet does not use such features and yields a continuous potential energy surface by using continuous-filter convolutional layers”— “yields a continuous potential energy surface by using continuous-filter convolutional layers” | concept_edges[0] |
| audit | interatomic forces —operationalised-as→ molecular energy — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says forces are RELATED to energy and obtained by differentiating it; operationalised-as is loose.— “As described above, the interatomic forces are related to the molecular energy, so that we can obtain an energy-conserving force model by differentiating the energy model” | concept_edges[1] |
| outcome | control — held— “We predict forces and energies in both cases and compare to the mean predictor as a… | controls[0] |
| for which use | limitation — any claim of coverage over chemical space: THE VASTNESS OF CHEMICAL COMPOUND SPACE AND THE COMPUTATIONAL COST OF ACCURATE QUANTUM-CHEMICAL CALCULATIONS PREVENT AN EXHAUSTIVE [exploration] | limitations[0] |
| for which use | limitation — the reported architecture choices: AN EXTENSIVE EVALUATION OF THE IMPACT OF THESE VARIABLES IS LEFT FOR FUTURE WORK | limitations[1] |
| for which use | limitation — the force-training results, which are not free: WE EXPECT TO SEE IMPROVED GENERALIZATION, HOWEVER, AT A COMPUTATIONAL COST | limitations[2] |
| for which use | limitation — the ISO17 benchmark result: WHILE WE ACHIEVE PROMISING RESULTS ON THIS NEW BENCHMARK, MODELING CHEMICAL AND CONFORMATIONAL VARIATIONS REMAINS DIFFICULT AND NEEDS FURTHER IMPROVEMENT Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| for which use | limitation — a comparison of this model against circular fingerprints, graph convolutions or message-passing networks on forces: those methods cannot be trained with forces at all, because discrete binning or one-hot bond types put discontinuities in their potential energy surface Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| for which use | limitation — a QM9 result as evidence about force prediction: QM9 holds only equilibrium molecules, so the forces there are zero by definition and are not predicted at all Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| for which use | limitation — GDML as a baseline: its kernel matrix grows quadratically in both the number of atoms and the number of examples, and it is stated elsewhere in the paper that it cannot be used for the molecular-dynamics predictions Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
| replication | untested | |
| limitation | chemical compound space is vast and accurate quantum calculations are costly, preventing exhaustive exploration Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[0] |
| limitation | The radial-basis filter parameters (number and range of centres) were not systematically studied. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[1] |
| limitation | Training on forces roughly doubles the computational cost, because forces require a full forward and backward pass through the energy model. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[2] |
| limitation | Performance on the new ISO17 benchmark, which combines chemical and conformational variation, is only promising rather than solved. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| limitation | A whole class of competing methods is excluded from force training by its REPRESENTATION - discrete binning and one-hot bond types - which makes their energy surface discontinuous. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| limitation | The main benchmark contains only equilibrium molecules, where the force term the paper exists to predict is zero by definition. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| limitation | A named competitor is ruled out of one benchmark entirely, and its scaling behaviour is given as quadratic in both atoms and examples. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | SchNet yields a joint model of total energy and interatomic forces that follows fundamental quantum-chemical principles. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[0] |
| evidence status note | finding — QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. | content_tags.findings[0] |
| finding | SchNet delivers rotationally invariant energy predictions and rotationally equivariant force predictions. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[1] |
| quantity | three quantum-chemistry datasets — benchmark datasets used (QM9, MD17, ISO17) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[0] |
| variable | total energy (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[2] |
| variable | interatomic forces (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[3] |
| definition | continuous-filter convolutional layer Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[0] |
| evidence status note | definition — QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. | content_tags.definitions[0] |
| definition | potential energy surface Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[1] |
| key-terms | molecules, atoms, energy, quantum, convolutional, forces, chemical, interatomic, continuous-filter |
| concept | continuous-filter convolution Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[4] |
| concept | potential energy surface Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[5] |
| concept | interatomic forces Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[6] |
| concept | molecular energy Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[7] |
| concept | rotational invariance Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[8] |
| concept | QM9 Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[9] |
When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824