- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 3(+1)
- Presentation
- 2
- Soundness
- 3(+1)
Read review
Paper summary
The paper proposes VINEA, a spectral representation for structure elucidation that replaces dense intensity grids or thresholded peak lists by a set of H0 persistent branches. For 1D spectra (¹H NMR, Raman, IR) each local maximum of the signed, shifted signal becomes a branch with birth, death and persistence (equal to topographic prominence in 1D), decorated with position, area, widths at three relative heights, asymmetry and neighbour spacings; for HSQC, connected cross-peak regions play the same role. Each branch is followed across a Gaussian scale-space ladder (a persistence vineyard) to obtain a relative-persistence profile and a scale-death statistic. Up to 128 branches with the highest persistence are encoded by a two-block set transformer with Fourier position features, persistence-weighted embeddings and a translation-invariant relative-position attention bias (about 0.6M parameters). The paper also introduces a synthetic corruption benchmark with five severities for four modalities and compares VINEA with 15 retrained published encoders over ten seeds, in clean-trained and corruption-aware (S1–S3 ramp) regimes, plus zero-shot and fine-tuned transfer to measured spectra, field-strength transfer on GISSMO, and architecture ablations.
Critical strengths
-
A broad, carefully controlled multi-modality robustness benchmark. Four modalities, five calibrated severity levels, 15 retrained published encoders plus internal controls, ten seeds, and corruptions that are byte-identical across models for each item (Appendix H.1) make the comparisons paired and reproducible. Under corruption-aware training, VINEA has clear and statistically convincing margins on several tasks: ¹H NMR S3 Recall@1 0.583 ± 0.022 vs 0.446 for NMRViT, HSQC 0.109 vs 0.023, and IR S5 macro-AUROC 0.780 vs 0.712 (Table 12), with an order of magnitude fewer parameters than most baselines. The benchmark itself is a useful resource.
-
Thorough and fairly candid reporting. The appendix reports results that do not favour the method — zero-shot transfer to measured spectra (Tables 13–14), single-artifact retention (Table 10) and latency (Table 15) — and includes an informative negative control: shuffling the association between branch position and the other descriptors reduces MRR-AUDC from 0.533 to 0.126 (Table 16), showing that the model relies on which morphology occurs at which chemical shift.
Critical weaknesses
1. The central claim that the topological representation is robust to real acquisition artifacts is not supported outside the authors' own synthetic corruptions.
- Zero-shot transfer to measured ¹H NMR (Table 13, ramp pretraining). VINEA obtains 0.068 / 0.047 / 0.201 / 0.221 Recall@1 on Chemotion / BMRB / GISSMO / NMRXiv, versus 0.173 / 0.106 / 0.278 / 0.327 for NMR2Struct and 0.144 / 0.125 / 0.283 / 0.303 for NMRViT; it beats only SECS. With clean pretraining it is also below NMR2Struct (e.g., 0.021 vs 0.037 on Chemotion). On measured HSQC (Table 14) VINEA-HSQC is near chance (0.020 vs 0.010 random), while SPECTRE reaches 0.097; on measured IR it is below ACT and UltraIR (0.684 vs 0.692). Only Raman favours VINEA (0.095 vs 0.090, s.d. 0.031). This contradicts the contribution "compact robustness that transfers beyond simulation" (l. 103–107), and the abstract mentions only fine-tuned results.
- The representation alone does not suppress noise. In Table 10, clean-trained VINEA retains only 1.6% (¹H) and 1.2% (HSQC) of its clean performance under thermal noise at S3, 6.1% under ¹H shimming and 5.6% under Raman shot noise, despite the abstract's claim of suppressing transient noise (l. 017–018). Robustness appears mainly after corruption-aware training, which improves all architectures (l. 424). The clean-trained "7–16×" advantage on ¹H (l. 104–105, 390–391) is a ratio between near-chance values (chance 5.4×10⁻⁵).
- Co-designed benchmark, unprocessed baselines. The signed filtration, the persistence normalization and the translation-invariant attention target the phase, baseline and referencing corruptions of the same benchmark, whereas dense baselines receive corrupted inputs before any model-specific preprocessing (l. 373–374) and without standard baseline correction, phasing or denoising.
- Fine-tuning claims lack statistics. The differences in §5.2 (0.382 vs 0.375 on ¹H, 0.336 vs 0.332 on HSQC) are shown only in Fig. 5a. l. 442 refers to Tables 13 and 14 for the fine-tuning result, but those tables contain only zero-shot numbers.
2. The experiments do not isolate what persistent homology and vineyards contribute, and the ablation study is incomplete and inconsistent with the main results.
- No peak-list baseline. The paper frames its contribution against dense grids and peak lists (l. 071–078) and discusses NMRTrans / NMR-Text (l. 118–124), yet all ¹H baselines are dense or patch encoders (Table 8); NMRTrans, NMR-Text and UltraNMR appear only in the learning-rate list (l. 2705–2707). Since 1D persistence equals topographic prominence (l. 161–162) and VINEA keeps the top-128 branches by persistence (Algorithm 1), the decisive control is the same set encoder on peaks from a standard prominence/width peak picker (optionally at several smoothing scales) with the same geometric descriptors. Without it, the gains cannot be attributed to the topological construction rather than to set encoding with relative-position attention.
- Interim three-seed ablations from a different protocol. Table 16 uses three seeds and is described as an "interim aggregate" to be treated as a trend until the remaining seeds are complete (l. 2594, 2611–2612, 2696–2698). In it, full VINEA has clean Recall@1 0.276 but S3 Recall@1 0.619 — better under corruption than clean — whereas Table 12 reports 0.778 (clean) and 0.583 (S3) for ramp-trained VINEA on the same pool, and Table 11 reports 0.859 for clean-trained VINEA. The ablation uses a different curriculum and checkpoint rule (l. 2416–2418), so its conclusions do not transfer to the reported model. The vineyard ablation ("− blur axis") changes MRR-AUDC by only −0.020 with standard deviations of about 0.015–0.018, so the title component is not shown to matter for robustness.
- Inconsistencies that affect fairness. Appendix G states that batch size (the InfoNCE negative pool) is 32 for every encoder and dataset (l. 2700–2701) but then lists VINEA batch sizes of 32/4/64/64 for ¹H/HSQC/Raman/IR (l. 2714–2716). Table 11's caption describes the Raman task as 5,056-candidate retrieval, Table 12's caption says Table 11 reports a pharmaceutical classification task, and Appendix E.10 says balanced accuracy is reported for Raman. The main text gives 0.588 for ¹H S3 (l. 425) while Table 12 gives 0.583. SPECTRE appears in the HSQC tables (0.381 clean, stronger than DeepSAT's 0.326) but is not among the described baselines, and l. 393–394 compares VINEA only with DeepSAT. Leftover text ("unequal n ... at the freeze date" although all n = 10, l. 2534–2535; "historical result key topo scalespace", l. 2355) suggests the appendix was not finalised. Finally, VINEA-HSQC needs 455 ms per spectrum versus 0.8–6 ms for the baselines (Table 15), so "compact" holds for parameters only.
Questions for authors
Clarifications that could change my assessment
- Please add the same set encoder trained on conventional peak lists (prominence/width-based peak picking, optionally at several smoothing scales, with the same geometric descriptors), and an NMRTrans-style peak-set baseline, under the same corruption protocol and seeds.
- Why does full VINEA in Table 16 reach only 0.276 clean Recall@1 while scoring 0.619 at S3, compared with 0.778/0.583 in Table 12? Please re-run the ablations under the main training protocol with all ten seeds.
- How do the dense baselines perform when given standard preprocessing (baseline correction, automatic phasing, smoothing) before encoding, both in the clean-trained setting and on measured spectra?
- Please provide a table of the fine-tuning results in Fig. 5a with standard deviations, candidate-pool sizes and paired tests.
- Which batch size (number of InfoNCE negatives) did each model use on each modality, and what hyper-parameter search budget did baselines receive compared with VINEA?
- What does Table 11 report for Raman (retrieval R@1 or classification BAcc)? What is SPECTRE, how was it trained, and why is it not in Table 8?
Suggestions (not required for my assessment)
- Analyse which real-data factors make VINEA worse than dense encoders in zero-shot ¹H transfer (e.g., solvent or impurity peaks, multiplet structure, the M = 128 token cap under noise), and report performance as a function of M under thermal noise.
- Report end-to-end throughput alongside parameter counts, and qualify "compact" accordingly.
11 comments
Response to Reviewer P3vK (Part 2)
How do the dense baselines perform when given standard preprocessing (baseline correction, automatic phasing, smoothing) before encoding, both in the clean-trained setting and on measured spectra?
Our experimental NMR/HSQC evaluations are made of processed spectra and not raw FIDs, and dense baselines and VINEA receive the same experimental inputs. We also retain preprocessing built into baseline implementations, including ACT’s baseline correction and UltraIR’s smoothing. Thus, the reported experimental results already include these existing processing steps. However, this does not replace a controlled preprocessing ablation: we have not separately quantified the benefit of adding baseline correction, automatic phasing, and smoothing to each encoder in either the clean-trained corruption benchmark or experimental evaluation. We will clarify this distinction and avoid attributing the observed performance differences solely to the representations.
Please provide a table of the fine-tuning results in Fig. 5a with standard deviations, candidate-pool sizes and paired tests.
We now provide the updated transfer results following calibrated-ramp training, as suggested by Reviewer KbXD, including zero-shot (ZS) and fine-tuned (FT) evaluation on identical held-out test sets. HSQC retains the original augmentation coefficients. Values are mean ± SD over 10 seeds (%): top-1 retrieval accuracy, and macro-AUROC for IR.
| Experimental test set | Candidates | VINEA ZS | Best dense ZS | VINEA FT | Best dense FT | Paired , ZS / FT |
|---|---|---|---|---|---|---|
| ¹H NMR — BMRB | 2,012 | 12.83 ± 0.91 | NMR2Struct: 12.73 ± 0.45 | 15.83 ± 2.31 | NMRViT: 15.65 ± 0.69 | 1.000 / 1.000 |
| ¹H NMR - Chemotion | 3,556 | 24.77 ± 0.75 | NMR2Struct: 20.10 ± 0.52 | 23.19 ± 1.91 | NMR2Struct: 20.04 ± 1.05 | 0.0469 / 0.0508 |
| ¹H NMR - nmrXiv | 316 | 49.05 ± 0.99 | NMR2Struct: 43.45 ± 2.07 | 47.97 ± 1.78 | NMR2Struct: 43.99 ± 1.88 | 0.0469 / 0.0508 |
| HSQC - nmrXiv | 19 | 14.74 ± 4.15 | DeepSAT: 24.21 ± 5.66 | 20.00 ± 7.77 | DeepSAT: 35.26 ± 4.99 | 0.0508 / 0.0703 |
| IR - NIST FTIR | N/A | 71.54 ± 1.23 | IRCNN: 71.06 ± 1.01 | 81.90 ± 1.29 | UltraIR: 82.59 ± 0.88 | 1.000 / 0.6738 |
| Raman - SOPRANO | 35 | 6.86 ± 3.86 | DeepCNN: 7.43 ± 2.41 | 9.43 ± 3.58 | RamanNet: 6.29 ± 1.81 | 1.000 / 0.3164 |
The reported -values compare VINEA with the displayed dense baseline using two-sided exact paired sign-flip permutation tests across ten matched training seeds. Holm correction covers all 24 VINEA/baseline comparisons across datasets, separately for zero-shot and fine-tuned evaluation, including baselines omitted from the table. After Holm correction, VINEA significantly outperforms the strongest dense baseline in zero-shot transfer on Chemotion and nmrXiv H NMR (both ()).
Which batch size (number of InfoNCE negatives) did each model use on each modality, and what hyper-parameter search budget did baselines receive compared with VINEA
We thank Reviewer P3vK for requesting this clarification. Our statement that every model used batch size 32 was incorrect. The main synthetic benchmarks used:
| Modality | Models | Batch size | InfoNCE negatives per query per direction |
|---|---|---|---|
| H NMR | NMR2Struct, CHEFNMR, NMRViT, SECS, VINEA | 32 | 31 |
| HSQC | DeepSAT, HSQC-CNN, NMRViT-HSQC, VINEA-HSQC | 4 | 3 |
| Raman | DeepCNN, RamanNet, SANet, RamanFormer, ReZeroNet, ResNet-1D, Spectral Transformer, VINEA | 64 | 63 |
| IR | ACT, IRCNN, SpectraML-CNN, UltraIR, VINEA | 64 | Not applicable |
For symmetric InfoNCE, a batch of matched pairs provides negatives per query in each direction, or negative comparisons per matched pair across both directions. Thus, the negative pools were consistent within each retrieval modality. IR uses supervised multilabel classification.
The historical SPECTRE comparison used batches of 32, four gradient-accumulation steps and 300 training epochs, compared with 30 epochs for the other HSQC models. Accumulation did not expand its InfoNCE pool: each query still had 31 negatives.
Regarding hyperparameter-search budgets, the documented NMR learning-rate screen was shared by NMR2Struct, CHEFNMR, NMRViT, SECS and VINEA. Each tested (,,) using seed 17 and 30 epochs per trial: three attempted fits per model. VINEA received additional exploration: its NMR architecture sweep and initial HSQC pilot each evaluated four configurations with three seeds (12 fits each), followed by nine HSQC configurations with three seeds (27 fits). We do not claim equal overall tuning budgets. We will correct the batch-size statement and clarify these budgets in the updated manuscript.
Response to Reviewer P3vK (Part 3)
What does Table 11 report for Raman (retrieval R@1 or classification BAcc)? What is SPECTRE, how was it trained, and why is it not in Table 8?
We thank the reviewer for identifying these inconsistencies. Tables 11 and 12 report Raman spectrum-to-molecule Recall@1 over 5,056 ChEMBL candidates. The reference to pharmaceutical classification in Table 12’s caption and the BAcc description in Appendix E.10 incorrectly describe these results. We will correct these descriptions. However, this task-label correction does not change the underlying retrieval scores.
SPECTRE (Xu et al., 2026) is a Transformer for NMR-based molecular fingerprint prediction. We explored several training configurations for an HSQC retrieval adaptation using our shared contrastive head. The exploratory configuration reported in the SI used ten seeds, a 300-epoch budget, microbatches of 32, four gradient-accumulation steps, and a Noam schedule with 8,000 warmup steps. Despite these attempts and the extended training budget, our adaptation showed unsatisfactory learning progress and convergence. We therefore excluded it from the final main comparison. Its preliminary results were inadvertently retained in Supplementary Table 11 during manuscript preparation, creating the discrepancy with Table 8. We will remove the obsolete SI entry and clarify the status of this exploratory adaptation.
Analyse which real-data factors make VINEA worse than dense encoders in zero-shot ¹H transfer (e.g., solvent or impurity peaks, multiplet structure, the M = 128 token cap under noise), and report performance as a function of M under thermal noise. Report end-to-end throughput alongside parameter counts, and qualify "compact" accordingly.
We thank Reviewer P3vK for this question. As requested, we further investigated the experimental transfer gap through different ablations, such as token-budget ablations under thermal noise, isolated noised experiments, and diagnostics on measured spectra.
The token-budget results show that retaining more tokens helps VINEA under moderate thermal noise. Increasing M from 128 to 256 improves S3 R@1 by 1.03 percentage points ( CI [0.46,1.78]). At S5, accuracy stays around for all three budgets, so increasing the token limit provides little benefit under severe noise.
We additionally evaluated individual noise artifacts across S1-S5 using ten paired training seeds. Each artifact was applied alone. We compared full VINEA with the no-blur control to measure how their performance difference depends on the noise type and severity. In H NMR, full VINEA achieves higher R@1 in all 25 conditions, with an average gain of percentage points ( CI ). At S5, the gains reach points under phase error and points under baseline drift. Shimming shows a gain of points at S4 and points at S5. Raman and HSQC show mixed effects. For example, the S5 differences are points for Raman fluorescence and for cosmic rays. For HSQC, they are points for shift jitter and for baseline drift.
We hypothesized that solvent or impurity peaks in experimental spectra could contribute to VINEA's transfer gap, as experimental spectra of products might contain impurities. We tested this possibility by adding solvent-reference signals to held-out MSD spectra and comparing VINEA with the dense baselines. We collected a list of most common solvents added each separately at peak heights of , , , , and of the original spectrum's maximum absolute intensity. All models received the same perturbed spectra. The results showed that at addition, VINEA achieves the highest mean R@1 for ten of the twelve solvent references. For example, it reaches under acetonitrile interference and under cyclohexane interference, compared with NMR2Struct's and , respectively. Averaging across all twelve solvents gives R@1 of for VINEA and for NMR2Struct. Ethyl acetate and DMF are the two exceptions, highlighting specific chemical-interference patterns that may contribute to the experimental transfer gap. We summarize all results in the next Table.
Response to Reviewer P3vK (Part 1)
We thank Reviewer P3vK for the detailed assessment and for recognizing the benchmark’s breadth, reproducibility, and reporting of negative results. The review identifies several places where our claims exceed the evidence or where the experimental description is inconsistent. We address these points below.
We thank Reviewer P3vK for this suggestion. We evaluated a conventional peak-set control and NMRTrans and UltraNMR retrieval adaptations on the same 1H NMR benchmark, using the same corruption conditions and ten matched training seeds. The conventional control uses peak positions, prominence, widths, areas and neighboring-peak gaps with the VINEA Set Transformer design and the same training budget. It removes the lifetime and blur-profile descriptors while retaining multiscale extraction. NMRTrans receives comparable peak geometry measured directly from the spectrum through its own encoder. The adaptation uses automatically detected peaks from
scipy.signal.find_peaksand was trained from scratch without externally supplied chemical annotations, with a learning rate of 310-5 selected through learning-rate screening.Peak-based retrieval comparisons. Spectrum-to-molecule R@1 over 18,493 candidates, reported as mean sample SD across ten seeds.
VINEA achieves the highest mean R@1 in both conditions, exceeding the conventional-peak control by 1.93 percentage points on clean spectra and 3.03 points at S3, calculated before rounding. NMRTrans approaches VINEA’s clean performance, but its gap increases to approximately 8.55 points under combined S3 corruption. These results support the robustness of the evaluated VINEA configuration relative to the tested peak-based alternatives.
UltraNMR is included as a supplementary comparison. It receives only automatically detected 1H chemical shifts, retains its Fourier embedding, and was trained from scratch without the 13C inputs or pretrained weights of its published setup. Its results therefore describe a restricted adaptation.
Thank you for identifying this inconsistency. Table 16 reported a three-seed ablation study using a different training protocol from the main benchmark. The main benchmark used 20 clean-training epochs followed by an 80-epoch S1-S3 corruption ramp. The original ablation instead began the ramp immediately, reached S3 after the first 70% of training, and selected checkpoints by clean validation MRR only from epoch 75 onward. Its full-model reference was therefore not directly comparable to the main-benchmark model.
Separately, Table 12 contained a stale seven-seed aggregate despite being labelled as ten seeds. This was caused by a bug in our aggregation pipeline. We apologize for this reporting error. Following this, we subsequently verified all numerical tables against the retained per-seed results and controlled the fine-tuning. Recomputing the complete ten-seed gives the following results:
We retrained all NMR ablation variants with ten matched seeds using the main training schedule and compared them against the existing full VINEA checkpoints from Figure 4, and we will provide attached to the extended tables of ablations for our method. The no-blur control achieves 0.760$\pm$0.005 clean R@1 and 0.557$\pm$0.023 S3 R@1.