Emb-Cos on MSAlign molecular retrieval NPLIB1: no formula, R@5: NPLIB1 retrieval with no formula
MSAlign molecular retrieval evaluation of Emb-Cos on NPLIB1 retrieval with no formula, scored with Recall@5.
Evaluation results
1 evaluation · 1 metric rows. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Emb-Cos | Protocol: MSAlign molecular retrieval NPLIB1: no formula, R@5: NPLIB1 retrieval with no formula Dataset subset: NPLIB1, no formula candidate pool (MSAlign molecular retrieval split) | 48.3% recall_at_5 percent · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · source checkedMethods, coverage and sourceEmb-Cos on MSAlign molecular retrieval NPLIB1: no formula, R@5: NPLIB1 retrieval with no formula Section 5.1 candidate retrieval: 256 mass-matched PubChem candidates per spectrum without formula; formula-conditioned methods can exploit true formula and MSAlign+Filter reduces the pool to about 100. Preserve the named source split; exact original split hashes remain unextracted. Aggregation: Not reported msalign: Primary paper PDF · Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) |
Source checking is not independent reproduction. Release 2026-09-23-2b89723c6dd9.
Evaluation procedure
Section 5.1 candidate retrieval: 256 mass-matched PubChem candidates per spectrum without formula; formula-conditioned methods can exploit true formula and MSAlign+Filter reduces the pool to about 100. Preserve the named source split; exact original split hashes remain unextracted.
- Configuration
- Emb-Cos
- Protocol
- MSAlign molecular retrieval NPLIB1: no formula, R@5: NPLIB1 retrieval with no formula
- Dataset subset
- NPLIB1, no formula candidate pool (MSAlign molecular retrieval split)
- origin
- Independent external evaluation
- configuration
- Not reported
- protocol id
- msalign-2026-table3-task-nplib1-no-formula-r-5
- metric implementation
- Recall@5
Metadata review: source checked. Unreported conditions prevent automatic comparisons.
Reproduction
- Split
- Not reported
- Adaptation
- Not reported
- Scoring implementation
- Recall@5
No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.
Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.
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.
15 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.adaptation Author-trained/evaluated retrieval models under the settings in Section 5.1. Candidate sets are kept distinct by dataset, split and whether the molecular formula is supplied. Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.comparison.metric_implementation Recall@5 Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.comparison.protocol_id msalign-2026-table3-task-nplib1-no-formula-r-5 Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.evaluation_group_id msalign-2026-table3-method-emb-cos-msalign-2026-table3-dataset-nplib1-no-formula-candidate-pool-evaluation-setup Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.evidence_overlap Complete Table 3 of one paper; dataset/split/input groups are not independent replications of a common protocol. Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.origin independent_paper Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.protocol Section 5.1 candidate retrieval: 256 mass-matched PubChem candidates per spectrum without formula; formula-conditioned methods can exploit true formula and MSAlign+Filter reduces the pool to about 100. Preserve the named source split; exact original split hashes remain unextracted. Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.published_score_reproduction false Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.source_locator Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.suite_complete false Context-only references | msalign: Primary paper PDF Table 3, NPLIB1, row R@5, column 6 (Emb-Cos) Version: 2605.19752v1 | not individually reviewed No individual claim review recorded independent paper Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Sources and history
View linked audit checks and correction history
Release 2026-09-23-2b89723c6dd9 · Record review: source checked
1 source records and release history
- msalign: Primary paper PDF · Original source · 2605.19752v1
Technical metadata and extraction receipts
Stable ID: msalign-2026-table3-evaluation-emb-cos-nplib1-no-formula-r-5
- areas
- molecular-omics
- tasks
- NPLIB1 retrieval with no formula
- origin
- independent_paper
- protocol
- Section 5.1 candidate retrieval: 256 mass-matched PubChem candidates per spectrum without formula; formula-conditioned methods can exploit true formula and MSAlign+Filter reduces the pool to about 100. Preserve the named source split; exact original split hashes remain unextracted.
- comparison
- protocol id: msalign-2026-table3-task-nplib1-no-formula-r-5; metric implementation: Recall@5
- missing metadata
- checkpoint revision: unreported; seeds: unreported; budget: unreported; split manifest: unextracted
- source locator
- Table 3, NPLIB1, row R@5, column 6 (Emb-Cos)
- adaptation
- Author-trained/evaluated retrieval models under the settings in Section 5.1. Candidate sets are kept distinct by dataset, split and whether the molecular formula is supplied.
- evidence overlap
- Complete Table 3 of one paper; dataset/split/input groups are not independent replications of a common protocol.
- published score reproduction
- false
- suite complete
- false
- evaluation group id
- msalign-2026-table3-method-emb-cos-msalign-2026-table3-dataset-nplib1-no-formula-candidate-pool-evaluation-setup