rewirebio.iobenchmarks
Evaluation

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

Author-reported evaluation transcribed from the pinned preprint; run by the PerturbPFN authors and not reproduced by Rewire.

Evaluation results

1 evaluation · 6 results. Different protocols are not a single leaderboard.

Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2) · Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)

Sorted by Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configurationMin max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols)Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost)Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols)
CondOT (PICNN, PerturbPFN Table 2)Evaluation0.740.8010.932(#3)72700.825
All 6 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
0.825 Weighted composite score (Equal-weight mean of the three protocol-averaged min-max normalised scores (mean distance, Pearson r, Sinkhorn W2) across the seven Table 2 rows on 12 Sci-Plex highest-dose protocols)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Avg. ŝ / rank', score before the bracket
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
(#3) Rank (Rank of the overall normalised score among the seven Table 2 rows on 12 Sci-Plex highest-dose protocols)
unitless · lower

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Avg. ŝ / rank', bracketed rank
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
7270 Runtime (Mean wall-clock seconds per Sci-Plex highest-dose protocol on one NVIDIA RTX 4090 worker, without any one-time pretraining cost)
second · lower

Uncertainty: SD 585.9

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'Time (s) / protocol'
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
0.801 Min max normalised score (Mean distance (L2 distance between predicted and observed mean expression over the 50 marker genes), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝMD ↑'
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
0.932 Min max normalised score (Pearson correlation between predicted and observed mean expression over the 50 marker genes, min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝr ↑'
Configuration: CondOT (PICNN, PerturbPFN Table 2)Protocol: Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset: Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
0.74 Min max normalised score (Debiased Sinkhorn 2-Wasserstein distance between predicted and observed cell sets (epsilon 0.1), negated, then min-max normalised across the seven Table 2 rows within each of 12 Sci-Plex highest-dose protocols and averaged over protocols)
unitless · higher

Uncertainty: Not reported by the source: No spread is printed for this value.

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

CondOT on the Sci-Plex highest-dose holdout (PerturbPFN Table 2)

perturbpfn-20261115-protocol-sciplex-highest-dose-normalised

Aggregation: Not reported

PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Table 2, row 'CondOT', column 'ŝW2 ↑'

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

Research readiness

0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.

Readiness checks, gaps and artifacts

Release 2026-11-21-c8bea25e5abb · Evidence verified: Not verified

Evidence incomplete

Replay metrics

Exact outcomes, predictions, identifiers and evaluator are connected.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified

Verified: Not verified

Evidence incomplete

Investigate discrepancies

Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Metrics are recomputed from the saved predictions: not yet verified
  • Sample annotations are recorded: not yet verified
  • Dependence between samples is assessed: not yet verified

Verified: Not verified

Evidence incomplete

Run locally

A pinned recipe describes the inputs, environment and resource requirements.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • A pinned run recipe exists: not yet verified
  • Compute requirements are estimated: not yet verified

Verified: Not verified

Evidence incomplete

Validate independently

Separate data and exposure records support an independent test.

Missing or unresolved evidence

  • No verified artifact manifest is linked to this exact record.
  • File checksums match the recorded files: not yet verified
  • Predictions are matched to the right samples: not yet verified
  • Score meaning and direction are confirmed: not yet verified
  • Independent validation data exist: not yet verified
  • Overlap with training data is checked: not yet verified

Verified: Not verified

Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.

Artifacts and reproduction

No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.

Evaluation procedure

Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)

Configuration
CondOT (PICNN, PerturbPFN Table 2)
Protocol
Sci-Plex highest-dose holdout with min-max normalised MD, Pearson r and W2 (PerturbPFN Table 2)
Dataset subset
Sci-Plex HDAC-inhibitor subset, 3 cell lines by 4 drugs (GIM preprocessing)
origin
Author-reported evaluation
configuration
arXiv:2607.23447v1
adaptation
Fitted per protocol on its training conditions
aggregation
Mean over 12 protocols per metric; overall score is the mean of the three metric means
budget
100,000 alternating optimisation steps per protocol
dataset version
Sci-Plex subset preprocessed as in the GIM benchmark (Schneider et al. 2025): median-control-count normalisation, filtering, log transform, 50 marker genes per protocol chosen from training conditions
inputs
Control cells, drug identity and dose descriptors and the expression of every context condition; no drug targets
metric implementation
MD, Pearson r of mean vectors and debiased Sinkhorn W2 (epsilon 0.1, 200 iterations, tolerance 1e-6), each oriented higher-is-better and min-max normalised across the seven Table 2 rows within each protocol
population
12 protocols: A549, K562 and MCF7 by belinostat, dacinostat, givinostat and quisinostat 2HCl
protocol id
perturbpfn-20261115-protocol-sciplex-highest-dose-normalised
split
Per cell line and drug pair, the highest dose is the query; context is controls, lower doses of that drug and all doses of the other three drugs in the same cell line

Metadata review: source checked. Unreported conditions prevent automatic comparisons.

Reproduction

Split
Per cell line and drug pair, the highest dose is the query; context is controls, lower doses of that drug and all doses of the other three drugs in the same cell line
Adaptation
Fitted per protocol on its training conditions
Scoring implementation
MD, Pearson r of mean vectors and debiased Sinkhorn W2 (epsilon 0.1, 200 iterations, tolerance 1e-6), each oriented higher-is-better and min-max normalised across the seven Table 2 rows within each protocol

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.

19 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance
Comparison: adaptation
Fitted per protocol on its training conditions
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.adaptation

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: aggregation
Mean over 12 protocols per metric; overall score is the mean of the three metric means
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.aggregation

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: budget
100,000 alternating optimisation steps per protocol
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.budget

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: dataset version
Sci-Plex subset preprocessed as in the GIM benchmark (Schneider et al. 2025): median-control-count normalisation, filtering, log transform, 50 marker genes per protocol chosen from training conditions
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.dataset_version

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: inputs
Control cells, drug identity and dose descriptors and the expression of every context condition; no drug targets
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.inputs

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: metric implementation
MD, Pearson r of mean vectors and debiased Sinkhorn W2 (epsilon 0.1, 200 iterations, tolerance 1e-6), each oriented higher-is-better and min-max normalised across the seven Table 2 rows within each protocol
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.metric_implementation

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: population
12 protocols: A549, K562 and MCF7 by belinostat, dacinostat, givinostat and quisinostat 2HCl
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.population

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: protocol id
perturbpfn-20261115-protocol-sciplex-highest-dose-normalised
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.protocol_id

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Comparison: split
Per cell line and drug pair, the highest dose is the query; context is controls, lower doses of that drug and all doses of the other three drugs in the same cell line
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.comparison.split

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

Limitations
2 values
  • Run by the PerturbPFN authors, who developed the proposed method and ran every comparator.
  • Min-max normalised within the seven compared rows: the value changes if a method is added or removed, so it is comparable only within Table 2.
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

Table 2, row 'CondOT'

Version: arXiv v1, submitted 2026-07-26
Retrieved: 2026-11-15T20:27:40Z

not individually reviewed

No individual claim review recorded

author reported

Audit details

Field: attributes.limitations

Source artifact SHA-256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1

Hash scope: Exact bytes of the PDF. Three downloads on 2026-11-15 (20:22Z to 20:27Z) gave identical bytes.

Inspected artifact

How to read the evidence

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: perturbpfn-20261115-eval-sciplex-condot

areas
single-cell; cells-tissues
contexts
research
comparison
adaptation: Fitted per protocol on its training conditions; aggregation: Mean over 12 protocols per metric; overall score is the mean of the three metric means; budget: 100,000 alternating optimisation steps per protocol; dataset version: Sci-Plex subset preprocessed as in the GIM benchmark (Schneider et al. 2025): median-control-count normalisation, filtering, log transform, 50 marker genes per protocol chosen from training conditions; inputs: Control cells, drug identity and dose descriptors and the expression of every context condition; no drug targets; metric implementation: MD, Pearson r of mean vectors and debiased Sinkhorn W2 (epsilon 0.1, 200 iterations, tolerance 1e-6), each oriented higher-is-better and min-max normalised across the seven Table 2 rows within each protocol; population: 12 protocols: A549, K562 and MCF7 by belinostat, dacinostat, givinostat and quisinostat 2HCl; protocol id: perturbpfn-20261115-protocol-sciplex-highest-dose-normalised; split: Per cell line and drug pair, the highest dose is the query; context is controls, lower doses of that drug and all doses of the other three drugs in the same cell line
limitations
Run by the PerturbPFN authors, who developed the proposed method and ran every comparator.; Min-max normalised within the seven compared rows: the value changes if a method is added or removed, so it is comparable only within Table 2.
origin
author_reported
protocol
perturbpfn-20261115-protocol-sciplex-highest-dose-normalised
review
artifact sha256: 42191efa04b45ca04b2be38b51ea374cd9bf891efe2399d331fec9eaeab200b1; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; method note: Independent review pass. Both pinned artifacts were re-downloaded and their SHA-256 checked against the source records, the mutable abstract page included, and both matched. A pdftotext -layout run (poppler 26.08.0) on the refetched PDF is byte for byte the contents of the archived gzipped text layer, so the archive is provably derived from the pinned bytes. npm run batch -- check-values reproduced the extractor's figures exactly (64 in_cell, 11 in_row, 6 locator_not_parsed, no wrong_column and no overclaimed_in_row) and wrote the same value-check.tsv. All 81 results were then re-read by review/recheck_tables.py, written for this pass and using neither extract/parse_tables.py nor extract/check_tables.py: it takes each table's column spans from the character offsets of that table's own printed header line, assigns every numeric token on a body line to the column whose header centre is nearest, and matches cells to records through each result's source_locator text rather than its ID, checking printed_value, numeric_value, the printed spread and the system the result's evaluation names. Two negative controls confirmed it fails on a swapped pair of values and on a cell shifted into the neighbouring column. A manual check of 16 cells covered column assignment in all three tables, including Table 2's unlabelled PerturbPFN score line, Table 1's third label and value pair on each of its three rows, and Table 3's middle columns. The printed overall score was re-derived as the equal-weight mean of each row's three normalised columns. The 54 descriptive records were read against Sections 2 to 5, Appendices A to E and Tables 4 to 8 of the pinned PDF.; retrieval url: https://arxiv.org/pdf/2607.23447v1; reviewed at: 2026-11-15T00:00:00Z; reviewer: claude; reviewer note: Claude review agent (independent of the extractor); no human review claimed. Transcription was checked against the pinned source; nothing was reproduced and no value was recomputed.
source locator
Table 2, row 'CondOT'
version
arXiv:2607.23447v1
Related records

Suggest a correction