rewirebio.iobenchmarks
Evidence claim

Perturbation response: scope note

Scope note of Perturbation response

Predict expression changes under a held-out perturbation condition. The held-out condition need not be an agent the model has never seen: a protocol under this task may hold out a dose, a time point or a cell context of an agent whose other conditions are available in training or in context, and each protocol record states which. A result under this task is therefore not evidence of prediction for an unseen perturbing agent unless its protocol says the agent itself was held out.

Correction made by the 2026-11-16 cross-batch coordinator fix pass. The previous value is kept here.

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.

7 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
Claimed field
attributes.scope_note
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.field

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

Previous value
Predict expression changes after unseen perturbations.
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.previous_value

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

Source location
arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.source_locator

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

Claimed value
Predict expression changes under a held-out perturbation condition. The held-out condition need not be an agent the model has never seen: a protocol under this task may hold out a dose, a time point or a cell context of an agent whose other conditions are available in training or in context, and each protocol record states which. A result under this task is therefore not evidence of prediction for an unseen perturbing agent unless its protocol says the agent itself was held out.
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: attributes.value

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

Description
Correction made by the 2026-11-16 cross-batch coordinator fix pass. The previous value is kept here.
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: description

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

Relationship: subject
catalog-task-cell-perturbation
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: links:subject:catalog-task-cell-perturbation

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

Name
Perturbation response: attributes.scope_note
Context-only references
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1)

Original source ↗

arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation

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

not individually reviewed

No individual claim review recorded

Audit details

Field: name

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

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: metadata-correction-coordfix-20261116-cell-perturbation-scope-note

areas
cells-tissues
field
attributes.scope_note
previous value
Predict expression changes after unseen perturbations.
value
Predict expression changes under a held-out perturbation condition. The held-out condition need not be an agent the model has never seen: a protocol under this task may hold out a dose, a time point or a cell context of an agent whose other conditions are available in training or in context, and each protocol record states which. A result under this task is therefore not evidence of prediction for an unseen perturbing agent unless its protocol says the agent itself was held out.
source locator
arXiv:2607.23447v1 Appendix D.2, sentence "The held-out drug is not completely unseen, since lower-dose responses are available"; data/entities/tasks.jsonl, record catalog-task-cell-perturbation
review
method: ai-assisted-source-review; scope-review; method note: Read the task record, every record in the store that links to it, and Appendix D.2 of arXiv:2607.23447v1, which is the first protocol to link to it. No value was read or recomputed.; reviewer: claude; reviewer note: Claude coordinator-fix agent; no human review claimed. It extracted none of the thirteen batches of 2026-11-15 and 2026-11-16. Each change is a reviewed correction to a stored record, justified by a dated review already in the repository and checked here against the store. Nothing was reproduced and no stored value was recomputed.; reviewed at: 2026-11-16T03:00:00Z; note: The scope note read as a claim that every protocol under this task holds out an unseen perturbing agent. The PerturbPFN Sci-Plex protocol, the first record in the store to link to this task, holds out the highest dose of a drug whose lower doses are available, which Appendix D.2 states. docs/reviews/2026-11-15-perturbpfn.md ruling 7 kept the link and left the scope note to the coordinator. The wording now covers dose, time and context holdouts and says a result here is not evidence about an unseen agent. The link, the task identity, the empty description, the status and the profile were not changed.
Related records

Suggest a correction