Baseline: Select perturbations for a defined cellular response
Baseline of Select perturbations for a defined cellular response
Random selection
Baseline method for the use case, reviewed against its cited sources.
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.
9 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field baseline Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
Method ids1 values
| BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
Pinned records2 values
| BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Rationale There is no pre-machine-learning method for choosing perturbations to reach a defined cell state, so the reference is random selection from the candidate set. Among the evidence linked to this use case, only the retrospective AssayBench-Loop replay scores it, as one random draw on the same screens and budget as the other policies; the CPPC protocols measure submitted methods only, and the challenge's ranking metric only takes 0.5 as the value expected from a random ranking. NAIAD's uniform arm still ranks pairs with the model, so it is not this baseline. Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Source location tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Claimed value Random selection Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Description Baseline method for the use case, reviewed against its cited sources. Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Relationship: subject use-case-phenotype-perturbation-selection Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
| Name Baseline: Select perturbations for a defined cellular response Context-only references | BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description Version: arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/extract_target_validation.py |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments · Original source · arXiv:2405.17631 version 3, updated 2025-03-09; published as a conference paper at ICLR 2025
Technical metadata and extraction receipts
Stable ID: use-case-baseline-phenotype-perturbation-selection
- field
- baseline
- value
- Random selection
- source locator
- tgtval-20261009-source-roohani2025: Table 2 (Random baseline by round) and baselines description
- method ids
- tgtval-20261009-method-random-selection
- rationale
- There is no pre-machine-learning method for choosing perturbations to reach a defined cell state, so the reference is random selection from the candidate set. Among the evidence linked to this use case, only the retrospective AssayBench-Loop replay scores it, as one random draw on the same screens and budget as the other policies; the CPPC protocols measure submitted methods only, and the challenge's ranking metric only takes 0.5 as the value expected from a random ranking. NAIAD's uniform arm still ranks pairs with the model, so it is not this baseline.
- review
- method: source-hash-verification; automated-source-review; reviewer: claude; reviewer note: Claude (Opus 5.5) use-case review agent in the evidence-pass workflow for issue #184, independent of the agent that drafted these judgements and the summary; no human review claimed; the reviewer corrected the rationale; reviewed at: 2026-10-22T18:00:00Z; note: Rationale updated in the 2026-10-22 refresh (issue #184): the earlier text said no linked evidence scores random selection, which stops being true once the AssayBench-Loop judgement is active (its Random configuration is tgtval-20261009-method-random-selection). Value, method_ids and source_ids unchanged; the 2026-10-12 review (docs/reviews/use-cases/baselines-2026-10-12.md) still covers them. See docs/reviews/use-cases/phenotype-perturbation-selection-2026-10-22.md.
- pins
- record id: tgtval-20261009-source-roohani2025; fields: status; attributes.artifact_sha256; sha256: 2cd7fb822f68bd61204618ad8ffaf1f70dfb094237c5787671c3a3ecfc8afd5b; record id: use-case-phenotype-perturbation-selection; fields: status; name; description; facets; attributes.question; attributes.decision; attributes.inputs; attributes.output; attributes.exclusions; attributes.setting; attributes.clinical_scope; attributes.intended_users; sha256: f00ad84ac33a7fc848a5df63f06252d4515e87648cf34342405b06f91a115fd4