training (assayformer-training)
Training of AssayFormer
Gene embeddings are initialised by BPMF on the training hit matrix; the policy is trained with binary cross-entropy on simulated partial histories, then fine-tuned with GRPO on full 10-round rollouts using a context-delta reward relative to a context-free reference policy.
Descriptive fact transcribed from the pinned source.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field training Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
| Source location Section 2.2; Figure 3C caption; Methods 4.5 Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
| Claimed value Gene embeddings are initialised by BPMF on the training hit matrix; the policy is trained with binary cross-entropy on simulated partial histories, then fine-tuned with GRPO on full 10-round rollouts using a context-delta reward relative to a context-free reference policy. Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
| Description Descriptive fact transcribed from the pinned source. Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
| Relationship: subject ucpheno-20261022-method-assayformer Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
| Name training (assayformer-training) Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.2; Figure 3C caption; Methods 4.5 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by data/omics/use-case-refresh-phenotype-20261022/extract/edwards2026assayloop.py |
Sources and history
Release 2026-10-23-5347695500ed · Record review: source checked
1 source record and release history
- Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens · Original source · arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed
Technical metadata and extraction receipts
Stable ID: ucpheno-20261022-claim-edwards2026-assayformer-training
- areas
- cells-tissues
- contexts
- research
- field
- training
- value
- Gene embeddings are initialised by BPMF on the training hit matrix; the policy is trained with binary cross-entropy on simulated partial histories, then fine-tuned with GRPO on full 10-round rollouts using a context-delta reward relative to a context-free reference policy.
- source locator
- Section 2.2; Figure 3C caption; Methods 4.5
- review
- method: source-hash-verification; ai-assisted-source-review; reviewer: claude; reviewer note: Claude (Opus 5.5) review agent in the evidence-pass workflow, independent of the extraction agent; no human review claimed; date: 2026-10-22; artifact sha256: adcaaa5b7f9bd0e3bc1f91d94d26c8d4924c5c0b3064b6625c01ba92c6eaef28; retrieval url: https://arxiv.org/pdf/2609.11877v1; note: Independent review: value checked against the text at the stated locator in the text layer.
Related records
- subject: AssayFormer