post_training (assayllm-training)
Post training of Qwen3.6-27B
AssayLLM is Qwen3.6-27B supervised fine-tuned on GLM-5.1 acquisition trajectories from the training screens and then trained with GRPO; the authors report EF rising from 2.65 (base) to 3.56 (SFT) and 3.69 (SFT + GRPO).
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 post_training Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.7; Figure 6 caption; Methods 4.7 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed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 2.7; Figure 6 caption; Methods 4.7 Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.7; Figure 6 caption; Methods 4.7 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed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 AssayLLM is Qwen3.6-27B supervised fine-tuned on GLM-5.1 acquisition trajectories from the training screens and then trained with GRPO; the authors report EF rising from 2.65 (base) to 3.56 (SFT) and 3.69 (SFT + GRPO). Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.7; Figure 6 caption; Methods 4.7 Version: arXiv:2609.11877 version 1, submitted 2026-09-10; not peer reviewed | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed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 2.7; Figure 6 caption; Methods 4.7 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-model-qwen3-6-27b Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.7; Figure 6 caption; Methods 4.7 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 post_training (assayllm-training) Context-only references | Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens Section 2.7; Figure 6 caption; Methods 4.7 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-assayllm-training
- areas
- cells-tissues
- contexts
- research
- field
- post_training
- value
- AssayLLM is Qwen3.6-27B supervised fine-tuned on GLM-5.1 acquisition trajectories from the training screens and then trained with GRPO; the authors report EF rising from 2.65 (base) to 3.56 (SFT) and 3.69 (SFT + GRPO).
- source locator
- Section 2.7; Figure 6 caption; Methods 4.7
- 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: Qwen3.6-27B