diff --git a/README.md b/README.md
index 6d0f3535..d8d56814 100644
--- a/README.md
+++ b/README.md
@@ -86,8 +86,6 @@ docker run \
   --output_vcf=/output/YOUR_OUTPUT_VCF \
   --output_gvcf=/output/YOUR_OUTPUT_GVCF \
   --num_shards=$(nproc) \ **This will use all your cores to run make_examples. Feel free to change.**
-  --vcf_stats_report=true \ **Optional. Creates VCF statistics report in html file. Default is false.
-  --disable_small_model=true \ **Optional. Disables the small model from make_examples stage. Default is false.
   --logging_dir=/output/logs \ **Optional. This saves the log output for each stage separately.
   --haploid_contigs="chrX,chrY" \ **Optional. Heterozygous variants in these contigs will be re-genotyped as the most likely of reference or homozygous alternates. For a sample with karyotype XY, it should be set to "chrX,chrY" for GRCh38 and "X,Y" for GRCh37. For a sample with karyotype XX, this should not be used.
   --par_regions_bed="/input/GRCh3X_par.bed" \ **Optional. If --haploid_contigs is set, then this can be used to provide PAR regions to be excluded from genotype adjustment. Download links to this files are available in this page.
diff --git a/docs/README.md b/docs/README.md
index d176134e..a761a13a 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -13,7 +13,8 @@
 *   [DeepVariant hybrid (PacBio and Illumina) case study](deepvariant-hybrid-case-study.md)
 *   [DeepVariant Complete Genomics T7 case study](deepvariant-complete-t7-case-study.md)
 *   [DeepVariant Complete Genomics G400 case study](deepvariant-complete-g400-case-study.md)
-*   [RNA-seq Case Study](deepvariant-rnaseq-case-study.md) for Illumina RNA-seq.
+*   [RNA-seq Case Study](deepvariant-rnaseq-case-study.md) for Illumina
+    RNA-seq.
 *   [PacBio Iso-Seq/MAS-Seq Case Study](deepvariant-masseq-case-study.md).
 *   [Runtime and accuracy metrics for all DeepVariant models](metrics.md)
 *   [Best practices for multi-sample variant calling](trio-merge-case-study.md)
@@ -21,8 +22,6 @@
 *   Pangenome-aware DeepVariant WGS:
     [Mapped with BWA](pangenome-aware-wgs-bwa-case-study.md),
     [Mapped with VG](pangenome-aware-wgs-vg-case-study.md)
-*   Pangenome-aware DeepVariant WES:
-    [Mapped with BWA](pangenome-aware-wes-bwa-case-study.md)
 
 ## Visualization and analysis
 
diff --git a/docs/deepvariant-fast-pipeline-case-study.md b/docs/deepvariant-fast-pipeline-case-study.md
index db341d4c..8a519aa0 100644
--- a/docs/deepvariant-fast-pipeline-case-study.md
+++ b/docs/deepvariant-fast-pipeline-case-study.md
@@ -23,7 +23,7 @@ Here we create Google Cloud compute instance. You may skip this step if you run
 the case study on a local computer with GPU.
 
 ```bash
-gcloud compute instances create "deepvariant-fast-pipeline" \
+gcloud compute instances create "deepvariant-casestudy" \
   --scopes "compute-rw,storage-full,cloud-platform" \
   --maintenance-policy "TERMINATE" \
   --accelerator=type=nvidia-tesla-p4,count=1 \
@@ -31,13 +31,8 @@ gcloud compute instances create "deepvariant-fast-pipeline" \
   --image-project "ubuntu-os-cloud" \
   --machine-type "n1-standard-16" \
   --boot-disk-size "100" \
-  --zone "us-central1-a"
-```
-
-You can then ssh into the machine by running:
-
-```bash
-gcloud compute ssh "deepvariant-fast-pipeline" --zone us-central1-a
+  --zone "us-central1-a" \
+  --min-cpu-platform "Intel Skylake"
 ```
 
 ## Install Nvidia drivers and Nvidia container toolkit (optional)
@@ -52,7 +47,6 @@ For this case study we used the
 that automates the CUDA and container tools kit installation.
 
 Please note that the script takes about 30 minutes to run.
-
 ```bash
 wget https://raw.githubusercontent.com/google/deepvariant/refs/heads/r1.8.0/scripts/install_nvidia_docker.sh
 chmod +x install_nvidia_docker.sh
@@ -64,7 +58,7 @@ chmod +x install_nvidia_docker.sh
 ### Get DeepVariant Docker image
 
 ```bash
-BIN_VERSION="1.8.0"
+BIN_VERSION="1.8.0-rc0"
 sudo docker pull google/deepvariant:"${BIN_VERSION}-gpu"
 ```
 
@@ -86,7 +80,7 @@ gcloud storage cp gs://deepvariant/case-study-testdata/GCA_000001405.15_GRCh38_n
 
 ```bash
 mkdir -p input
-gcloud storage cp gs://deepvariant/pacbio-case-study-testdata/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam* input/
+gcloud storage cp gs://deepvariant/pacbio-case-study-testdata/HG003.pfda_challenge.grch38.phased.chr20.bam* input/
 ```
 
 ## Run DeepVariant pipeline on chromosome 20 alignments
@@ -116,7 +110,7 @@ cat <<EOM >$FILE
 --examples=/tmp/examples.tfrecords@14.gz
 --gvcf=/tmp/examples.gvcf.tfrecord@14.gz
 --mode=calling
---reads=/input/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam
+--reads=/input/HG003.pfda_challenge.grch38.phased.chr20.bam
 --ref=/reference/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz
 --alt_aligned_pileup=diff_channels
 --max_reads_per_partition=600
@@ -162,7 +156,7 @@ cat <<EOM >$FILE
 --outfile=/output/variants.chr20.vcf
 --gvcf_outfile=/output/variants.gvcf.chr20.vcf
 --small_model_cvo_records=/tmp/examples_call_variant_outputs.tfrecords@14.gz
---cpus=14
+--cpus=0
 EOM
 ```
 
@@ -184,7 +178,7 @@ time sudo docker run \
     --shm_prefix dv \
     --num_shards 14 \
     --buffer_size 10485760 \
-    2>&1  | tee /tmp/fast_pipeline.docker.log
+    2>&1  | tee /tmp/fast_pipeline.Docker_chr20.log
 ```
 
 *   `-v` allows to map local directory inside docker container.
@@ -217,9 +211,9 @@ variants.gvcf.chr20.vcf
 With the same settings the pipeline takes approximately 10 minutes.
 
 ```
-real    8m15.252s
-user    0m0.007s
-sys     0m0.035s
+real    10m35.875s
+user    0m0.009s
+sys     0m0.034s
 ```
 
 ## Benchmark output
@@ -236,8 +230,6 @@ curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi > benchmark/HG003_G
 
 ```
 HAPPY_VERSION=v0.3.12
-
-time sudo docker run \
   -v ${PWD}/output:/output \
   -v ${PWD}/benchmark:/benchmark \
   -v ${PWD}/reference:/reference \
@@ -254,10 +246,9 @@ time sudo docker run \
 ```
 
 ```
-Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL        10628     10543        85        22403        74      11375     40     29       0.992002          0.993290        0.507744         0.992646                     NaN                     NaN                   1.748961                   2.138647
-INDEL   PASS        10628     10543        85        22403        74      11375     40     29       0.992002          0.993290        0.507744         0.992646                     NaN                     NaN                   1.748961                   2.138647
-  SNP    ALL        70166     70101        65       105602        71      35342     12     12       0.999074          0.998989        0.334672         0.999032                2.296566                1.713281                   1.883951                   1.503192
-  SNP   PASS        70166     70101        65       105602        71      35342     12     12       0.999074          0.998989        0.334672         0.999032                2.296566                1.713281                   1.883951                   1.503192
+INDEL    ALL        10628     10560        68        22592        70      11520     39     30       0.993602          0.993678        0.509915         0.993640                     NaN                     NaN                   1.748961                   2.324711
+INDEL   PASS        10628     10560        68        22592        70      11520     39     30       0.993602          0.993678        0.509915         0.993640                     NaN                     NaN                   1.748961                   2.324711
+  SNP    ALL        70166     70142        24       104271        23      34047      7      5       0.999658          0.999672        0.326524         0.999665                2.296566                 1.74197                   1.883951                   1.849802
+  SNP   PASS        70166     70142        24       104271        23      34047      7      5       0.999658          0.999672        0.326524         0.999665                2.296566                 1.74197                   1.883951                   1.849802
 ```
diff --git a/docs/deepvariant-pacbio-model-case-study.md b/docs/deepvariant-pacbio-model-case-study.md
index 68d72553..f533622b 100644
--- a/docs/deepvariant-pacbio-model-case-study.md
+++ b/docs/deepvariant-pacbio-model-case-study.md
@@ -1,145 +1,119 @@
-# DeepVariant with PacBio HiFi data
+# Using DeepVariant for small variant calling from PacBio HiFi reads
+
+#### Author: William Rowell <wrowell@pacificbiosciences.com>
 
 In this case study we describe applying DeepVariant to PacBio HiFi reads to call
 variants. We will call small variants from a publicly available whole genome
 HiFi dataset from PacBio.
 
-### Updated dataset in release 1.8.0
-
-In release 1.8.0, we have updated the PacBio test data from HG003 Sequel-II to
-latest Revio with SPRQ chemistry data to showcase performance on the updated
-platform and chemistry. The full bam data is available [here](https://downloads.pacbcloud.com/public/revio/2024Q4/WGS/GIAB_trio/HG003/analysis/GRCh38.m84039_241002_000337_s3.hifi_reads.bc2020.bam).
-
-The dataset used in this case-study has following attributes:
-
-```bash
-Sample: HG003
-Region: Chr20
-Chemistry: REVIO SPRQ
-Coverage: 32x
-```
+Starting in v1.4.0, PacBio calling uses one-step variant calling. If you're
+looking for documentation for the two-step process, please look at v1.3.0.
 
 ## Prepare environment
 
-In this case-study, we will use [Docker](https://docs.docker.com/get-docker/) to
-run DeepVariant for variant calling and
-[hap.py](https://github.com/illumina/hap.py) for benchmarking.
+### Tools
 
-If you want to run on GPU machines, or use `Singularity` instead of `Docker`,
-please follow [Quick Start](deepvariant-quick-start.md) documentation.
+[Singularity](https://sylabs.io/docs/) will be used to run DeepVariant and
+[hap.py](https://github.com/illumina/hap.py), and we'll use
+[miniconda](https://docs.conda.io/en/latest/miniconda.html) and a conda
+environment to handle the other dependencies for the case study and samtools.
 
-### Create input and output directory structures and download inputs
+-   singularity (must be installed by `root` user; outside of the scope of this
+    case study)
+-   samtools
 
 ```bash
-BASE="${HOME}/pacbio-case-study"
-
-# Set up input and output directory data
-INPUT_DIR="${BASE}/input/data"
-OUTPUT_DIR="${BASE}/output"
-
-## Create local directory structure
-mkdir -p "${INPUT_DIR}"
-mkdir -p "${OUTPUT_DIR}"
+# add channels to conda configuration
+conda config --add channels defaults
+conda config --add channels bioconda
+conda config --add channels conda-forge
+
+# create the environment and install dependencies
+conda create -y -n deepvariant_env
+conda activate deepvariant_env
+conda install -y samtools==1.10
+```
 
-# Download reference to input directory
-FTPDIR=ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids
-curl ${FTPDIR}/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz | gunzip > ${INPUT_DIR}/GRCh38_no_alt_analysis_set.fasta
-curl ${FTPDIR}/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.fai > ${INPUT_DIR}/GRCh38_no_alt_analysis_set.fasta.fai
+### Download Reference
 
-HTTPDIR=https://storage.googleapis.com/deepvariant/pacbio-case-study-testdata
-curl ${HTTPDIR}/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam > ${INPUT_DIR}/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam
-curl ${HTTPDIR}/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam.bai > ${INPUT_DIR}/HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam.bai
+We will be using GRCh38 for this case study.
 
-# Set up input variables
-REF="GRCh38_no_alt_analysis_set.fasta"
-BAM="HG003.SPRQ.pacbio.GRCh38.nov2024.chr20.bam"
-THREADS=$(nproc)
-REGION="chr20"
+```bash
+mkdir -p reference
 
-# Set up output variable
-OUTPUT_VCF="HG003_PACBIO_SPRQ_GRCh38.chr20.output.vcf.gz"
-OUTPUT_GVCF="HG003_PACBIO_SPRQ_GRCh38.chr20.output.g.vcf.gz"
-INTERMEDIATE_DIRECTORY="intermediate_results_dir"
+# download and decompress
+curl ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz | gunzip > reference/GRCh38_no_alt_analysis_set.fasta
 
-mkdir -p "${OUTPUT_DIR}/${INTERMEDIATE_DIRECTORY}"
+# index reference
+samtools faidx reference/GRCh38_no_alt_analysis_set.fasta
 ```
 
-## Run DeepVariant
+### Download Genome in a Bottle Benchmarks
 
-We will run DeepVariant from docker using the `run_deepvariant` script.
+We will benchmark our variant calls against v4.2.1 of the Genome in a Bottle
+small variant benchmarks for HG003.
 
 ```bash
-BIN_VERSION="1.8.0"
-
-sudo docker run \
-  -v "${INPUT_DIR}":"${INPUT_DIR}" \
-  -v "${OUTPUT_DIR}":"${OUTPUT_DIR}" \
-  google/deepvariant:"${BIN_VERSION}" \
-  /opt/deepvariant/bin/run_deepvariant \
-  --model_type PACBIO \
-  --ref "${INPUT_DIR}/${REF}" \
-  --reads "${INPUT_DIR}/${BAM}" \
-  --output_vcf "${OUTPUT_DIR}/${OUTPUT_VCF}" \
-  --output_gvcf "${OUTPUT_DIR}/${OUTPUT_GVCF}" \
-  --num_shards "${THREADS}" \
-  --regions "${REGION}" \
-  --intermediate_results_dir "${OUTPUT_DIR}/${INTERMEDIATE_DIRECTORY}"
-```
+mkdir -p benchmark
 
-By specifying `--model_type PACBIO`, you'll be using a model that is best
-suited for PacBio data.
-
-NOTE: If you want to run each of the steps separately, add `--dry_run=true` to
-the command above to figure out what flags you need in each step. Based on the
-different model types, different flags are needed in the `make_examples` step.
-
-`--intermediate_results_dir` flag is optional. By specifying it, the
-intermediate outputs of `make_examples` and `call_variants` stages can be found
-in the directory. After the command, you can find these files in the directory:
+FTPDIR=ftp://ftp-trace.ncbi.nlm.nih.gov/giab/ftp/release/AshkenazimTrio/HG003_NA24149_father/NISTv4.2.1/GRCh38
 
-```
-call_variants_output.tfrecord.gz
-gvcf.tfrecord-?????-of-?????.gz
-make_examples.tfrecord-?????-of-?????.gz
+curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed
+curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz
+curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi
 ```
 
-## Benchmark HG003 chr20 output from DeepVariant
+### Download HG003 chr20 HiFi alignments
 
-We will use Genome-in-a-Bottle (GIAB) dataset to evaluate the performance of
-DeepVariant.
+We'll use HG003 chr20 HiFi reads publicly available from the [PrecisionFDA Truth v2 Challenge](https://precision.fda.gov/challenges/10).
 
-### Download Genome in a Bottle Benchmarks
+```bash
+mkdir -p input
+HTTPDIR=https://downloads.pacbcloud.com/public/dataset/HG003/deepvariant-case-study
 
-We will benchmark our variant calls against v4.2.1 of the Genome in a Bottle
-small variant benchmarks for HG003.
+curl ${HTTPDIR}/HG003.GRCh38.chr20.pFDA_truthv2.bam > input/HG003.GRCh38.chr20.pFDA_truthv2.bam
+curl ${HTTPDIR}/HG003.GRCh38.chr20.pFDA_truthv2.bam.bai > input/HG003.GRCh38.chr20.pFDA_truthv2.bam.bai
+```
+
+## Run DeepVariant on chromosome 20 alignments
 
 ```bash
-FTPDIR=ftp://ftp-trace.ncbi.nlm.nih.gov/giab/ftp/release/AshkenazimTrio/HG003_NA24149_father/NISTv4.2.1/GRCh38
+ulimit -u 10000 # https://stackoverflow.com/questions/52026652/openblas-blas-thread-init-pthread-create-resource-temporarily-unavailable/54746150#54746150
+BIN_VERSION="1.7.0"
+mkdir -p deepvariant_output
+
+singularity exec --bind /usr/lib/locale/ \
+  docker://google/deepvariant:${BIN_VERSION} \
+    /opt/deepvariant/bin/run_deepvariant \
+    --model_type PACBIO \
+    --ref reference/GRCh38_no_alt_analysis_set.fasta \
+    --reads input/HG003.GRCh38.chr20.pFDA_truthv2.bam \
+    --output_vcf deepvariant_output/output.vcf.gz \
+    --num_shards $(nproc) \
+    --regions chr20
+```
 
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed > ${INPUT_DIR}/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz > ${INPUT_DIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi > ${INPUT_DIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi
+NOTE: If you want to run each of the steps separately, add `--dry_run=true`
+to the command above to figure out what flags you need in each step. Based on
+the different model types, different flags are needed in the `make_examples`
+step.
 
-TRUTH_VCF="HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz"
-TRUTH_BED="HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed"
-```
+## Benchmark output
 
 ```bash
-sudo docker pull jmcdani20/hap.py:v0.3.12
-
-sudo docker run \
-  -v "${INPUT_DIR}":"${INPUT_DIR}" \
-  -v "${OUTPUT_DIR}":"${OUTPUT_DIR}" \
-  -v "${PWD}/happy:/happy" \
-  jmcdani20/hap.py:v0.3.12 /opt/hap.py/bin/hap.py \
-  "${INPUT_DIR}/${TRUTH_VCF}" \
-  "${OUTPUT_DIR}/${OUTPUT_VCF}" \
-  -f "${INPUT_DIR}/${TRUTH_BED}" \
-  -r "${INPUT_DIR}/${REF}" \
-  -o "${OUTPUT_DIR}/hg003.pacbio.chr20.happy.output" \
-  --engine=vcfeval \
-  --pass-only \
-  -l "${REGION}"
+mkdir -p happy
+
+singularity exec docker://jmcdani20/hap.py:v0.3.12 \
+    /opt/hap.py/bin/hap.py \
+        --threads $(nproc) \
+        -r reference/GRCh38_no_alt_analysis_set.fasta \
+        -f benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed \
+        -o happy/giab-comparison.v4.2.first_pass \
+        --engine=vcfeval \
+        --pass-only \
+        -l chr20 \
+        benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz \
+        deepvariant_output/output.vcf.gz
 ```
 
 Output:
@@ -147,8 +121,8 @@ Output:
 ```
 Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL        10628     10543        85        22403        74      11375     40     29       0.992002          0.993290        0.507744         0.992646                     NaN                     NaN                   1.748961                   2.138647
-INDEL   PASS        10628     10543        85        22403        74      11375     40     29       0.992002          0.993290        0.507744         0.992646                     NaN                     NaN                   1.748961                   2.138647
-  SNP    ALL        70166     70101        65       105602        71      35342     12     12       0.999074          0.998989        0.334672         0.999032                2.296566                1.713281                   1.883951                   1.503192
-  SNP   PASS        70166     70101        65       105602        71      35342     12     12       0.999074          0.998989        0.334672         0.999032                2.296566                1.713281                   1.883951                   1.503192
+INDEL    ALL        10628     10551        77        22590        69      11527     39     29       0.992755          0.993763        0.510270         0.993259                     NaN                     NaN                   1.748961                   2.275319
+INDEL   PASS        10628     10551        77        22590        69      11527     39     29       0.992755          0.993763        0.510270         0.993259                     NaN                     NaN                   1.748961                   2.275319
+  SNP    ALL        70166     70141        25        98780        23      28559      5     11       0.999644          0.999672        0.289117         0.999658                2.296566                1.823452                   1.883951                   1.913585
+  SNP   PASS        70166     70141        25        98780        23      28559      5     11       0.999644          0.999672        0.289117         0.999658                2.296566                1.823452                   1.883951                   1.913585
 ```
diff --git a/docs/deepvariant-quick-start.md b/docs/deepvariant-quick-start.md
index c9005452..062a0377 100644
--- a/docs/deepvariant-quick-start.md
+++ b/docs/deepvariant-quick-start.md
@@ -33,7 +33,7 @@ If you want to compile the DeepVariant binaries for yourself, we also have a
 ### Get Docker image
 
 ```bash
-BIN_VERSION="1.8.0"
+BIN_VERSION="1.7.0"
 
 sudo apt -y update
 sudo apt-get -y install docker.io
@@ -124,7 +124,6 @@ sudo docker run \
   google/deepvariant:"${BIN_VERSION}" \
   /opt/deepvariant/bin/run_deepvariant \
   --model_type=WGS \
-  --vcf_stats_report=true \
   --ref=/input/ucsc.hg19.chr20.unittest.fasta \
   --reads=/input/NA12878_S1.chr20.10_10p1mb.bam \
   --regions "chr20:10,000,000-10,010,000" \
@@ -195,7 +194,6 @@ singularity run -B /usr/lib/locale/:/usr/lib/locale/ \
   docker://google/deepvariant:"${BIN_VERSION}" \
   /opt/deepvariant/bin/run_deepvariant \
   --model_type=WGS \ **Replace this string with exactly one of the following [WGS,WES,PACBIO,ONT_R104,HYBRID_PACBIO_ILLUMINA]**
-  --vcf_stats_report=true \ 
   --ref="${INPUT_DIR}"/ucsc.hg19.chr20.unittest.fasta \
   --reads="${INPUT_DIR}"/NA12878_S1.chr20.10_10p1mb.bam \
   --regions "chr20:10,000,000-10,010,000" \
@@ -267,16 +265,16 @@ You should see output similar to the following.
 ```
 Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL            4         4         0           13         0          9      0      0       1.000000               1.0        0.692308         1.000000                     NaN                     NaN                   0.333333                   1.000000
-INDEL   PASS            4         4         0           13         0          9      0      0       1.000000               1.0        0.692308         1.000000                     NaN                     NaN                   0.333333                   1.000000
-  SNP    ALL           44        43         1           59         0         16      0      0       0.977273               1.0        0.271186         0.988506                     1.2                    1.36                   0.333333                   0.340909
-  SNP   PASS           44        43         1           59         0         16      0      0       0.977273               1.0        0.271186         0.988506                     1.2                    1.36                   0.333333                   0.340909
+INDEL    ALL            4         4         0           13         0          9      0      0            1.0               1.0        0.692308              1.0                     NaN                     NaN                   0.333333                   1.000000
+INDEL   PASS            4         4         0           13         0          9      0      0            1.0               1.0        0.692308              1.0                     NaN                     NaN                   0.333333                   1.000000
+  SNP    ALL           44        44         0           60         0         16      0      0            1.0               1.0        0.266667              1.0                     1.2                1.307692                   0.333333                   0.363636
+  SNP   PASS           44        44         0           60         0         16      0      0            1.0               1.0        0.266667              1.0                     1.2                1.307692                   0.333333                   0.363636
 ```
 
 [BAM]: http://genome.sph.umich.edu/wiki/BAM
 [BWA]: https://academic.oup.com/bioinformatics/article/25/14/1754/225615/Fast-and-accurate-short-read-alignment-with
 [docker build]: https://docs.docker.com/engine/reference/commandline/build/
-[Dockerfile]: https://github.com/google/deepvariant/blob/r1.8/Dockerfile
+[Dockerfile]: https://github.com/google/deepvariant/blob/r1.7/Dockerfile
 [FASTA]: https://en.wikipedia.org/wiki/FASTA_format
 [Quick Start in r0.7]: https://github.com/google/deepvariant/blob/r0.7/docs/deepvariant-quick-start.md
 [VCF]: https://samtools.github.io/hts-specs/VCFv4.3.pdf
diff --git a/docs/deepvariant-vg-case-study.md b/docs/deepvariant-vg-case-study.md
index 24f0a551..86a38ef6 100644
--- a/docs/deepvariant-vg-case-study.md
+++ b/docs/deepvariant-vg-case-study.md
@@ -4,7 +4,7 @@
 This is an example to run `vg giraffe`, so we can go from FASTQs --> BAM.
 
 For simplicity and consistency, we run the following with a
-[Google Cloud instance with 96 cores](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform).
+[Google Cloud instance with 64 cores](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform).
 
 I added more disks because 300G is not enough for the example below. I changed
 it to `--boot-disk-size "1000"`.
@@ -184,11 +184,11 @@ And then, run DeepVariant.
 [DeepVariant Case Study](deepvariant-case-study.md).)
 
 ```bash
-BIN_VERSION="1.8.0"
+BIN_VERSION="1.7.0"
 
 sudo docker pull google/deepvariant:"${BIN_VERSION}"
 
-time sudo docker run \
+time sudo docker run --rm \
   -v "${DATA_DIR}":"${DATA_DIR}" \
   -v "${PWD}:${PWD}" \
   google/deepvariant:"${BIN_VERSION}" \
@@ -204,9 +204,9 @@ time sudo docker run \
 
 Stage                            | Time (minutes)
 -------------------------------- | -----------------
-make_examples                    | 59m19.845s
-call_variants                    | 49m41.643s
-postprocess_variants (with gVCF) | 7m46.195s
+make_examples                    | 101m31.676s
+call_variants                    | 215m33.631s
+postprocess_variants (with gVCF) | 24m44.242s
 
 
 ### Run hap.py
@@ -244,16 +244,21 @@ Output:
 ```
 Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL       504501    502210      2291       954974      1522     429900    956    362       0.995459          0.997101        0.450169         0.996279                     NaN                     NaN                   1.489759                   1.942299
-INDEL   PASS       504501    502210      2291       954974      1522     429900    956    362       0.995459          0.997101        0.450169         0.996279                     NaN                     NaN                   1.489759                   1.942299
-  SNP    ALL      3327496   3316336     11160      3823082      4229     500683   1696    356       0.996646          0.998727        0.130963         0.997686                2.102576                1.990152                   1.535137                   1.449299
-  SNP   PASS      3327496   3316336     11160      3823082      4229     500683   1696    356       0.996646          0.998727        0.130963         0.997686                2.102576                1.990152                   1.535137                   1.449299
+INDEL    ALL       504501    502283      2218       958181      1471     433079    913    351       0.995604          0.997199        0.451980         0.996400                     NaN                     NaN                   1.489759                   1.954212
+INDEL   PASS       504501    502283      2218       958181      1471     433079    913    351       0.995604          0.997199        0.451980         0.996400                     NaN                     NaN                   1.489759                   1.954212
+  SNP    ALL      3327496   3316374     11122      3820052      4177     497662   1686    344       0.996658          0.998743        0.130276         0.997699                2.102576                1.991054                   1.535137                   1.457635
+  SNP   PASS      3327496   3316374     11122      3820052      4177     497662   1686    344       0.996658          0.998743        0.130276         0.997699                2.102576                1.991054                   1.535137                   1.457635
 ```
 
+| Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
+| ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
+| INDEL | 502283   | 2218     | 1471     | 0.995604      | 0.997199         | 0.9964          |
+| SNP   | 3316374  | 11122    | 4177     | 0.996658      | 0.998743         | 0.997699        |
+
 This can be compared with
-https://github.com/google/deepvariant/blob/r1.8/docs/metrics.md#accuracy.
+https://github.com/google/deepvariant/blob/r1.7/docs/metrics.md#accuracy.
 
 Which shows that `vg giraffe` improves F1:
 
-- Indel F1: 0.995945 --> 0.996279
-- SNP F1: 0.996213 --> 0.997686
+- Indel F1: 0.995998 --> 0.9964
+- SNP F1: 0.996237 --> 0.997699
diff --git a/docs/metrics-deeptrio.md b/docs/metrics-deeptrio.md
index a2a5f306..0afcb9d0 100644
--- a/docs/metrics-deeptrio.md
+++ b/docs/metrics-deeptrio.md
@@ -2,18 +2,6 @@
 
 ## WGS (Illumina)
 
-## Setup
-
-The runtime and accuracy reported in this page are generated using
-`n2-standard-96` GCP instances which has the following configuration:
-
-```bash
-GCP instance type: n2-standard-96
-CPUs: 96-core (vCPU)
-Memory: 384GiB
-GPUs: 0
-```
-
 ### Runtime
 
 Runtime is on HG002/HG003/HG004 (all chromosomes).
@@ -21,15 +9,15 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Wall time (minutes)
 -------------------------------- | -----------------
-make_examples                    | 172m53.87s
-call_variants: HG002             | 269m26.55s
-call_variants: HG003             | 268m2.29s
-call_variants: HG004             | 270m22.72s
-postprocess_variants (parallel)  | 34m12.36s; 35m4.75s; 35m8.14s
-vcf_stats_report(optional):HG002 | 6m36.58s
-vcf_stats_report(optional):HG003 | 6m39.92s
-vcf_stats_report(optional):HG003 | 6m40.64s
-total                            | 1028m3.08s (17h08m3.08s)
+make_examples                    | 381m27.76s
+call_variants: HG002             | 376m44.92s
+call_variants: HG003             | 379m55.40s
+call_variants: HG004             | 380m27.95s
+postprocess_variants (parallel)  | 45m24.88s; 47m0.02s; 47m46.29s
+vcf_stats_report(optional):HG002 | 9m20.03s
+vcf_stats_report(optional):HG003 | 9m29.88s
+vcf_stats_report(optional):HG003 | 9m29.88s
+total                            | 1576m56.29s (26h16m56.29s)
 
 ### Accuracy
 
@@ -59,13 +47,13 @@ truth), which was held out while training.
 | SNP   | 71445    | 214      | 48       | 0.997014      | 0.999329         | 0.99817         |
 
 * See VCF stats report (for all chromosomes)
-  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WGS/HG002.output.visual_report.html)
-  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WGS/HG003.output.visual_report.html)
-  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WGS/HG004.output.visual_report.html)
+  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WGS/HG002.output.visual_report.html)
+  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WGS/HG003.output.visual_report.html)
+  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WGS/HG004.output.visual_report.html)
 
 ## PacBio (HiFi)
 
-Read haplotagging in DeepTrio PacBio is on by default. You no longer
+In v1.7.0, we introduced read haplotagging in DeepTrio PacBio. You no longer
 need to run DeepVariant->WhatsHap->DeepTrio, and can just run DeepTrio once.
 
 ### Runtime
@@ -75,20 +63,20 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Wall time (minutes)
 -------------------------------- | -------------------
-make_examples                    | 16m48.88s+288m15.08s
-call_variants: HG002             | 279m5.76s
-call_variants: HG003             | 274m47.90s
-call_variants: HG004             | 283m37.89s
-postprocess_variants (parallel)  | 44m12.28s; 51m39.02s; 51m52.66s
-vcf_stats_report(optional):HG002 | 6m49.94s
-vcf_stats_report(optional):HG003 | 6m53.24s
-vcf_stats_report(optional):HG003 | 7m19.57s
-total                            | 1206m35.85s (20h6m35.85s)
+make_examples                    | 50m35.96s+621m56.74s
+call_variants: HG002             | 364m39.93s
+call_variants: HG003             | 368m0.84s
+call_variants: HG004             | 372m44.77s
+postprocess_variants (parallel)  | 58m52.92s; 66m36.57s; 67m35.91s
+vcf_stats_report(optional):HG002 | 9m33.72s
+vcf_stats_report(optional):HG003 | 9m48.13s
+vcf_stats_report(optional):HG003 | 10m1.22s
+total                            | 1858m53.78s (30h58m53.78s)
 
 * See VCF stats report (for all chromosomes)
-  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/PACBIO/HG002.output.visual_report.html)
-  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/PACBIO/HG003.output.visual_report.html)
-  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/PACBIO/HG004.output.visual_report.html)
+  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/PACBIO/HG002.output.visual_report.html)
+  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/PACBIO/HG003.output.visual_report.html)
+  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/PACBIO/HG004.output.visual_report.html)
 
 ### Accuracy
 
@@ -108,7 +96,6 @@ truth), which was held out while training.
 | ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
 | INDEL | 10577    | 51       | 77       | 0.995201      | 0.993089         | 0.994144        |
 | SNP   | 70143    | 23       | 35       | 0.999672      | 0.999502         | 0.999587        |
-
 #### HG004:
 
 | Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
@@ -125,15 +112,15 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Wall time (minutes)
 -------------------------------- | --------------
-make_examples                    | 7m11.47s
-call_variants: HG002             | 3m49.25s
-call_variants: HG003             | 3m53.32s
-call_variants: HG004             | 3m52.68s
-postprocess_variants (parallel)  | 0m40.52s; 0m42.09s; 0m42.30s
-vcf_stats_report(optional):HG002 | 0m5.65s
-vcf_stats_report(optional):HG003 | 0m5.69s
-vcf_stats_report(optional):HG003 | 0m7.15s
-total                            | 20m6.26s
+make_examples                    | 15m6.77s
+call_variants: HG002             | 5m16.13s
+call_variants: HG003             | 5m18.83s
+call_variants: HG004             | 5m19.09s
+postprocess_variants (parallel)  | 0m51.70s; 0m52.27s; 0m53.73s
+vcf_stats_report(optional):HG002 | 0m7.84s
+vcf_stats_report(optional):HG003 | 0m8.01s
+vcf_stats_report(optional):HG003 | 0m10.00s
+total                            | 32m20.47s
 
 ### Accuracy
 
@@ -163,14 +150,14 @@ truth), which was held out while training.
 | SNP   | 676      | 3        | 0        | 0.995582      | 1.0              | 0.997786        |
 
 * See VCF stats report (for all chromosomes)
-  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WES/HG002.output.visual_report.html)
-  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WES/HG003.output.visual_report.html)
-  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.8.0/WES/HG004.output.visual_report.html)
+  - [HG002](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WES/HG002.output.visual_report.html)
+  - [HG003](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WES/HG003.output.visual_report.html)
+  - [HG004](https://storage.googleapis.com/deepvariant/visual_reports/DeepTrio/1.7.0/WES/HG004.output.visual_report.html)
 
 ## How to reproduce the metrics on this page
 
 For simplicity and consistency, we report runtime with a
-[CPU instance with 96 CPUs](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform)
+[CPU instance with 64 CPUs](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform)
 For bigger datasets (WGS and PACBIO), we used bigger disk size (900G).
 This is NOT the fastest or cheapest configuration.
 
@@ -179,7 +166,7 @@ Use `gcloud compute ssh` to log in to the newly created instance.
 Download and run any of the following case study scripts:
 
 ```
-curl -O https://raw.githubusercontent.com/google/deepvariant/r1.8/scripts/inference_deeptrio.sh
+curl -O https://raw.githubusercontent.com/google/deepvariant/r1.7/scripts/inference_deeptrio.sh
 
 # WGS
 bash inference_deeptrio.sh --model_preset WGS
@@ -197,4 +184,4 @@ DeepTrio. The runtime numbers reported above are the average of 5 runs each.
 The accuracy metrics come from the hap.py summary.csv output file.
 The runs are deterministic so all 5 runs produced the same output.
 
-[CPU instance with 96 CPUs]: deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform
+[CPU instance with 64 CPUs]: deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform
diff --git a/docs/metrics.md b/docs/metrics.md
index fadb0c43..ad45a5fb 100644
--- a/docs/metrics.md
+++ b/docs/metrics.md
@@ -1,17 +1,5 @@
 # Runtime and accuracy metrics for all release models
 
-## Setup
-
-The runtime and accuracy reported in this page are generated using
-`n2-standard-96` GCP instances which has the following configuration:
-
-```bash
-GCP instance type: n2-standard-96
-CPUs: 96-core (vCPU)
-Memory: 384GiB
-GPUs: 0
-```
-
 ## WGS (Illumina)
 
 ### Runtime
@@ -21,11 +9,11 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | ------------------
-make_examples                    | 54m58.62s
-call_variants                    | 38m45.29s
-postprocess_variants (with gVCF) | 8m22.88s
-vcf_stats_report (optional)      | 5m37.52s (optional)
-total                            | 113m11.70s (1h53m11.70s)
+make_examples                    | 114m35.42s
+call_variants                    | 65m6.69s
+postprocess_variants (with gVCF) | 12m7.55s
+vcf_stats_report (optional)      | 9m9.16s
+total                            | 208m46.70s (3h28m46.70s)
 
 ### Accuracy
 
@@ -37,7 +25,7 @@ held out while training.
 | INDEL | 501653   | 2848     | 1289     | 0.994355      | 0.997541         | 0.995945        |
 | SNP   | 3306740  | 20756    | 4386     | 0.993762      | 0.998676         | 0.996213        |
 
-[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.8.0/WGS/deepvariant.output.visual_report.html)
+[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.7.0/WGS/deepvariant.output.visual_report.html)
 
 ## WES (Illumina)
 
@@ -48,11 +36,11 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | -----------------
-make_examples                    | 3m17.64s
-call_variants                    | 0m56.36s
-postprocess_variants (with gVCF) | 0m39.27s
-vcf_stats_report (optional)      | 0m4.93s (optional)
-total                            | 5m26.00s
+make_examples                    | 6m35.96s
+call_variants                    | 1m31.70s
+postprocess_variants (with gVCF) | 0m58.50s
+vcf_stats_report (optional)      | 0m7.67s
+total                            | 9m38.11s
 
 ### Accuracy
 
@@ -61,26 +49,13 @@ held out while training.
 
 | Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
 | ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
-| INDEL | 1020     | 31       | 7        | 0.970504      | 0.993327         | 0.981783        |
-| SNP   | 24984    | 295      | 60       | 0.98833       | 0.997604         | 0.992946        |
+| INDEL | 1020     | 31       | 12       | 0.970504      | 0.988615         | 0.979476        |
+| SNP   | 24982    | 297      | 64       | 0.988251      | 0.997445         | 0.992827        |
 
-[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.8.0/WES/deepvariant.output.visual_report.html)
+[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.7.0/WES/deepvariant.output.visual_report.html)
 
 ## PacBio (HiFi)
 
-### Updated dataset in release 1.8.0
-
-In release 1.8.0, we have updated the PacBio test data from HG003 Sequel-II to
-latest Revio with SPRQ chemistry data to showcase performance on the updated
-platform and chemistry. The numbers reported here are generated using the bam
-that can be found in:
-
-```bash
-gs://deepvariant/pacbio-case-study-testdata/HG003.SPRQ.pacbio.GRCh38.nov2024.bam
-```
-
-Which is also available through [here](https://downloads.pacbcloud.com/public/revio/2024Q4/WGS/GIAB_trio/HG003/analysis/GRCh38.m84039_241002_000337_s3.hifi_reads.bc2020.bam).
-
 ### Runtime
 
 Runtime is on HG003 (all chromosomes).
@@ -88,11 +63,11 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | -------------------
-make_examples                    | 31m51.00s
-call_variants                    | 34m49.62s
-postprocess_variants (with gVCF) | 5m28.59s
-vcf_stats_report (optional)      | 5m36.49s (optional)
-total                            | 86m50.09s (1h26m50.09s)
+make_examples                    | 77m48.24s
+call_variants                    | 82m33.11s
+postprocess_variants (with gVCF) | 10m27.86s
+vcf_stats_report (optional)      | 10m1.56s
+total                            | 190m21.52s (3h10m21.52s)
 
 ### Accuracy
 
@@ -104,11 +79,10 @@ to run DeepVariant once.
 
 | Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
 | ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
-| INDEL | 500955   | 3546     | 3373     | 0.992971      | 0.993555         | 0.993263        |
-| SNP   | 3321825  | 5670     | 4263     | 0.998296      | 0.99872          | 0.998508        |
-
+| INDEL | 501727   | 2774     | 2643     | 0.994501      | 0.994968         | 0.994735        |
+| SNP   | 3324603  | 2892     | 2056     | 0.999131      | 0.999382         | 0.999257        |
 
-[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.8.0/PACBIO/deepvariant.output.visual_report.html)
+[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.7.0/PACBIO/deepvariant.output.visual_report.html)
 
 ## ONT_R104
 
@@ -119,11 +93,11 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | --------------------
-make_examples                    | 53m25.60s
-call_variants                    | 55m24.86s
-postprocess_variants (with gVCF) | 7m17.83s
-vcf_stats_report (optional)      | 6m30.29s (optional)
-total                            | 127m56.44s (2h7m56.44s)
+make_examples                    | 125m50.85s
+call_variants                    | 107m45.55s
+postprocess_variants (with gVCF) | 11m30.19s
+vcf_stats_report (optional)      | 11m0.03s
+total                            | 258m4.89s (4h18m4.89s)
 
 ### Accuracy
 
@@ -132,11 +106,10 @@ truth), which was held out while training.
 
 | Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
 | ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
-| INDEL | 452010   | 52491    | 40289    | 0.895955      | 0.920501         | 0.908062        |
-| SNP   | 3321452  | 6032     | 3942     | 0.998187      | 0.998815         | 0.998501        |
+| INDEL | 443724   | 60777    | 42938    | 0.87953       | 0.914541         | 0.896694        |
+| SNP   | 3319440  | 8044     | 5005     | 0.997583      | 0.998495         | 0.998039        |
 
-
-[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.8.0/ONT_R104/deepvariant.output.visual_report.html)
+[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.7.0/ONT_R104/deepvariant.output.visual_report.html)
 
 ## Hybrid (Illumina + PacBio HiFi)
 
@@ -146,12 +119,12 @@ Runtime is on HG003 (all chromosomes).
 Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
--------------------------------- | ------------------
-make_examples                    | 71m52.43s
-call_variants                    | 51m42.37s
-postprocess_variants (with gVCF) | 4m6.13s
-vcf_stats_report (optional)      | 5m18.39s (optional)
-total                            | 151m34.49s (2h31m34.49s)
+-------------------------------- | -------------------
+make_examples                    | 160m29.82s
+call_variants                    | 90m45.03s
+postprocess_variants (with gVCF) | 6m43.66s
+vcf_stats_report (optional)      | 9m31.77s
+total                            | 278m59.35s (4h38m59.35s)
 
 ### Accuracy
 
@@ -163,7 +136,7 @@ out while training the hybrid model.
 | INDEL | 503109   | 1392     | 2636     | 0.997241      | 0.995022         | 0.99613         |
 | SNP   | 3324179  | 3316     | 2049     | 0.999003      | 0.999384         | 0.999194        |
 
-[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.8.0/HYBRID/deepvariant.output.visual_report.html)
+[See VCF stats report.](https://storage.googleapis.com/deepvariant/visual_reports/DeepVariant/1.7.0/HYBRID/deepvariant.output.visual_report.html)
 
 ## Inspect outputs that produced the metrics above
 
@@ -179,7 +152,7 @@ https://42basepairs.com/browse/gs/deepvariant/case-study-outputs
 ## How to reproduce the metrics on this page
 
 For simplicity and consistency, we report runtime with a
-[CPU instance with 96 CPUs](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform)
+[CPU instance with 64 CPUs](deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform)
 This is NOT the fastest or cheapest configuration.
 
 Use `gcloud compute ssh` to log in to the newly created instance.
@@ -188,7 +161,7 @@ Download and run any of the following case study scripts:
 
 ```
 # Get the script.
-curl -O https://raw.githubusercontent.com/google/deepvariant/r1.8/scripts/inference_deepvariant.sh
+curl -O https://raw.githubusercontent.com/google/deepvariant/r1.7/scripts/inference_deepvariant.sh
 
 # WGS
 bash inference_deepvariant.sh --model_preset WGS
@@ -211,5 +184,5 @@ DeepVariant. The runtime numbers reported above are the average of 5 runs each.
 The accuracy metrics come from the hap.py summary.csv output file.
 The runs are deterministic so all 5 runs produced the same output.
 
-[CPU instance with 96 CPUs]: deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform
+[CPU instance with 64 CPUs]: deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform
 
diff --git a/docs/pangenome-aware-metrics.md b/docs/pangenome-aware-metrics.md
index 9b86e9fb..da80f67d 100644
--- a/docs/pangenome-aware-metrics.md
+++ b/docs/pangenome-aware-metrics.md
@@ -1,20 +1,16 @@
 # Runtime and accuracy metrics for Pangenome-aware DeepVariant
 
-## Setup
+## How to reproduce the metrics on this page
 
-The runtime and accuracy reported in this page are generated using
-`n2-standard-96` GCP instances which has the following configuration:
+We report runtime with a n1-highmem-96 machine, and we ran with
+`--num_shards 50` to avoid OOM.
 
-```bash
-GCP instance type: n2-standard-96
-CPUs: 96-core (vCPU)
-Memory: 384GiB
-GPUs: 0
-```
+This is NOT the fastest or cheapest configuration. We plan to improve the high
+memory usage in the future.
 
 ## WGS (Illumina)
 
-BAM: We used the VG Giraffe mapped BAM file. The file is available here:
+BAM: We used the VG Giraffe mapped BAM file. You can find it in:
 `gs://deepvariant/vg-case-study/HG003.novaseq.pcr-free.35x.vg-1.55.0.bam`
 
 ### Runtime
@@ -24,21 +20,24 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | ------------------
-make_examples                    | 85m58.66s
-call_variants                    | 313m49.80s
-postprocess_variants (with gVCF) | 7m52.00s
-vcf_stats_report (optional)      | 5m48.88s
-total                            | 423m6.93s (7h3m6.93s)
+make_examples                    | 170m2.87s
+call_variants                    | 522m44.28s
+postprocess_variants (with gVCF) | 10m20.44s
+vcf_stats_report (optional)      | 9m4.78s
+total                            | 721m14.42s (12h1m14.42s)
 
 ### Accuracy
 
 hap.py results on HG003 (all chromosomes, using NIST v4.2.1 truth), which was
 held out while training.
 
+TODO: Update this table after retraining with pangenome=GBZ. Note that
+these numbers are not a correct base for future comparison.
+
 | Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
 | ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
-| INDEL | 502338   | 2163     | 1511     | 0.995713      | 0.997122         | 0.996417        |
-| SNP   | 3320044  | 7452     | 4735     | 0.99776       | 0.998577         | 0.998168        |
+| INDEL | 501918   | 2583     | 1757     | 0.99488       | 0.996652         | 0.995765        |
+| SNP   | 3318596  | 8900     | 8158     | 0.997325      | 0.997549         | 0.997437        |
 
 ## WES (Illumina)
 
@@ -49,46 +48,16 @@ Reported runtime is an average of 5 runs.
 
 Stage                            | Time (minutes)
 -------------------------------- | -----------------
-make_examples                    | 5m4.22s
-call_variants                    | 1m50.67s
-postprocess_variants (with gVCF) | 0m38.74s
-vcf_stats_report (optional)      | 0m4.91s
-total                            | 10m20.44s
+make_examples                    | TODO
+call_variants                    | TODO
+postprocess_variants (with gVCF) | TODO
+vcf_stats_report (optional)      | TODO
+total                            | TODO
 
 ### Accuracy
 
 hap.py results on HG003 (all chromosomes, using NIST v4.2.1 truth), which was
 held out while training.
 
-| Type  | TRUTH.TP | TRUTH.FN | QUERY.FP | METRIC.Recall | METRIC.Precision | METRIC.F1_Score |
-| ----- | -------- | -------- | -------- | ------------- | ---------------- | --------------- |
-| INDEL | 1020     | 31       | 15       | 0.970504      | 0.985782         | 0.978083        |
-| SNP   | 25006    | 273      | 54       | 0.989201      | 0.997845         | 0.993504        |
-
-## How to reproduce the metrics on this page
-
-For simplicity and consistency, we report runtime with a
-[CPU instance with 96 CPUs](https://github.com/google/deepvariant/blob/r1.8/docs/deepvariant-details.md#command-for-a-cpu-only-machine-on-google-cloud-platform)
-This is NOT the fastest or cheapest configuration.
-
-Use `gcloud compute ssh` to log in to the newly created instance.
-
-Download and run any of the following case study scripts:
-
-```
-# Get the script.
-curl -O https://raw.githubusercontent.com/google/deepvariant/r1.8/scripts/inference_deepvariant.sh
-
-# WGS-PANGENOME
-bash inference_deepvariant.sh --model_preset WGS_PANGENOME
-
-# WGS-PANGENOME
-bash inference_deepvariant.sh --model_preset WES_PANGENOME
-```
-
-Runtime metrics are taken from the resulting log after each stage of
-DeepVariant.
-
-The accuracy metrics came from the hap.py program.
-
+TODO
 
diff --git a/docs/pangenome-aware-wes-bwa-case-study.md b/docs/pangenome-aware-wes-bwa-case-study.md
deleted file mode 100644
index 4f924dc7..00000000
--- a/docs/pangenome-aware-wes-bwa-case-study.md
+++ /dev/null
@@ -1,166 +0,0 @@
-# DeepVariant Pangenome-aware WES case study (mapped with BWA)
-
-To make it faster to run over this case study, we run only on chromosome 20.
-
-## Prepare environment
-
-### Tools
-
-[Docker](https://docs.docker.com/get-docker/) will be used to run DeepVariant
-and [hap.py](https://github.com/illumina/hap.py),
-
-### Download Reference
-
-We will be using GRCh38 for this case study.
-
-```bash
-mkdir -p reference
-
-FTPDIR=ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/000/001/405/GCA_000001405.15_GRCh38/seqs_for_alignment_pipelines.ucsc_ids
-
-curl ${FTPDIR}/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.gz | gunzip > reference/GRCh38_no_alt_analysis_set.fasta
-curl ${FTPDIR}/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna.fai > reference/GRCh38_no_alt_analysis_set.fasta.fai
-```
-
-### Download Genome in a Bottle Benchmarks
-
-We will benchmark our variant calls against v4.2.1 of the Genome in a Bottle
-small variant benchmarks for HG003.
-
-```bash
-mkdir -p benchmark
-
-FTPDIR=ftp://ftp-trace.ncbi.nlm.nih.gov/giab/ftp/release/AshkenazimTrio/HG003_NA24149_father/NISTv4.2.1/GRCh38
-
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz
-curl ${FTPDIR}/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi > benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz.tbi
-```
-
-### Download HG003 chr20 BAM
-
-We'll use HG003 Illumina WES reads.
-
-```bash
-mkdir -p input
-HTTPDIR=https://storage.googleapis.com/deepvariant/exome-case-study-testdata
-
-curl ${HTTPDIR}/HG003.novaseq.wes_idt.100x.dedup.bam > input/HG003.novaseq.wes_idt.100x.dedup.bam
-curl ${HTTPDIR}/HG003.novaseq.wes_idt.100x.dedup.bam.bai > input/HG003.novaseq.wes_idt.100x.dedup.bam.bai
-```
-
-### Download capture target BED file
-
-In this case study we'll use `idt_capture_novogene.grch38.bed` as the capture
-target BED file. For evaluation, `hap.py` will intersect this BED with the GIAB
-confident regions.
-
-```bash
-HTTPDIR=https://storage.googleapis.com/deepvariant/exome-case-study-testdata
-
-curl ${HTTPDIR}/idt_capture_novogene.grch38.bed > input/idt_capture_novogene.grch38.bed
-```
-
-### Download GBZ built for GRCh38
-
-```bash
-mkdir -p input
-HTTPDIR=https://s3-us-west-2.amazonaws.com/human-pangenomics/pangenomes/freeze/freeze1/minigraph-cactus/hprc-v1.1-mc-grch38
-
-curl ${HTTPDIR}/hprc-v1.1-mc-grch38.gbz > input/hprc-v1.1-mc-grch38.gbz
-```
-
-## Running Pangenome-aware DeepVariant with one command
-
-DeepVariant pipeline consists of 3 steps: `make_examples`, `call_variants`, and
-`postprocess_variants`. You can now run DeepVariant with one command using the
-`run_pangenome_aware_deepvariant` script.
-
-### Running on a CPU-only machine
-
-In this example, we used a
-[n2-standard-96](https://cloud.google.com/compute/docs/general-purpose-machines)
-machine.
-
-```bash
-mkdir -p output
-mkdir -p output/intermediate_results_dir
-
-BIN_VERSION="pangenome_aware_deepvariant-1.8.0"
-
-sudo docker pull google/deepvariant:"${BIN_VERSION}"
-
-sudo docker run \
-  -v "${PWD}/input":"/input" \
-  -v "${PWD}/output":"/output" \
-  -v "${PWD}/reference":"/reference" \
-  --shm-size 12gb \
-  google/deepvariant:"${BIN_VERSION}" \
-  /opt/deepvariant/bin/run_pangenome_aware_deepvariant \
-  --model_type WES \
-  --ref /reference/GRCh38_no_alt_analysis_set.fasta \
-  --reads /input/HG003.novaseq.wes_idt.100x.dedup.bam  \
-  --pangenome /input/hprc-v1.1-mc-grch38.gbz \
-  --output_vcf /output/HG003.output.vcf.gz \
-  --output_gvcf /output/HG003.output.g.vcf.gz \
-  --num_shards $(nproc) \
-  --regions chr20 \
-  --intermediate_results_dir /output/intermediate_results_dir
-```
-
-
-By specifying `--model_type WES`, you'll be using a model that is best
-suited for short-read WES data.
-
-NOTE: If you want to run each of the steps separately, add `--dry_run=true`
-to the command above to figure out what flags you need in each step.
-
-`--intermediate_results_dir` flag is optional. By specifying it, the
-intermediate outputs can be found in the directory. After the command, you can
-find these intermediate files in the directory:
-
-```
-call_variants_output-?????-of-?????.tfrecord.gz
-gvcf.tfrecord-?????-of-?????.gz
-make_examples_pangenome_aware_dv.tfrecord-?????-of-?????.gz
-```
-
-For running on GPU machines, or using Singularity instead of Docker, see
-[Quick Start](deepvariant-quick-start.md).
-
-## Benchmark on chr20
-
-```bash
-mkdir -p happy
-
-sudo docker pull jmcdani20/hap.py:v0.3.12
-
-sudo docker run \
-  -v "${PWD}/benchmark":"/benchmark" \
-  -v "${PWD}/input":"/input" \
-  -v "${PWD}/output":"/output" \
-  -v "${PWD}/reference":"/reference" \
-  -v "${PWD}/happy:/happy" \
-  jmcdani20/hap.py:v0.3.12 \
-  /opt/hap.py/bin/hap.py \
-  /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz \
-  /output/HG003.output.vcf.gz \
-  -f /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed \
-  -T /input/idt_capture_novogene.grch38.bed \
-  -r /reference/GRCh38_no_alt_analysis_set.fasta \
-  -o /happy/happy.output \
-  --engine=vcfeval \
-  --pass-only \
-  -l chr20
-```
-
-Output:
-
-```
-Benchmarking Summary:
-Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL           29        29         0           41         0         11      0      0        1.00000               1.0        0.268293         1.000000                     NaN                     NaN                   3.000000                   2.727273
-INDEL   PASS           29        29         0           41         0         11      0      0        1.00000               1.0        0.268293         1.000000                     NaN                     NaN                   3.000000                   2.727273
-  SNP    ALL          685       683         2          704         0         21      0      0        0.99708               1.0        0.029830         0.998538                 3.28125                3.266667                   1.795918                   1.838710
-  SNP   PASS          685       683         2          704         0         21      0      0        0.99708               1.0        0.029830         0.998538                 3.28125                3.266667                   1.795918                   1.838710
-```
diff --git a/docs/pangenome-aware-wgs-bwa-case-study.md b/docs/pangenome-aware-wgs-bwa-case-study.md
index e2a4f9f5..e3c8380b 100644
--- a/docs/pangenome-aware-wgs-bwa-case-study.md
+++ b/docs/pangenome-aware-wgs-bwa-case-study.md
@@ -68,31 +68,32 @@ DeepVariant pipeline consists of 3 steps: `make_examples`, `call_variants`, and
 ### Running on a CPU-only machine
 
 In this example, we used a
-[n2-standard-96](https://cloud.google.com/compute/docs/general-purpose-machines)
-machine.
+[n1-standard-64](https://cloud.google.com/compute/docs/general-purpose-machines#n1-standard)
+machine. Because reading in GBZ takes a lot of memory, we will run with
+`--num_shards 18` below.
 
 ```bash
 mkdir -p output
 mkdir -p output/intermediate_results_dir
 
-BIN_VERSION="pangenome_aware_deepvariant-1.8.0"
+BIN_VERSION="1.7.0"
+DOCKER=google/deepvariant:"${BIN_VERSION}"
 
-sudo docker pull google/deepvariant:"${BIN_VERSION}"
 
 sudo docker run \
   -v "${PWD}/input":"/input" \
   -v "${PWD}/output":"/output" \
   -v "${PWD}/reference":"/reference" \
   --shm-size 12gb \
-  google/deepvariant:"${BIN_VERSION}" \
+  ${DOCKER} \
   /opt/deepvariant/bin/run_pangenome_aware_deepvariant \
   --model_type WGS \
   --ref /reference/GRCh38_no_alt_analysis_set.fasta \
-  --reads /input//HG003.novaseq.pcr-free.35x.dedup.grch38_no_alt.chr20.bam  \
+  --reads /input/HG003.novaseq.pcr-free.35x.dedup.grch38_no_alt.chr20.bam \
   --pangenome /input/hprc-v1.1-mc-grch38.gbz \
   --output_vcf /output/HG003.output.vcf.gz \
   --output_gvcf /output/HG003.output.g.vcf.gz \
-  --num_shards $(nproc) \
+  --num_shards 18 \
   --regions chr20 \
   --intermediate_results_dir /output/intermediate_results_dir
 ```
@@ -130,8 +131,7 @@ sudo docker run \
   -v "${PWD}/output":"/output" \
   -v "${PWD}/reference":"/reference" \
   -v "${PWD}/happy:/happy" \
-  jmcdani20/hap.py:v0.3.12 \
-  /opt/hap.py/bin/hap.py \
+  jmcdani20/hap.py:v0.3.12 /opt/hap.py/bin/hap.py \
   /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz \
   /output/HG003.output.vcf.gz \
   -f /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed \
@@ -144,11 +144,13 @@ sudo docker run \
 
 Output:
 
+TODO: Update to new results
+
 ```
 Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL        10628     10584        44        20850        19       9790     14      5       0.995860          0.998282        0.469544          0.99707                     NaN                     NaN                   1.748961                   2.291024
-INDEL   PASS        10628     10584        44        20850        19       9790     14      5       0.995860          0.998282        0.469544          0.99707                     NaN                     NaN                   1.748961                   2.291024
-  SNP    ALL        70166     69932       234        86798        66      16764     45      3       0.996665          0.999058        0.193138          0.99786                2.296566                2.016604                   1.883951                   1.739749
-  SNP   PASS        70166     69932       234        86798        66      16764     45      3       0.996665          0.999058        0.193138          0.99786                2.296566                2.016604                   1.883951                   1.739749
+INDEL    ALL        10628     10581        47        21124        21      10071     16      5       0.995578          0.998100        0.476756         0.996837                     NaN                     NaN                   1.748961                   2.290880
+INDEL   PASS        10628     10581        47        21124        21      10071     16      5       0.995578          0.998100        0.476756         0.996837                     NaN                     NaN                   1.748961                   2.290880
+  SNP    ALL        70166     69910       256        92500        95      22457     38      3       0.996352          0.998644        0.242778         0.997496                2.296566                1.989145                   1.883951                   2.127093
+  SNP   PASS        70166     69910       256        92500        95      22457     38      3       0.996352          0.998644        0.242778         0.997496                2.296566                1.989145                   1.883951                   2.127093
 ```
diff --git a/docs/pangenome-aware-wgs-vg-case-study.md b/docs/pangenome-aware-wgs-vg-case-study.md
index e7d80869..3459efdf 100644
--- a/docs/pangenome-aware-wgs-vg-case-study.md
+++ b/docs/pangenome-aware-wgs-vg-case-study.md
@@ -1,4 +1,4 @@
-# DeepVariant Pangenome-aware WGS case study (mapped with VG)
+# DeepVariant Pangenome-aware WGS case study (mapped with VG Giraffe)
 
 To make it faster to run over this case study, we run only on chromosome 20.
 
@@ -73,31 +73,33 @@ DeepVariant pipeline consists of 3 steps: `make_examples`, `call_variants`, and
 ### Running on a CPU-only machine
 
 In this example, we used a
-[n2-standard-96](https://cloud.google.com/compute/docs/general-purpose-machines)
-machine.
+[n1-standard-64](https://cloud.google.com/compute/docs/general-purpose-machines#n1-standard)
+machine. Because reading in GBZ takes a lot of memory, we will run with
+`--num_shards 18` below.
 
 ```bash
 mkdir -p output
 mkdir -p output/intermediate_results_dir
 
-BIN_VERSION="pangenome_aware_deepvariant-1.8.0"
+BIN_VERSION="1.7.0"
+DOCKER=google/deepvariant:"${BIN_VERSION}"
 
-sudo docker pull google/deepvariant:"${BIN_VERSION}"
 
 sudo docker run \
   -v "${PWD}/input":"/input" \
   -v "${PWD}/output":"/output" \
   -v "${PWD}/reference":"/reference" \
   --shm-size 12gb \
-  google/deepvariant:"${BIN_VERSION}" \
+  ${DOCKER} \
   /opt/deepvariant/bin/run_pangenome_aware_deepvariant \
   --model_type WGS \
   --ref /reference/GRCh38_no_alt_analysis_set.fasta \
   --reads /input/HG003.novaseq.pcr-free.35x.vg-1.55.0.chr20.bam \
+  --make_examples_extra_args="min_mapping_quality=0,keep_legacy_allele_counter_behavior=true,normalize_reads=true" \
   --pangenome /input/hprc-v1.1-mc-grch38.gbz \
   --output_vcf /output/HG003.output.vcf.gz \
   --output_gvcf /output/HG003.output.g.vcf.gz \
-  --num_shards $(nproc) \
+  --num_shards 18 \
   --regions chr20 \
   --intermediate_results_dir /output/intermediate_results_dir
 ```
@@ -135,8 +137,7 @@ sudo docker run \
   -v "${PWD}/output":"/output" \
   -v "${PWD}/reference":"/reference" \
   -v "${PWD}/happy:/happy" \
-  jmcdani20/hap.py:v0.3.12 \
-  /opt/hap.py/bin/hap.py \
+  jmcdani20/hap.py:v0.3.12 /opt/hap.py/bin/hap.py \
   /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz \
   /output/HG003.output.vcf.gz \
   -f /benchmark/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed \
@@ -149,11 +150,13 @@ sudo docker run \
 
 Output:
 
+TODO: Update to new results
+
 ```
 Benchmarking Summary:
 Type Filter  TRUTH.TOTAL  TRUTH.TP  TRUTH.FN  QUERY.TOTAL  QUERY.FP  QUERY.UNK  FP.gt  FP.al  METRIC.Recall  METRIC.Precision  METRIC.Frac_NA  METRIC.F1_Score  TRUTH.TOTAL.TiTv_ratio  QUERY.TOTAL.TiTv_ratio  TRUTH.TOTAL.het_hom_ratio  QUERY.TOTAL.het_hom_ratio
-INDEL    ALL        10628     10594        34        21276        32      10189     21      8       0.996801          0.997114        0.478896         0.996957                     NaN                     NaN                   1.748961                   2.231995
-INDEL   PASS        10628     10594        34        21276        32      10189     21      8       0.996801          0.997114        0.478896         0.996957                     NaN                     NaN                   1.748961                   2.231995
-  SNP    ALL        70166     70090        76        90303        94      20078     21      5       0.998917          0.998661        0.222340         0.998789                2.296566                1.942569                   1.883951                   1.599631
-  SNP   PASS        70166     70090        76        90303        94      20078     21      5       0.998917          0.998661        0.222340         0.998789                2.296566                1.942569                   1.883951                   1.599631
+INDEL    ALL        10628     10585        43        21463        40      10383     26     12       0.995954          0.996390        0.483763         0.996172                     NaN                     NaN                   1.748961                   2.194253
+INDEL   PASS        10628     10585        43        21463        40      10383     26     12       0.995954          0.996390        0.483763         0.996172                     NaN                     NaN                   1.748961                   2.194253
+  SNP    ALL        70166     70072        94        92606        97      22398     22      6       0.998660          0.998618        0.241863         0.998639                2.296566                1.982488                   1.883951                   1.982758
+  SNP   PASS        70166     70072        94        92606        97      22398     22      6       0.998660          0.998618        0.241863         0.998639                2.296566                1.982488                   1.883951                   1.982758
 ```
diff --git a/scripts/inference_deepvariant.sh b/scripts/inference_deepvariant.sh
index d825d505..3c194048 100755
--- a/scripts/inference_deepvariant.sh
+++ b/scripts/inference_deepvariant.sh
@@ -312,7 +312,7 @@ if [[ "${MODEL_PRESET}" = "PACBIO" ]]; then
   BASE="${HOME}/pacbio-case-study"
 
   REF="${REF:=${GCS_DATA_DIR}/case-study-testdata/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna}"
-  BAM="${BAM:=${GCS_DATA_DIR}/pacbio-case-study-testdata/HG003.SPRQ.pacbio.GRCh38.nov2024.bam}"
+  BAM="${BAM:=${GCS_DATA_DIR}/pacbio-case-study-testdata/HG003.SPRQ.pacbio.GRCh38.40x.nov2024.bam}"
   TRUTH_VCF="${TRUTH_VCF:=${GCS_DATA_DIR}/case-study-testdata/HG003_GRCh38_1_22_v4.2.1_benchmark.vcf.gz}"
   TRUTH_BED="${TRUTH_BED:=${GCS_DATA_DIR}/case-study-testdata/HG003_GRCh38_1_22_v4.2.1_benchmark_noinconsistent.bed}"
 elif [[ "${MODEL_PRESET}" = "ONT_R104" ]]; then
diff --git a/third_party/nucleus/io/gfile.cc b/third_party/nucleus/io/gfile.cc
index a66fdcab..aafd069b 100644
--- a/third_party/nucleus/io/gfile.cc
+++ b/third_party/nucleus/io/gfile.cc
@@ -41,13 +41,13 @@ namespace nucleus {
 
 bool Exists(const std::string& filename) {
   // FileExists sets s to tensorflow::error::NOT_FOUND if it doesn't exist.
-  tensorflow::Status s = tensorflow::Env::Default()->FileExists(filename);
+  absl::Status s = tensorflow::Env::Default()->FileExists(filename);
   return s.ok();
 }
 
 std::vector<std::string> Glob(const std::string& pattern) {
   std::vector<std::string> results;
-  ::tensorflow::Status s =
+  absl::Status s =
       tensorflow::Env::Default()->GetMatchingPaths(pattern, &results);
   return results;
 }
@@ -56,7 +56,7 @@ ReadableFile::ReadableFile() {}
 
 std::unique_ptr<ReadableFile> ReadableFile::New(const std::string& filename) {
   std::unique_ptr<tensorflow::RandomAccessFile> file;
-  tensorflow::Status status =
+  absl::Status status =
       tensorflow::Env::Default()->NewRandomAccessFile(filename, &file);
   if (!status.ok()) {
     return nullptr;
@@ -91,8 +91,7 @@ WritableFile::WritableFile() {}
 std::unique_ptr<WritableFile> WritableFile::New(const std::string& filename) {
   std::unique_ptr<tensorflow::WritableFile> file;
 
-  tensorflow::Status s =
-      tensorflow::Env::Default()->NewWritableFile(filename, &file);
+  absl::Status s = tensorflow::Env::Default()->NewWritableFile(filename, &file);
 
   if (!s.ok()) {
     return nullptr;
@@ -105,7 +104,7 @@ std::unique_ptr<WritableFile> WritableFile::New(const std::string& filename) {
 }
 
 bool WritableFile::Write(const std::string& s) {
-  tensorflow::Status status = file_->Append(s);
+  absl::Status status = file_->Append(s);
   return status.ok();
 }
 
diff --git a/third_party/nucleus/io/tfrecord_reader.cc b/third_party/nucleus/io/tfrecord_reader.cc
index 2826bdbe..3b119e66 100644
--- a/third_party/nucleus/io/tfrecord_reader.cc
+++ b/third_party/nucleus/io/tfrecord_reader.cc
@@ -45,7 +45,7 @@ TFRecordReader::TFRecordReader() {}
 std::unique_ptr<TFRecordReader> TFRecordReader::New(
     const std::string& filename, const std::string& compression_type) {
   std::unique_ptr<tensorflow::RandomAccessFile> file;
-  tensorflow::Status s =
+  absl::Status s =
       tensorflow::Env::Default()->NewRandomAccessFile(filename, &file);
   if (!s.ok()) {
     LOG(ERROR) << s;
@@ -74,7 +74,7 @@ bool TFRecordReader::GetNext() {
     return false;
   }
 
-  tensorflow::Status s = reader_->ReadRecord(&offset_, &record_);
+  absl::Status s = reader_->ReadRecord(&offset_, &record_);
 
   return s.ok();
 }
diff --git a/third_party/nucleus/io/tfrecord_writer.cc b/third_party/nucleus/io/tfrecord_writer.cc
index c4f79314..c84360d4 100644
--- a/third_party/nucleus/io/tfrecord_writer.cc
+++ b/third_party/nucleus/io/tfrecord_writer.cc
@@ -45,8 +45,7 @@ TFRecordWriter::TFRecordWriter() {}
 std::unique_ptr<TFRecordWriter> TFRecordWriter::New(
     const std::string& filename, const std::string& compression_type) {
   std::unique_ptr<tensorflow::WritableFile> file;
-  tensorflow::Status s =
-      tensorflow::Env::Default()->NewWritableFile(filename, &file);
+  absl::Status s = tensorflow::Env::Default()->NewWritableFile(filename, &file);
   if (!s.ok()) {
     LOG(ERROR) << s;
     return nullptr;
@@ -69,7 +68,7 @@ bool TFRecordWriter::WriteRecord(const std::string& record) {
   if (writer_ == nullptr) {
     return false;
   }
-  tensorflow::Status s = writer_->WriteRecord(record);
+  absl::Status s = writer_->WriteRecord(record);
   return s.ok();
 }
 
@@ -77,13 +76,13 @@ bool TFRecordWriter::Flush() {
   if (writer_ == nullptr) {
     return false;
   }
-  tensorflow:: Status s = writer_->Flush();
+  absl::Status s = writer_->Flush();
   return s.ok();
 }
 
 bool TFRecordWriter::Close() {
   if (writer_ != nullptr) {
-    tensorflow::Status s = writer_->Close();
+    absl::Status s = writer_->Close();
     if (!s.ok()) {
       return false;
     }
@@ -91,7 +90,7 @@ bool TFRecordWriter::Close() {
   }
 
   if (file_ != nullptr) {
-    tensorflow:: Status s = file_->Close();
+    absl::Status s = file_->Close();
     if (!s.ok()) {
       return false;
     }