Record public input source binding

Signed-off-by: yoshifuminakamura <nakamura@riken.jp>

Author: yoshifuminakamura

docs/cx/BENCHKIT_SPEC.md

@@ -490,6 +490,9 @@ Benchkit は、pre-staged input、restart、学習済みモデル、公開 archi
 この場合、`source_info` が実際に使った app source と repo 内 input の両方の固定点になる。
 `input_info` は省略してもよく、Portal や review で dataset 名を見せたい場合だけ、`kind: "repo-local-input"`、`source: "source_info"`、`repo_relative_path`、`verification_status: "covered_by_source_commit"` などの補助情報を持たせてよい。
 
+入力が別の public input repository や public archive から来る場合は、`input_info` 側に公開URL、ref、resolved commit または digest、取得/生成 recipe を置く。
+この場合も、入力が記録済み source commit で固定されるなら `verification_status: "public_source_commit"` として `Covered` に分類できる。
+
 site-local path は所在情報であり、長期的な input identity ではない。
 巨大データや共同研究由来データを site-local shared storage に置くことは許容されるが、Result provenance では path より dataset identity、recipe、manifest、digest を優先する。
 public surface では、必要がない限り detailed local path を表示しない。
@@ -514,6 +517,9 @@ When the input is already stored in the top-level application repository and is
 In that case, `source_info` is the fixed point for both the application source and the repository-local input actually used.
 `input_info` may be omitted, or it may carry lightweight helper fields such as `kind: "repo-local-input"`, `source: "source_info"`, `repo_relative_path`, and `verification_status: "covered_by_source_commit"` when the dataset name should be visible in the Portal or during review.
 
+When the input comes from a separate public input repository or public archive, `input_info` should carry the public URL, ref, resolved commit or digest, and acquisition or generation recipe.
+If the input is fixed by a recorded source commit, it may use `verification_status: "public_source_commit"` and be classified as `Covered`.
+
 A site-local path is location information, not a durable input identity.
 Large datasets and collaboration-derived inputs may still be staged on site-local shared storage, but Result provenance should prefer dataset identity, recipe, manifest, and digest over paths.
 Detailed local paths should not be exposed on the public surface unless they are necessary.

docs/guides/add-app.md

@@ -193,7 +193,7 @@ Portal の `/results/usage` では、通常の benchmark result に対する入
 
 - `None`: `input_info` がない
 - `Declared`: `input_info` はあるが、digest 検証や source commit coverage までは示していない
-- `Covered`: repo-local input が `source_info.resolved_commit` で固定されることを示している
+- `Covered`: repo-local input または public input source が記録済み source commit で固定されることを示している
 - `Verified`: manifest / content digest などの証跡と `verification_status: "verified"` がある
 
 `None` や `Declared` はただちに CI failure ではありません。

programs/genesis/run.sh

@@ -35,6 +35,43 @@ stderr="${resultsdir}/log_${header}_err.txt"
 binary="spdyn"
 inputdir="../../../inputs/apoa1/"
 
+record_public_input_info() {
+    local input_source_commit="$1"
+    {
+        printf '{\n'
+        printf '  "schema_version": 1,\n'
+        printf '  "inputs": [\n'
+        printf '    {\n'
+        printf '      "dataset_id": '
+        bk_json_string "apoa1-p8"
+        printf ',\n'
+        printf '      "dataset_version": '
+        bk_json_string "$BRANCH"
+        printf ',\n'
+        printf '      "kind": "public-git",\n'
+        printf '      "source": "public_url",\n'
+        printf '      "public_url": '
+        bk_json_string "$REPO_URL"
+        printf ',\n'
+        printf '      "source_ref": '
+        bk_json_string "$BRANCH"
+        printf ',\n'
+        printf '      "resolved_commit": '
+        bk_json_string "$input_source_commit"
+        printf ',\n'
+        printf '      "repo_relative_path": '
+        bk_json_string "$dir_path"
+        printf ',\n'
+        printf '      "recipe": '
+        bk_json_string "${input}.sub generated from ${input}"
+        printf ',\n'
+        printf '      "verification_status": "public_source_commit"\n'
+        printf '    }\n'
+        printf '  ]\n'
+        printf '}\n'
+    } | bk_record_input_info
+}
+
 echo "[${REPO_DIR}] Running on system: $system"
 
 if [[ -d "${REPO_DIR}" ]]; then
@@ -51,14 +88,15 @@ echo "System=$system"
 echo "Nodes=$nodes"
 echo "numproc=$numproc"
 echo "nthreads=$nthreads"
-totalcores=$(( numproc * nthreads ))
 
 if [[ ! -d ${REPO_DIR} ]]; then
     git clone --branch "${BRANCH}" "${REPO_URL}" "${REPO_DIR}"
 else
     echo "Reposiotry already exists and looks valid. Skipping clone."
 fi
 
+input_source_commit=$(git -C "${REPO_DIR}" rev-parse HEAD)
+record_public_input_info "$input_source_commit"
 
 if [[ ! -f "${artifactsdir}/spdyn" ]]; then
     echo "Error: spdyn does not exist."
@@ -128,17 +166,19 @@ run_genesis_nvidia_gpu() {
     local cuda_visible_devices_var="${env_prefix}_CUDA_VISIBLE_DEVICES"
     local profiler_tool_var="${env_prefix}_PROFILER_TOOL"
     local profiler_level_var="${env_prefix}_PROFILER_LEVEL"
+    local -a nvidia_mpi_cmd
+    local -a nvidia_mpi_args
 
     local module_name="${!module_var:-$default_module}"
     if [ "$module_name" != "none" ] && command -v module >/dev/null 2>&1; then
         read -r -a module_names <<< "$module_name"
         module load "${module_names[@]}"
     fi
 
-    read -r -a mpi_cmd <<< "${!mpi_cmd_var:-mpirun -np ${numproc}}"
+    read -r -a nvidia_mpi_cmd <<< "${!mpi_cmd_var:-mpirun -np ${numproc}}"
     if [ -n "${!mpi_args_var:-}" ]; then
         read -r -a nvidia_mpi_args <<< "${!mpi_args_var}"
-        mpi_cmd+=("${nvidia_mpi_args[@]}")
+        nvidia_mpi_cmd+=("${nvidia_mpi_args[@]}")
     fi
 
     export OMP_NUM_THREADS=${nthreads}
@@ -150,8 +190,8 @@ run_genesis_nvidia_gpu() {
     genesis_configure_ncu_profile "$system_name" "$profiler_tool_var" "$profiler_level_var" "$module_var" || return 1
 
     echo "Running ${system_name} as NVIDIA GPU benchmark run without profiler"
-    "${mpi_cmd[@]}" ./${binary} ${input}.sub 2>&1 | tee ${output}
-    genesis_run_configured_ncu_profiles "$system_name" "${mpi_cmd[@]}" ./${binary} ${input}.sub || return 1
+    "${nvidia_mpi_cmd[@]}" ./${binary} ${input}.sub 2>&1 | tee ${output}
+    genesis_run_configured_ncu_profiles "$system_name" "${nvidia_mpi_cmd[@]}" ./${binary} ${input}.sub || return 1
 }
 
 genesis_rikyu_apptainer_run_prefix() {

result_server/templates/_usage_report_evidence_snapshot_section.html

@@ -17,7 +17,7 @@ <h2 class="section-title">Evidence Snapshot</h2>
     <span><strong>Evidence Snapshot:</strong> the roll-up and CSV export source for configured, executed, profiled, estimated, source, input, and build-cache evidence.</span>
     <span><strong>Configured:</strong> yes = enabled and implemented; partial = enabled but script support incomplete; off = configured off; no = not listed.</span>
     <span><strong>Result Quality:</strong> missing = no result; basic = core result only; ready = estimation bindings present; rich = source provenance and artifacts present.</span>
-    <span><strong>Input Status:</strong> None = no input_info; Declared = input_info only; Covered = repo-local input fixed by source_info; Verified = digest-backed input verification.</span>
+    <span><strong>Input Status:</strong> None = no input_info; Declared = input_info only; Covered = input fixed by a recorded source commit; Verified = digest-backed input verification.</span>
     <span><strong>Reuse Package:</strong> complete = public packet eligible with profile and estimate evidence; public packet eligible = source material is ready for a public Markdown reuse packet.</span>
     <span><strong>Public Packet:</strong> eligible = public result with public source provenance and public input binding.</span>
     <span><strong>Next Action:</strong> the first practical follow-up suggested by the current evidence state.</span>

result_server/tests/test_evidence_snapshot.py

@@ -162,6 +162,62 @@ def test_evidence_snapshot_requires_public_source_for_public_packet(tmp_path):
     assert row["reuse_package_status"] == "needs public evidence"
 
 
+def test_evidence_snapshot_accepts_public_input_commit_for_public_packet(tmp_path):
+    received_dir = tmp_path / "received"
+    estimated_dir = tmp_path / "estimated"
+    received_dir.mkdir()
+    estimated_dir.mkdir()
+
+    _write_json(
+        received_dir / "result_20260901_010101_aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee.json",
+        {
+            "code": "demoapp",
+            "system": "DemoSystem",
+            "Exp": "CASE0",
+            "FOM": 1.0,
+            "source_info": {
+                "source_type": "git",
+                "repo_url": "https://example.com/demoapp.git",
+                "ref_name": "main",
+                "resolved_commit": "abcdef1234567890",
+            },
+            "input_info": {
+                "inputs": [
+                    {
+                        "dataset_id": "apoa1-p8",
+                        "kind": "public-git",
+                        "source": "public_url",
+                        "public_url": "https://example.com/input.git",
+                        "source_ref": "main",
+                        "resolved_commit": "1234567890abcdef",
+                        "repo_relative_path": "npt/apoa1",
+                        "verification_status": "public_source_commit",
+                    }
+                ],
+            },
+        },
+    )
+
+    snapshot = build_evidence_snapshot(
+        str(received_dir),
+        str(estimated_dir),
+        generated_at="2026-09-07T00:00:00Z",
+        app_support_rows=[
+            {
+                "app": "demoapp",
+                "systems": {
+                    "DemoSystem": {"status": "enabled"},
+                },
+            }
+        ],
+    )
+
+    row = snapshot["rows"][0]
+    assert row["input_status"] == "Covered"
+    assert row["public_packet_status"] == "eligible"
+    assert row["reuse_package_status"] == "public packet eligible"
+
+
 def test_evidence_snapshot_uses_estimate_benchmark_systems_without_future_target_rows(tmp_path):
     received_dir = tmp_path / "received"
     estimated_dir = tmp_path / "estimated"

result_server/tests/test_portal_list_templates.py

@@ -823,5 +823,5 @@ def test_usage_report_evidence_snapshot_consolidates_coverage_and_quality():
     assert "Maturity Gaps" in html
     assert "Input Status" in html
     assert "None = no input_info" in html
-    assert "Covered = repo-local input fixed by source_info" in html
+    assert "Covered = input fixed by a recorded source commit" in html
     assert "no profile; no estimate; source incomplete; input not declared" in html

result_server/tests/test_results_loader.py

@@ -504,6 +504,28 @@ def test_input_info_status_classification(self):
         })
         assert covered["stats"]["input_info_status"] == "covered"
 
+        public_source_covered = summarize_result_quality({
+            "code": "test",
+            "system": "sys",
+            "FOM": 1.0,
+            "input_info": {
+                "schema_version": 1,
+                "inputs": [
+                    {
+                        "dataset_id": "case0",
+                        "kind": "public-git",
+                        "source": "public_url",
+                        "public_url": "https://example.com/input.git",
+                        "source_ref": "main",
+                        "resolved_commit": "abcdef1234567890",
+                        "repo_relative_path": "benchmarks/case0",
+                        "verification_status": "public_source_commit",
+                    }
+                ],
+            },
+        })
+        assert public_source_covered["stats"]["input_info_status"] == "covered"
+
         missing_source_commit = summarize_result_quality({
             "code": "test",
             "system": "sys",

result_server/utils/result_records.py

@@ -252,7 +252,7 @@ def summarize_input_info(data):
     }
     summaries = {
         "declared": "input_info is present, but digest or source-commit coverage is not declared as verified.",
-        "covered": "input_info declares repository-local input covered by source_info.resolved_commit.",
+        "covered": "input_info declares input covered by a recorded source commit.",
         "verified": "input_info declares verified input with digest evidence.",
     }
     return {
@@ -277,6 +277,14 @@ def _classify_input_info_item(item, has_source_commit):
         "digest",
     )
     has_digest = any(item.get(field) for field in digest_fields)
+    revision_fields = (
+        "resolved_commit",
+        "commit_hash",
+        "source_commit",
+        "revision",
+        "dataset_revision",
+    )
+    has_input_revision = any(item.get(field) for field in revision_fields)
 
     if verification_status == "verified" and has_digest:
         return "verified"
@@ -289,6 +297,19 @@ def _classify_input_info_item(item, has_source_commit):
     if repo_local_covered:
         return "covered"
 
+    public_source_covered = (
+        has_input_revision
+        and verification_status in {"public_source_commit", "covered_by_public_source_commit"}
+        and (
+            source in {"public_url", "public_git", "public-git"}
+            or item.get("public_url")
+            or item.get("source_url")
+            or item.get("archive_url")
+        )
+    )
+    if public_source_covered:
+        return "covered"
+
     return "declared"