diff --git a/reports/benchmark_reproducibility.json b/reports/benchmark_reproducibility.json index 257214e..0e32dcd 100644 --- a/reports/benchmark_reproducibility.json +++ b/reports/benchmark_reproducibility.json @@ -3,7 +3,7 @@ "ok": true, "generated_at": "2026-06-14", "skill_dir": ".", - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "git_status": { "available": true, "dirty": false, @@ -17,9 +17,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de", - "source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5", - "archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc", + "evidence_bundle_sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429", + "source_contract_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a", + "archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -50,7 +50,7 @@ }, "release_lock": { "ready": true, - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -60,7 +60,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de" + "sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -133,8 +133,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7964, - "sha256": "2c230fbc6455657eec1738b43c33cf31219a6e70b8e5d846bada11e1051c3168" + "bytes": 7967, + "sha256": "f934e2b43e24d30cd23098b81c7d2602d9038c793f1afd7cd42b64974bee3bc2" }, { "label": "blind_review", @@ -168,8 +168,8 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 98830, - "sha256": "3c69120778acb66ad88743c62d26d119a23abab81926e2f8f0ed9cfbc483318c" + "bytes": 99433, + "sha256": "bde78b81ac27913186aa6072f60bddb8fc2b006f596413e032e4864ad345c1d3" }, { "label": "python_compatibility", @@ -183,21 +183,21 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9387060b0ca239dde97a2f80fc0917cce44ff343ee99893af8f5443d7ebf75bc" + "sha256": "28c7a971924e56012df29e7bd924cc7a2d9a6de78b37b327b81c3b222cad29dd" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19325, - "sha256": "007d65fe23663d4377861b2e44612629eb3a90e0b1f400e763132bf5e6495f0a" + "sha256": "34d291fa975346752b34283f38f60e3498a7d1165f89f4081200ad8c2a8d5e1b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, "bytes": 8604, - "sha256": "8f987e805c92bf4178e3f246356ab268e59f62e9b6948be09f5c53054e7780ec" + "sha256": "1ed7ce5266c2dd7ee8daf83a3a5c65cdb69ade1567a33b88b77b619d3f5afa16" }, { "label": "skill_os2_audit", @@ -231,29 +231,29 @@ "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 7263, - "sha256": "4f03edb2ef28d9dfd27a393f8058d6e27d2b10fa8cbfe35f473e003556b9ffe0" + "bytes": 12413, + "sha256": "a6d609911ed5d14a4e710233f3207a12750982eaa1f9d6d6ebc5d612b16e7ac4" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 15206, - "sha256": "43492b169ade7202f4fcd5db989e314c3b04cb96d6178ec6854bb90788d7e586" + "bytes": 19980, + "sha256": "bb416ed286487c98c8e99d6bf3ddf5f0e041a0ccdd23b407f3b178383e3c5bb4" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 9445, - "sha256": "cb05eec07f1ed0939fecbfc46b9101029498be6b8ebc03bb536fa3223e5846af" + "bytes": 10458, + "sha256": "892412f842a17b9992056a52f65021698264294206fffc093ecf3dbe58c82400" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 13430, - "sha256": "68b45d5f6f88df6eb22ad23643846e60207ab41af11d9c85cb20d5fe3e0e7182" + "bytes": 16575, + "sha256": "e11b4f3ebe8f0a047b3118ccfc655595af185561c2d90e47974defcf876b0ef3" }, { "label": "world_class_claim_guard", diff --git a/reports/benchmark_reproducibility.md b/reports/benchmark_reproducibility.md index 60f3248..578179c 100644 --- a/reports/benchmark_reproducibility.md +++ b/reports/benchmark_reproducibility.md @@ -1,9 +1,9 @@ # Benchmark Reproducibility Generated at: `2026-06-14` -Commit: `7cbbf58078b146fdb6f2e7678934f057e961bdf4` +Commit: `0936ce727e7ebc414bcc5a95db139bbecbd594f9` Working tree dirty at generation: `false` -Evidence bundle SHA256: `6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de` +Evidence bundle SHA256: `ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429` ## Summary @@ -12,8 +12,8 @@ Evidence bundle SHA256: `6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b721 - methodology complete: `true` - required artifacts: `24` - missing artifacts: `0` -- source contract sha256: `25098dc5932e` -- archive sha256: `11c75419dc65` +- source contract sha256: `52472a5f16d0` +- archive sha256: `36ec77ec0bad` - output cases: `5` - disclosed failure cases: `3` - reproduction commands: `21` @@ -48,7 +48,7 @@ This report proves local benchmark reproducibility only. It keeps external provi - algorithm: `sha256(path,label,exists,artifact_sha256)` - artifacts: `24` / `24` -- sha256: `6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de` +- sha256: `ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429` ## Methodology Sections @@ -70,24 +70,24 @@ This report proves local benchmark reproducibility only. It keeps external provi | output_cases | `evals/output/cases.jsonl` | present | `a6ae96857116` | | output_schema | `evals/output/schema.json` | present | `8ee340c95064` | | output_scorecard | `reports/output_quality_scorecard.json` | present | `0806258a8e08` | -| output_execution | `reports/output_execution_runs.json` | present | `2c230fbc6455` | +| output_execution | `reports/output_execution_runs.json` | present | `f934e2b43e24` | | blind_review | `reports/output_blind_review_pack.json` | present | `bbe2db8ec277` | | review_adjudication | `reports/output_review_adjudication.json` | present | `240485a721af` | | trigger_scorecard | `reports/route_scorecard.json` | present | `c164e83e36d0` | | runtime_conformance | `reports/conformance_matrix.json` | present | `8251329e663d` | -| trust_report | `reports/security_trust_report.json` | present | `3c69120778ac` | +| trust_report | `reports/security_trust_report.json` | present | `bde78b81ac27` | | python_compatibility | `reports/python_compatibility.json` | present | `ae16e17266e4` | -| registry_audit | `reports/registry_audit.json` | present | `9387060b0ca2` | -| package_verification | `reports/package_verification.json` | present | `007d65fe2366` | -| install_simulation | `reports/install_simulation.json` | present | `8f987e805c92` | +| registry_audit | `reports/registry_audit.json` | present | `28c7a971924e` | +| package_verification | `reports/package_verification.json` | present | `34d291fa9753` | +| install_simulation | `reports/install_simulation.json` | present | `1ed7ce5266c2` | | skill_os2_audit | `reports/skill_os2_audit.json` | present | `6bb2dcb0e1e5` | | world_class_evidence_plan | `reports/world_class_evidence_plan.json` | present | `164803bb1cea` | | world_class_evidence_ledger | `reports/world_class_evidence_ledger.json` | present | `0bff14542475` | | world_class_evidence_intake | `reports/world_class_evidence_intake.json` | present | `8f7f9db6f899` | -| world_class_submission_review | `reports/world_class_submission_review.json` | present | `4f03edb2ef28` | -| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `43492b169ade` | -| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `cb05eec07f1e` | -| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `68b45d5f6f88` | +| world_class_submission_review | `reports/world_class_submission_review.json` | present | `a6d609911ed5` | +| world_class_operator_runbook | `reports/world_class_operator_runbook.json` | present | `bb416ed28648` | +| world_class_operator_runbook_markdown | `reports/world_class_operator_runbook.md` | present | `892412f842a1` | +| world_class_operator_runbook_html | `reports/world_class_operator_runbook.html` | present | `e11b4f3ebe8f` | | world_class_claim_guard | `reports/world_class_claim_guard.json` | present | `250d616b028c` | ## Reproduction Commands diff --git a/reports/review-studio.json b/reports/review-studio.json index 8ced0b9..db71f54 100644 --- a/reports/review-studio.json +++ b/reports/review-studio.json @@ -1336,9 +1336,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de", - "source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5", - "archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc", + "evidence_bundle_sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429", + "source_contract_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a", + "archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -1357,7 +1357,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", @@ -4764,7 +4764,7 @@ "ok": true, "generated_at": "2026-06-14", "skill_dir": ".", - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "git_status": { "available": true, "dirty": false, @@ -4778,9 +4778,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de", - "source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5", - "archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc", + "evidence_bundle_sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429", + "source_contract_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a", + "archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -4811,7 +4811,7 @@ }, "release_lock": { "ready": true, - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "status_scope": "generation-time status before this report is written", "reason": "clean generation-time HEAD" }, @@ -4821,7 +4821,7 @@ "existing_count": 24, "missing_count": 0, "missing_paths": [], - "sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de" + "sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429" }, "methodology": { "path": "reports/benchmark_methodology.md", @@ -4894,8 +4894,8 @@ "label": "output_execution", "path": "reports/output_execution_runs.json", "exists": true, - "bytes": 7964, - "sha256": "2c230fbc6455657eec1738b43c33cf31219a6e70b8e5d846bada11e1051c3168" + "bytes": 7967, + "sha256": "f934e2b43e24d30cd23098b81c7d2602d9038c793f1afd7cd42b64974bee3bc2" }, { "label": "blind_review", @@ -4929,8 +4929,8 @@ "label": "trust_report", "path": "reports/security_trust_report.json", "exists": true, - "bytes": 98830, - "sha256": "3c69120778acb66ad88743c62d26d119a23abab81926e2f8f0ed9cfbc483318c" + "bytes": 99433, + "sha256": "bde78b81ac27913186aa6072f60bddb8fc2b006f596413e032e4864ad345c1d3" }, { "label": "python_compatibility", @@ -4944,21 +4944,21 @@ "path": "reports/registry_audit.json", "exists": true, "bytes": 3183, - "sha256": "9387060b0ca239dde97a2f80fc0917cce44ff343ee99893af8f5443d7ebf75bc" + "sha256": "28c7a971924e56012df29e7bd924cc7a2d9a6de78b37b327b81c3b222cad29dd" }, { "label": "package_verification", "path": "reports/package_verification.json", "exists": true, "bytes": 19325, - "sha256": "007d65fe23663d4377861b2e44612629eb3a90e0b1f400e763132bf5e6495f0a" + "sha256": "34d291fa975346752b34283f38f60e3498a7d1165f89f4081200ad8c2a8d5e1b" }, { "label": "install_simulation", "path": "reports/install_simulation.json", "exists": true, "bytes": 8604, - "sha256": "8f987e805c92bf4178e3f246356ab268e59f62e9b6948be09f5c53054e7780ec" + "sha256": "1ed7ce5266c2dd7ee8daf83a3a5c65cdb69ade1567a33b88b77b619d3f5afa16" }, { "label": "skill_os2_audit", @@ -4992,29 +4992,29 @@ "label": "world_class_submission_review", "path": "reports/world_class_submission_review.json", "exists": true, - "bytes": 7263, - "sha256": "4f03edb2ef28d9dfd27a393f8058d6e27d2b10fa8cbfe35f473e003556b9ffe0" + "bytes": 12413, + "sha256": "a6d609911ed5d14a4e710233f3207a12750982eaa1f9d6d6ebc5d612b16e7ac4" }, { "label": "world_class_operator_runbook", "path": "reports/world_class_operator_runbook.json", "exists": true, - "bytes": 15206, - "sha256": "43492b169ade7202f4fcd5db989e314c3b04cb96d6178ec6854bb90788d7e586" + "bytes": 19980, + "sha256": "bb416ed286487c98c8e99d6bf3ddf5f0e041a0ccdd23b407f3b178383e3c5bb4" }, { "label": "world_class_operator_runbook_markdown", "path": "reports/world_class_operator_runbook.md", "exists": true, - "bytes": 9445, - "sha256": "cb05eec07f1ed0939fecbfc46b9101029498be6b8ebc03bb536fa3223e5846af" + "bytes": 10458, + "sha256": "892412f842a17b9992056a52f65021698264294206fffc093ecf3dbe58c82400" }, { "label": "world_class_operator_runbook_html", "path": "reports/world_class_operator_runbook.html", "exists": true, - "bytes": 13430, - "sha256": "68b45d5f6f88df6eb22ad23643846e60207ab41af11d9c85cb20d5fe3e0e7182" + "bytes": 16575, + "sha256": "e11b4f3ebe8f0a047b3118ccfc655595af185561c2d90e47974defcf876b0ef3" }, { "label": "world_class_claim_guard", diff --git a/reports/review-viewer.json b/reports/review-viewer.json index 6ffeb49..cee60a7 100644 --- a/reports/review-viewer.json +++ b/reports/review-viewer.json @@ -923,9 +923,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de", - "source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5", - "archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc", + "evidence_bundle_sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429", + "source_contract_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a", + "archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -944,7 +944,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.", diff --git a/reports/skill-overview.json b/reports/skill-overview.json index 84ac870..8300d77 100644 --- a/reports/skill-overview.json +++ b/reports/skill-overview.json @@ -922,9 +922,9 @@ "methodology_complete": true, "required_artifact_count": 24, "missing_artifact_count": 0, - "evidence_bundle_sha256": "6a3b36fb8168d0b7173e5e4fa9ea2613f4bdaf6f733e9959c32b72197b1e56de", - "source_contract_sha256": "25098dc5932e847a1aeb06f51ada0de60fec1382fe286fc88e9bc5e60fb4d3c5", - "archive_sha256": "11c75419dc6599e7c555a153e4d72127a2c32a73d9426ecde4d110e4777453dc", + "evidence_bundle_sha256": "ba36213f867958bf4a3f35d0d81e864862134510e313b87b4326197b25f36429", + "source_contract_sha256": "52472a5f16d07e88959326df916a03a327b3f3c9443d2128556002c431c9f70a", + "archive_sha256": "36ec77ec0badfe8b44286434d0c10de0470dee241f33b569ea24a0e971721a0e", "output_case_count": 5, "failure_disclosure_count": 3, "command_count": 21, @@ -943,7 +943,7 @@ "working_tree_dirty": false, "changed_file_count": 0 }, - "commit": "7cbbf58078b146fdb6f2e7678934f057e961bdf4", + "commit": "0936ce727e7ebc414bcc5a95db139bbecbd594f9", "missing_artifacts": [], "limitations": [ "The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",