{
  "kind": "real-gpu-execution",
  "hardware_label": "RTX 3080 / Ubuntu WSL",
  "run_id": "20260913-210946-683068",
  "experiment": "baseline-control.yaml",
  "experiment_sha256": "0901253017f393fb1d80febc23d24fafe7e2880ea3dea8e5e1e70b339ed3bef4",
  "python": "3.12.3",
  "runtime_metadata": {
    "vllm_optimizer_version": "0.1.0a13",
    "vtune_version": "0.1.0a13",
    "python_version": "3.12.3",
    "platform": "Linux-6.18.33.2-microsoft-standard-WSL2-x86_64-with-glibc2.39",
    "software": {
      "vllm": "0.28.0",
      "guidellm": "0.7.3"
    },
    "cuda_version": "13.0",
    "gpus": [
      {
        "name": "NVIDIA GeForce RTX 3080",
        "uuid": "GPU-REDACTED",
        "driver_version": "616.64",
        "memory_mib": "10240"
      }
    ]
  },
  "software": {
    "vllm": "0.28.0",
    "guidellm": "0.7.3",
    "torch": "2.13.0",
    "transformers": "5.16.1",
    "tokenizers": "0.23.1",
    "huggingface-hub": "1.29.0"
  },
  "model_revision": "27dcfa74d334bc871f3234de431e71c6eeba5dd6",
  "model_checksums_sha256": "9e6aeb70c8f7d8b882fb9eb9d5bfed087f924c192f4d9188cc1b67505e267a6f",
  "source_files_sha256": {
    "src/vllm_optimizer/__init__.py": "3f2f4ebef4ccbf094fbbd917593762e00f3dcf2b4a759f7a7dfabb2b25f21b6e",
    "src/vllm_optimizer/benchmarks/__init__.py": "aa263e53a85dfe49a0c648178e55a2545f2a54920353a4a1ad82b15f64a8c4c0",
    "src/vllm_optimizer/benchmarks/configuration.py": "88e47b4f5fce10794e3943aeebd6be9ba97c7fce7fdd4ac1022cdbd54b29de58",
    "src/vllm_optimizer/benchmarks/failures.py": "8feb5c464506b4a616605f0784ecad1e3be4aaf893b9f7781936894ece13f96b",
    "src/vllm_optimizer/benchmarks/guidellm.py": "0d99f7b2724dc390c4eece97ad7ef3a046b3e41dba8555194ce0335b79dd73eb",
    "src/vllm_optimizer/benchmarks/metrics.py": "5eaa182f9ff8ff66c0ebba6f2b2296d3ec0319a10c74dadf113ad486c2d870c3",
    "src/vllm_optimizer/benchmarks/policy.py": "1a7afca83601a25721546028161ced834813fe1c83ddcd1073c20232a2152cc7",
    "src/vllm_optimizer/benchmarks/quality.py": "31386ddbdadd035ab94bc709117354ee8f5e6104a4f206cc1d985221b75bc2a4",
    "src/vllm_optimizer/benchmarks/timing.py": "2d53ad1c45e3ccf246fcd01f769a647928fb7367a91a4201acd752ee5beb61e7",
    "src/vllm_optimizer/benchmarks/vllm.py": "e08ebbe2a955d795c2f70a23d07526dcf7436609decf19384d00b30cf293e528",
    "src/vllm_optimizer/cli.py": "5697cfd42efd5c305553332928d07c315f093e8272578d77311f78cd14e37312",
    "src/vllm_optimizer/cli_options.py": "5a8e1e08c4c4102fee9a3d8b319bedf9a82ed20a38a229b4539b613c541eecd7",
    "src/vllm_optimizer/config/__init__.py": "7dfa5aa4971d4267756d52686ac0e1c985647ebb9792b58176afb6848d5704ed",
    "src/vllm_optimizer/config/errors.py": "250897d8a434f8360d2d7db670be693966f25adf31d80d08a085ba3660516b94",
    "src/vllm_optimizer/config/loader.py": "6c3c5a381596740cc3b9f06808543848f40a3f10b14231e946706c207091b9f3",
    "src/vllm_optimizer/config/models.py": "2e8ef0dde094962e4afa25c1fcda7da87b378abe9f4d7c480d80fc1414f30632",
    "src/vllm_optimizer/config/preflight.py": "f50dc40fd81a615f4fc281ee5ac7add34137f2ec5c34fe28192282f01eb6f412",
    "src/vllm_optimizer/config/runtime.py": "140a59ac97a257145a7044f0da599c9b32ffa36bdea486d16da2bc921f422cf3",
    "src/vllm_optimizer/domain/__init__.py": "e24740ca258b80d4ec60593171617a40c4f399765bbfe4eed658b7e2b2e52097",
    "src/vllm_optimizer/domain/attempt_report.py": "e010882e8df200541a91df930b65cdb18bc5407fa03039077e5856dbcdd41661",
    "src/vllm_optimizer/domain/benchmark.py": "03da9fc5d2f681a0528e4fcd93b5e406a351b3e98fc7e1244b03b94779808e41",
    "src/vllm_optimizer/domain/models.py": "0012290687358ab4ce37dcf4bbbbf612c6bbf118b8a2519546ea813e326be2b6",
    "src/vllm_optimizer/domain/results.py": "b1797f6b6b7091b54d5c635097bf4632fd1001844061026eccfd8480d1156cd9",
    "src/vllm_optimizer/domain/states.py": "99d3cfa87a7ba2d724f40de75b77334b8c30523f9fdc880d0115fa6972e57216",
    "src/vllm_optimizer/domain/trial_report.py": "20845da8a5cac9433c5f20354beb74aca504d322d7b930c6e3ed0be3e73ab752",
    "src/vllm_optimizer/execution/__init__.py": "dfb0745cc87c6f7a18dee19b3cdad568909cb7e48431c2e17720b43f48d51553",
    "src/vllm_optimizer/execution/finalist_validation.py": "9dcef7e5bc200e284dd96a2cf447f377a0a114bb95fce0b7f534c64ffb02f6eb",
    "src/vllm_optimizer/execution/scheduler.py": "855e44ac991b280105b28d8aa0b294e6ca477f1a7d7d6322c99d2187bffba5f2",
    "src/vllm_optimizer/execution/slots.py": "abd76e4e7eaf59a3c0d98310c0bf1016b406a32bff78a59f127c3c316ca2212a",
    "src/vllm_optimizer/execution/trial_executor.py": "85e52dcdf7e08182442fd87245566e2b9cb881706445c42dcc3517662d25b6d2",
    "src/vllm_optimizer/lifecycle/__init__.py": "8226f0614ce1752f31a56812b7ce57464709a7e62fe5a979b98288b66a11b593",
    "src/vllm_optimizer/lifecycle/integrity.py": "84c28b5f2b7392f2f67f4df61a8ab67d79e0d8c577ea4b19e01ac5edaee7a012",
    "src/vllm_optimizer/lifecycle/retry.py": "5cbb791787308ba868dcd16296cdb7decbf169d9b7055d8c150bc746f54252c1",
    "src/vllm_optimizer/managers/__init__.py": "13b675a8cf602c625797a8897f6895b10da10da3175ac15f5ff1676ab38b7c44",
    "src/vllm_optimizer/managers/results.py": "8b65f46a500fb533e63ab183032d9dc42d629cd1da3c1dacb460cbfb9cf4d00e",
    "src/vllm_optimizer/managers/run_documents.py": "fabebe389bf1ceb4118455c20f8420067c741ac5fa2e30d8ab80d5d6f66258ee",
    "src/vllm_optimizer/managers/run_finalization.py": "2ae3c4d687f64d5142e73626234bf74fb56869cef9bab7e097564ade1d043351",
    "src/vllm_optimizer/managers/run_results.py": "2f5dda803905309681b8de19773e4a5c306e80599da46ec3a6ca997a533fca42",
    "src/vllm_optimizer/managers/run_session.py": "e43bda66acfb201b584dcf2700525826e65ae8ca9400d788ac5205cfa08b2dfc",
    "src/vllm_optimizer/managers/scoring.py": "c9d39f08869f657c1f73f1f280a1af2c53a51bac3fe23c1c50513117b55239da",
    "src/vllm_optimizer/managers/trial.py": "d00edfdae048b467328f5695f3be7fd405640e2676e2c3a27367acbfd999f061",
    "src/vllm_optimizer/measurement.py": "e7ea28d72fa55e0b90d61805d284352753cc0682cb2590fca55baf8c34c99291",
    "src/vllm_optimizer/orchestrator.py": "dfe94bdf8accefdb4dff70e03ff53d9fa3ac9ffc4c6726b06a3175de3ea32480",
    "src/vllm_optimizer/orchestrator_messages.py": "d016b0e3bfb756c1374f781d7e7871bd56759ed1dd945aa77a3eeaffc49347b8",
    "src/vllm_optimizer/orchestrator_search.py": "9564c09b002ff4ea7e60dfb13894c13abbff3bf9e18c44b32799e59e68af9d7e",
    "src/vllm_optimizer/orchestrator_setup.py": "80683df31188131d180cba25002ea12e95d244eefb0cd5d7455a7a75fb32b37b",
    "src/vllm_optimizer/reporting/__init__.py": "5ee4b9d49e4303eca48e69671504bbf805e6b864c83204972f0f082e0ff8c69d",
    "src/vllm_optimizer/reporting/accepted_scores.py": "a62d0b4c2ec3038dcecf11f8fbdc6b7fd76aa4fb04c376259bf4321a9ac6efd6",
    "src/vllm_optimizer/reporting/analysis.py": "e32b8329ebe72c5524660da0622353894468cb75f8e57c77afebb0776d9105c6",
    "src/vllm_optimizer/reporting/benchmark_details.py": "08ec4cf65770078c9a3bbb7c6586003960bddadb20aefa21520615b498a5e240",
    "src/vllm_optimizer/reporting/charts.py": "eb1a85bc4c08e5f6d76a666d3b424080b4deaaf4b75666539efad1ffa3a3d797",
    "src/vllm_optimizer/reporting/comparison.py": "a7da1d188c206a05a3f8409727ac823f67f456fdcd3dc1a60f791953b0e58dcd",
    "src/vllm_optimizer/reporting/confidence.py": "6c218580db61f6c5729aadd24237966b8a2739f50ded6b2917b61dbfedda128b",
    "src/vllm_optimizer/reporting/context.py": "7fa2a410c73b347947dc1eebad9199e7183d7f752d55877efac7cee44b813c3c",
    "src/vllm_optimizer/reporting/dashboard.py": "5b272add8bfd2186e06847b90a939e271b236b9e69c00bd34814f59fd89b256c",
    "src/vllm_optimizer/reporting/dashboard_selection.py": "c8bfed1b36e40a0202a95950baa0b01f5928794b08a254691daebcab416c9e2d",
    "src/vllm_optimizer/reporting/importance.py": "403ad6d9f41bd04b602163cec380b6b79291202b14778f6d37273b7b35f3a1f1",
    "src/vllm_optimizer/reporting/interactions.py": "86cd286eb058606c1e492bef3aa567c6c18c4f87ba2bb2cb772417cbe6004709",
    "src/vllm_optimizer/reporting/leaderboard.py": "9e68aa8cff9d627d82e03973704d8b7a5dd15da6bbabb6355e850e41a4e71fd7",
    "src/vllm_optimizer/reporting/llm_summary.py": "1fb51de68d91139dc9d0ae1a07db3f64fa11d2dce7f786ff9c4b8ce08c02c4fe",
    "src/vllm_optimizer/reporting/measurement.py": "51e594298efacfa9de8869eeec3a07c4ca052126c367eae7a00f49408141026d",
    "src/vllm_optimizer/reporting/methodology.py": "f2d6cb8d49ac41a46a87bf06af1235a339a120efff49d1b81e939c557586bf85",
    "src/vllm_optimizer/reporting/offline.py": "08cfd35f3e99f20210275388a385dfd21f669d567114b996d34c69f74931be8b",
    "src/vllm_optimizer/reporting/offline_loading.py": "e2018dafa24dbb5ba12e64dd051f7b5ea7ca0276dcd0a8328b42748a1c5e7ea2",
    "src/vllm_optimizer/reporting/reclassify.py": "ddeb5179006cfc5072805b549ce376887e9265d50be176433f6a05510086090d",
    "src/vllm_optimizer/reporting/reclassify_scores.py": "3ba5596657423af29f6c9fbe3df3fa7af56ec8f363c434fd828d05807b8fe52f",
    "src/vllm_optimizer/reporting/recommendation.py": "1524597ea3dabe299b45e36e4ddcedc55e6712af558bf81a9b507a526f9e60f0",
    "src/vllm_optimizer/reporting/reporter.py": "e775b41e4b7d9a8768870fedeb5d3279643cd413b6a35b45078cc52fa743d87e",
    "src/vllm_optimizer/reporting/styles.py": "2e99673bf029dd3b3cb56b907a980cf6e5960ef5d6fea4520c36f066c07867bc",
    "src/vllm_optimizer/reporting/tables.py": "459deb52fe078737921247f88e402db52dcfe2d4b76c7ab798438e5e558972c8",
    "src/vllm_optimizer/reporting/validation.py": "efc68e6279ab60f9d8ffcfc283b8736daa0459b6e04186fa5e0af8ffddb12bae",
    "src/vllm_optimizer/reporting/workloads.py": "238ac5a824d222c9f759dad97bea2773d25687d86ac24ef1735b207ce25dec26",
    "src/vllm_optimizer/reproduction/__init__.py": "0709802b8da827821036577d2c46a50d31a46dd1daf8842f0efe013fb93c2e6b",
    "src/vllm_optimizer/reproduction/accepted.py": "7275b130d2c5c49a367c2cee198070f726566a933e1ab1ba6edb9d7b551facf8",
    "src/vllm_optimizer/reproduction/display.py": "79f97773f8d2d01e3b7d5b1bd477cf05c13dc3447aef7e760a662dd4a6c07103",
    "src/vllm_optimizer/reproduction/export.py": "ac75a39e1ba056a9e5c34489ead92e6008201ee7d79de0f499f663e8a876872f",
    "src/vllm_optimizer/reproduction/manifest.py": "1e1d5b208286c3c3116f1b7daf16756464763643249fd3a619252b4a2e39dc6f",
    "src/vllm_optimizer/reproduction/metadata.py": "e15e8419248d99634c19076cd261d94ad7ae90a7c8194a3177a8f7e33e024a2b",
    "src/vllm_optimizer/reproduction/models.py": "6a3a7556815f6f66ea7b9f0f29159b12b0d8ce936a3a21537b5af29436388b9d",
    "src/vllm_optimizer/reproduction/reader.py": "16d491c416d0f32eac6f295d0e9b7096bf74d284e8711aa70b228efae3f2e891",
    "src/vllm_optimizer/reproduction/redaction.py": "23c4f229a1f602e4adc05e5859cfeff7e12b41bbb5e1749ca9e7d03d2ab041ff",
    "src/vllm_optimizer/search/__init__.py": "9275c82e928df60351aac48e6af9a98489924536d9f786af7b0f04efd40e3872",
    "src/vllm_optimizer/search/factory.py": "0750dddb14fc6a8010d938c9566a2242f123cb8e31e4a7f2a958bcd6f9096d20",
    "src/vllm_optimizer/search/fixed_session.py": "3665b61178acb20dbc8581a13bfbb1664ce4a35bf2ab2b282ba9df7904bdd274",
    "src/vllm_optimizer/search/grid.py": "4e6020e2b6f159444e9a455e48e2c068b8dd69c84ec54933df8aec08859055e9",
    "src/vllm_optimizer/search/grid_session.py": "f16c1b4dd89621526371aa047248e187f3c218c615eca950cd33e0be0baffe7e",
    "src/vllm_optimizer/search/optuna_session.py": "2356fd979df02ec9c3477f1de04d25724d214e63b555e24a7a17f910546dac1f",
    "src/vllm_optimizer/search/strategy.py": "e96ecbaeb62778d30ee35553d52facc2635cb54ca30fae3556dcc21e902eba4a",
    "src/vllm_optimizer/terminal.py": "828a8163b7216148db91a6249507039e323436234d3cd9f25dcef7531c8472fa",
    "src/vllm_optimizer/terminal_style.py": "0cf00914371e83196966820c9ef430fec7615cdd2856cb65acbb5ed05ac9146c",
    "src/vllm_optimizer/workers/__init__.py": "144fb68c108440133c580cfbd35ee718c2250027a3e4854b23bd0a2ff90d532a",
    "src/vllm_optimizer/workers/attempts.py": "21416d89f87f9c10352906a2990cf737c560f0a2ef41fd148a44d56cd08554e1",
    "src/vllm_optimizer/workers/base.py": "a3cb461d1f36fa2897fd13e6568891ecb9e882f39c76752a578bae09b261b754",
    "src/vllm_optimizer/workers/benchmark.py": "afe347527a745e3e37f73f37e0a12fa44fc3ebc291227ebe4b92e0d7098238eb",
    "src/vllm_optimizer/workers/benchmark_state.py": "204746379f0d56a2b8daf9e396efca0540ca9f6d7958cc8d14e4f3f288a1e8a6",
    "src/vllm_optimizer/workers/completion.py": "9cd9f23c0ba90f799597d7d91f49374a1c2dbc63763aab8a52c328e56e998d0e",
    "src/vllm_optimizer/workers/configuration.py": "8daaf35c7ae34b607fe7b184676da99da89bc8cc1ce6c566284cdd0a69582cd8",
    "src/vllm_optimizer/workers/drain.py": "f8268eb6a40fcedf887b46c73305b6afb168f610217f489edb53fd605c2090bb",
    "src/vllm_optimizer/workers/factory.py": "cc652033cf679a9b6a9911aeab251c9e38d873ef2da4bba967b87539bdd8bafc",
    "src/vllm_optimizer/workers/failure_details.py": "0ace7a65e6db546255746cf2138a71e9359a5f4e59cafef9a3afaca647b7c449",
    "src/vllm_optimizer/workers/guidellm_completion.py": "f765a0b8a5a60c0c37249760ea21bfed8c66de8d9045d16f8ab4a1c1339f8d12",
    "src/vllm_optimizer/workers/output_stream.py": "d97d351dfc77f90dc04ec44f909480e1bbdd6676b8557f546927f65d2dd54259",
    "src/vllm_optimizer/workers/process.py": "ac5979a3588527f6a0058ea7da47c27a5348fb4e0d642080af4ce525320d309a",
    "src/vllm_optimizer/workers/progress.py": "ace569f67fefe3566515fca1b08abd28d4031d70444b0bb7052ac6e654fd8f7b",
    "src/vllm_optimizer/workers/progress_policy.py": "f1cf3d58f23923b3e00bfd5c1faf53793efacf68c819017dd8764d3213707038",
    "src/vllm_optimizer/workers/readiness.py": "df63be790802cc7107c9e89041d23796f31c67b08925d13452d26b8a25376fa8",
    "src/vllm_optimizer/workers/vllm.py": "879a9fc79dc9be2e5514d19dd3e76ef60bc2e21c350ddeac6475640726979b03",
    "src/vllm_optimizer/workers/vllm_benchmark.py": "c49aa1a7bdc1fe3608dab7aa35a2410212ce07b40028b29bdc331c0adb1ed379"
  },
  "public_export": "Personal paths, GPU UUIDs, and artifact locations were redacted. Normalized result files were compacted and HTML/CSV outputs regenerated with the current reviewed report code; affected public manifest sizes and checksums were refreshed. Raw backend outputs, benchmark measurements, request counts, statuses, scores, and original-artifact hashes are unchanged.",
  "original_artifact_sha256": {
    "report.html": "a571fa31c267c443b5fe6822b7d8fdb7e292944811fe0417f9c35e88a11ad68c",
    "result.json": "036f0bbf96c628f901185150f4d8d370dcc6ced748b3331643ce08c393fa378b",
    "results.csv": "af04d2036ec36db61dbcf1189862f43a391659c79b3a3425e8e733c40df13344",
    "trials/baseline/manifest.json": "e286efe35f49cf205e716c8758a59b552895d91d3e8bcd23c7da72502b22c05c",
    "trials/baseline/result.json": "4630899294259bcf6037b5c5cf032bd25ba513bb79b5355fc2b92a613a455b65",
    "trials/trial-0001/manifest.json": "4b99c508a3ec8a8b156f105893fb29e50fe0808a61277da2f9027d175c791419",
    "trials/trial-0001/result.json": "86101d46256b18ccaa77a26c635a2272e1e7556a4ba967ec3d57f7d29f8b0e08",
    "trials/baseline/attempts/001/vllm.log": "43434f6794e55c40c9280f81e951f6101ffdb86e2aef4e1a15864ee5758ec29f",
    "trials/baseline/attempts/001/warmups/001/short-chat/benchmark.log": "268f096ce22d5f4257cfc18cc8efd5099a3508a2536cdad513a0c4037ad87851",
    "trials/baseline/attempts/001/warmups/001/short-chat/drain.json": "2ad203a5a94425ea76575d5fd1402512419c09a64a552341ceb0a2306eea7019",
    "trials/baseline/attempts/001/warmups/001/short-chat/results.json": "bb117f48eceb8f36020cc304f8c1ddb26838c02079853c10736bcaa256e7ea15",
    "trials/baseline/attempts/001/repeats/001/short-chat/benchmark.log": "9c2be1cf791f0030ea5af54a5ba6aaec32a34fa2e801292f6ffe2ea0aadbbe89",
    "trials/baseline/attempts/001/repeats/001/short-chat/drain.json": "3a7b87bd3faf03412dcaa0547fe9950c1cce79bb4667bf08fcf0ecc159a43b4e",
    "trials/baseline/attempts/001/repeats/001/short-chat/results.json": "144aa36fb735590ed303d8d30d65e27700cb56b439f477dced67e76a480eff26",
    "trials/baseline/attempts/001/repeats/002/short-chat/benchmark.log": "f6f1885641c81db87d7523b4569ec033628188afe2e81d0f7b9a503f3aa30e64",
    "trials/baseline/attempts/001/repeats/002/short-chat/drain.json": "3d56ef5def7ef244151896cc1b7956697dfd60296f7bbbb67995b1a9d510333f",
    "trials/baseline/attempts/001/repeats/002/short-chat/results.json": "e4ce2f85051fd0a80408052168fecf7f34d7621c2cc4b11e094843d917bae00e",
    "trials/baseline/attempts/001/repeats/003/short-chat/benchmark.log": "e54807e3815a7dfb56830c5d6e2e3f1e1db44de534254a4f832cd863568b1bcd",
    "trials/baseline/attempts/001/repeats/003/short-chat/drain.json": "329a7a75169c43aa514fb577f7c3e468a0d1ce0ec95ca2e906a7198b24f3e378",
    "trials/baseline/attempts/001/repeats/003/short-chat/results.json": "9d2f99375c4a7a14b0a86432e75ebb2556e1f2627bca6204c21f33a24acb62c9",
    "trials/trial-0001/attempts/001/vllm.log": "1db6031d5c6b164699a561c7ff39a2c4ab1f0f66855cbf1a77836d533fb104b6",
    "trials/trial-0001/attempts/001/warmups/001/short-chat/benchmark.log": "3cb37b803b57ca1f277f069ec18d7bad0eb89b35cb8af2d600f249b9b08e9d7a",
    "trials/trial-0001/attempts/001/warmups/001/short-chat/drain.json": "eec151c095589fd07838766442a969bd48446824a209d78c3bc7d2190df04346",
    "trials/trial-0001/attempts/001/warmups/001/short-chat/results.json": "4fd958adfd86e53c9fed8ec335f0a9d688978a15740d2259d13d0b0b1051800c",
    "trials/trial-0001/attempts/001/repeats/001/short-chat/benchmark.log": "806676790a3eca67f772a71491c592ef69497f76ce4839267cbed70562c9ee63",
    "trials/trial-0001/attempts/001/repeats/001/short-chat/drain.json": "c2ca1d28bc9a405a911584bfba6155a6ea5b554a52c3af0ea7691d47393f265e",
    "trials/trial-0001/attempts/001/repeats/001/short-chat/results.json": "c3ed248cbe9a9e4684b8d84b7f8fbcc953defd1393562a8bb2ecf7b60bbba099",
    "trials/trial-0001/attempts/001/repeats/002/short-chat/benchmark.log": "4a024f91e215d4ca9f6ac15444680cb0606cd010418c5f01c60d004ef75dd865",
    "trials/trial-0001/attempts/001/repeats/002/short-chat/drain.json": "4ef7187289f9b76a90706e23498466aebc1974f42fdf355c088438d200c0b3bc",
    "trials/trial-0001/attempts/001/repeats/002/short-chat/results.json": "52366be2ed6837cdd089f49996b527a4b8ece801acfd33e05b644a2fdbd0b5ce",
    "trials/trial-0001/attempts/001/repeats/003/short-chat/benchmark.log": "08db7ee2c86d965b8fe6e0ad7429c2efb58d32becdb24e9210df36878c955802",
    "trials/trial-0001/attempts/001/repeats/003/short-chat/drain.json": "ac5456b5440f653ca828c84398b623a774ece5ed5020487e82d3051a9bc855f2",
    "trials/trial-0001/attempts/001/repeats/003/short-chat/results.json": "1f7de668eb41bacaeb20c93b44797ef01258d303a1a0cc3eb36f5ffc82b575af"
  },
  "restoration_directory": "/var/tmp/vllm-optimizer-demo/public/baseline-control",
  "comparison_refresh": {
    "description": "Expanded comparison and coverage guards; HTML/CSV regenerated without changing archived measurements or scores.",
    "report_sha256": "fc1b5e80e8ccc1aedf9465362648d61bba8f317d54a5e2750e13d0e702140cf2",
    "csv_sha256": "df7363848208c11c9e75e474cc5c6dde02acb8801238cfdc72760ce25fa42d07",
    "source_files_sha256": {
      "src/vllm_optimizer/reporting/__init__.py": "5ee4b9d49e4303eca48e69671504bbf805e6b864c83204972f0f082e0ff8c69d",
      "src/vllm_optimizer/reporting/accepted_scores.py": "8a34df81cef9d1de100d4a8d3efdb086120bad0bfd6020ecb96592ff145760f1",
      "src/vllm_optimizer/reporting/analysis.py": "e32b8329ebe72c5524660da0622353894468cb75f8e57c77afebb0776d9105c6",
      "src/vllm_optimizer/reporting/charts.py": "eb1a85bc4c08e5f6d76a666d3b424080b4deaaf4b75666539efad1ffa3a3d797",
      "src/vllm_optimizer/reporting/comparison.py": "b149118e6b84e08981c8a56cb96e16a8e3d1336f7aed0079787bd197d79a41df",
      "src/vllm_optimizer/reporting/comparison_evidence.py": "f556ca6d68d67a68307a6ecd3b2fc596448a3b1bb0da8469a169496ba411e883",
      "src/vllm_optimizer/reporting/confidence.py": "318b393ce7ff98d666d0ba742d33e28f858010c9c54be0791c287aeec571526f",
      "src/vllm_optimizer/reporting/context.py": "b07e98c3e81104f29111e8d90e7d56a63afdf4a1551f7b283ac9ae5fd0bb3e4b",
      "src/vllm_optimizer/reporting/dashboard.py": "15d9e78328dbc39a9038d731198e8fce07f749098701c270bafc0d66ac002981",
      "src/vllm_optimizer/reporting/dashboard_selection.py": "1fbffd9143707c332e2f989c3a82a72baf322813d81478aa0c53d3a2133bdd1f",
      "src/vllm_optimizer/reporting/durations.py": "d08d0d3a68d98e98ef77f5b5ba062ecb8537a48d71d17d75575395ece1069a04",
      "src/vllm_optimizer/reporting/importance.py": "403ad6d9f41bd04b602163cec380b6b79291202b14778f6d37273b7b35f3a1f1",
      "src/vllm_optimizer/reporting/interactions.py": "410a242bf466711a3c277fb976740fce57fa78031b0548f27e9ba6cdbeced4da",
      "src/vllm_optimizer/reporting/leaderboard.py": "6593e718454b88452ed456a5d13d1227176b1d68cef51f28744867c599cddb99",
      "src/vllm_optimizer/reporting/llm_summary.py": "1fb51de68d91139dc9d0ae1a07db3f64fa11d2dce7f786ff9c4b8ce08c02c4fe",
      "src/vllm_optimizer/reporting/measurement.py": "0a98b0bd2c5198540e3f8901529a472afa4694ad8c41fc312298118f08de84d2",
      "src/vllm_optimizer/reporting/methodology.py": "3c89279882d858ded3d581436be1049e89510e64c47943d1c8c8fcaf126c0a1f",
      "src/vllm_optimizer/reporting/offline.py": "68f19d75e3d18a4d692cb3e810652af6d1db883776689abfe05b6df84ac8cbca",
      "src/vllm_optimizer/reporting/offline_loading.py": "e2018dafa24dbb5ba12e64dd051f7b5ea7ca0276dcd0a8328b42748a1c5e7ea2",
      "src/vllm_optimizer/reporting/reclassify.py": "5406b971ad8847b42731650667a898903d65f973075e7c6d0c8d324eb3e267e5",
      "src/vllm_optimizer/reporting/reclassify_scores.py": "e9f8376d8e43eda273278d0e499a9e05aab2c45e7250ab0e65eaaff809ac5216",
      "src/vllm_optimizer/reporting/recommendation.py": "06c0b175b9c494f2c39e2d2fe1c29531f1a9a211fc115cc7d80b9e2720502ef0",
      "src/vllm_optimizer/reporting/reporter.py": "e775b41e4b7d9a8768870fedeb5d3279643cd413b6a35b45078cc52fa743d87e",
      "src/vllm_optimizer/reporting/styles.py": "2e99673bf029dd3b3cb56b907a980cf6e5960ef5d6fea4520c36f066c07867bc",
      "src/vllm_optimizer/reporting/tables.py": "b5d7e110b163053ae0f3be7d33b5c773a750d4ef9133f241a4bdabdb95c95bcc",
      "src/vllm_optimizer/reporting/validation.py": "efc68e6279ab60f9d8ffcfc283b8736daa0459b6e04186fa5e0af8ffddb12bae",
      "src/vllm_optimizer/reporting/workloads.py": "d395c113d9dc83c9a228f413423b09fbbab2fcb57c6eb3fa888c70d492855994"
    }
  },
  "concise_report_refresh": {
    "description": "Concise overview, throughput/duration summary, and full trial details; HTML/CSV regenerated without changing archived measurements or scores.",
    "report_sha256": "c9b6453067d7014e40f22d8cfb6199d139566cd371c036fe475a9cb653417807",
    "csv_sha256": "df7363848208c11c9e75e474cc5c6dde02acb8801238cfdc72760ce25fa42d07",
    "source_files_sha256": {
      "src/vllm_optimizer/reporting/__init__.py": "5ee4b9d49e4303eca48e69671504bbf805e6b864c83204972f0f082e0ff8c69d",
      "src/vllm_optimizer/reporting/accepted_scores.py": "4c7dccf8fdf8f23d728dc893b512690f958a752dd75c529d0bf20714647a56a6",
      "src/vllm_optimizer/reporting/analysis.py": "e32b8329ebe72c5524660da0622353894468cb75f8e57c77afebb0776d9105c6",
      "src/vllm_optimizer/reporting/charts.py": "eb1a85bc4c08e5f6d76a666d3b424080b4deaaf4b75666539efad1ffa3a3d797",
      "src/vllm_optimizer/reporting/comparison.py": "0860838d574cf628c65eddb43452a579b9d698b831fb50f37e61a72fe8c0aaa1",
      "src/vllm_optimizer/reporting/comparison_evidence.py": "5d317652a5e7d5d439b92968931d2ffb448803e94d054f8230b525e4d32f4108",
      "src/vllm_optimizer/reporting/confidence.py": "a7cef35f640ad0776832f6b00256606ed4c696eb885a1a56701dedc2686fc914",
      "src/vllm_optimizer/reporting/context.py": "0817b5d05c4882a860a38be789df4bf064f9c6047af76a2f47b844934e100b16",
      "src/vllm_optimizer/reporting/dashboard.py": "11a70571c85972b6348733ca495f1fd1995759fe48f78c7688597932bdc4367c",
      "src/vllm_optimizer/reporting/dashboard_selection.py": "1fbffd9143707c332e2f989c3a82a72baf322813d81478aa0c53d3a2133bdd1f",
      "src/vllm_optimizer/reporting/durations.py": "d08d0d3a68d98e98ef77f5b5ba062ecb8537a48d71d17d75575395ece1069a04",
      "src/vllm_optimizer/reporting/finalist_decision.py": "a6407500e957c559bee89e5f91cbd683e1a34920596d480bda93b70d7ffcc9f2",
      "src/vllm_optimizer/reporting/importance.py": "403ad6d9f41bd04b602163cec380b6b79291202b14778f6d37273b7b35f3a1f1",
      "src/vllm_optimizer/reporting/interactions.py": "239700e353150b87a65bcb170fd8fc5f1ebe6f944cd3218f4a2792c002f9a549",
      "src/vllm_optimizer/reporting/leaderboard.py": "73c04ccd24eb3f1c742388a8b5ab73093357108f99078db03933e37bf1a875d8",
      "src/vllm_optimizer/reporting/llm_summary.py": "10136827fad3174ef8006040551b9fd4460fda479580f8c88e88182173f68d14",
      "src/vllm_optimizer/reporting/measurement.py": "0a98b0bd2c5198540e3f8901529a472afa4694ad8c41fc312298118f08de84d2",
      "src/vllm_optimizer/reporting/methodology.py": "3c89279882d858ded3d581436be1049e89510e64c47943d1c8c8fcaf126c0a1f",
      "src/vllm_optimizer/reporting/offline.py": "486a173562740ac14c258d0f7b1e00060a6ff9c8971ffd159bddfa48b38b8518",
      "src/vllm_optimizer/reporting/offline_loading.py": "e2018dafa24dbb5ba12e64dd051f7b5ea7ca0276dcd0a8328b42748a1c5e7ea2",
      "src/vllm_optimizer/reporting/overview.py": "9e9a4bfcf2721ae354be3afa868e99af411feca5bfadf6da2dc67330bf5a23ac",
      "src/vllm_optimizer/reporting/reclassify.py": "34730c63bd8ff9b3afc1a6f0a0ba184656b7d9f978da940666ee8bc475375b24",
      "src/vllm_optimizer/reporting/reclassify_scores.py": "e9f8376d8e43eda273278d0e499a9e05aab2c45e7250ab0e65eaaff809ac5216",
      "src/vllm_optimizer/reporting/recommendation.py": "1c8fb65735c721dc9dac0025524a0592bb7460c7b4dcf289c9b98fc85f73ccc2",
      "src/vllm_optimizer/reporting/reporter.py": "e775b41e4b7d9a8768870fedeb5d3279643cd413b6a35b45078cc52fa743d87e",
      "src/vllm_optimizer/reporting/styles.py": "b4ffcb252979943386aec8871e5726b8030e363439275b654c4751e3b85f9cbc",
      "src/vllm_optimizer/reporting/tables.py": "b5d7e110b163053ae0f3be7d33b5c773a750d4ef9133f241a4bdabdb95c95bcc",
      "src/vllm_optimizer/reporting/validation.py": "66361b56b4b3fd34be119a16e26ba0d861b3775fb20183100d3e53e49bdc5488",
      "src/vllm_optimizer/reporting/workloads.py": "150a83ceca85d589e766cecd78b078165f11ac8c125f786b598f7fb8b588fe25"
    }
  }
}