{ "run_id": "vinnylarouge--jevlike-claude-haiku-5-5-1792803213193376094", "date": "2026-10-24T01:14:12.302207+00:00", "repo": "vinnylarouge/jevlike", "kind": "repo", "source": "https://github.com/vinnylarouge/jevlike", "commit": "94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": true, "outcome": "pass", "time_to_working_s": 708.6398443999933, "total_s": 1239.1087973117828, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat /etc/os-release | head -3 && git status 2>&1 | head -2; ls /inputs 2>&1", "cd && find . -maxdepth 2 -not -path './.git*' | head -100; echo ---; cat README.md 2>/dev/null | head -200", "cd && cat pyproject.toml; echo ---; which uv git node npm; uv --version 2>&1; git --version; ls .coldpass; echo ---; grep -n -i \"python\\|uv \" AGENTS.md | head -20; ls examples/* | head -50; ls tests", "cd && git init -q && git remote add origin https://github.com/vinnylarouge/jevlike && git fetch --depth 1 origin 94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452 2>&1 | tail -5; git reset --mixed FETCH_HEAD 2>&1 | tail -3; git log --oneline -1; git status --short | head; python3 -m pip --version 2>&1; python3 -m pip install --user uv 2>&1 | tail -3 ; ls ~/.local/bin", "sudo -n apt-get update -qq 2>&1 | tail -2; sudo -n DEBIAN_FRONTEND=noninteractive apt-get install -y -qq python3-pip python3-venv 2>&1 | tail -3; python3 -m pip --version && python3 -m pip install --user --break-system-packages -q uv 2>&1 | tail -3; ls ~/.local/bin; ~/.local/bin/uv --version", "cd && export PATH=$HOME/.local/bin:$PATH && uv venv 2>&1 | tail -2 && source .venv/bin/activate && uv pip install -e '.[dev]' 2>&1 | tail -5; which jevlike-train; python --version", "cd && source .venv/bin/activate && jevlike-data synthetic --output data/synthetic 2>&1 | tail -5; ls data/synthetic; jevlike-train data/synthetic/train.jsonl --validation data/synthetic/validation.jsonl --output runs/synthetic.pt 2>&1 | tail -8; ls -la runs", "cd && source .venv/bin/activate && jevlike-eval runs/synthetic.pt data/synthetic/test.jsonl 2>&1 | tail -5; echo \"--- predict\"; jevlike-predict runs/synthetic.pt --context \"Choose the exact badge amber badger. Badge: amber badger.\" --option \"azure crane\" --option \"amber badger\" --option \"gold heron\" 2>&1 | tail -20", "cd && source .venv/bin/activate && jevlike-eval runs/synthetic.pt data/synthetic/test.jsonl 2>&1", "cd && source .venv/bin/activate && python -m pytest -q 2>&1 | tail -5; echo ---; grep -rn -i \"sleep\\|cron\\|schedule\\|while True\\|webhook\\|--once\\|--now\\|interval\" --include=*.py --include=*.md --include=*.sh jevlike examples/doom/*.py examples/chess/*.py README.md examples/*/README.md scripts 2>/dev/null | head -30", "cd && export PATH=$HOME/.local/bin:$PATH && source .venv/bin/activate && timeout 900 uv pip install -e '.[dev,games]' 2>&1 | tail -6; echo \"rc=$?\"", "cd && source .venv/bin/activate && PYTHONPATH=examples/doom timeout 900 pytest -q examples/doom/test_smoke.py 2>&1 | tail -8; echo \"rc=${PIPESTATUS[0]}\"; cd examples/chess && timeout 900 python test_smoke.py 2>&1 | tail -8; echo \"chess rc=${PIPESTATUS[0]}\"", "cd && source .venv/bin/activate && ls runs/doom.mp4 runs/doom-trace.json 2>&1; time (timeout 1500 python examples/doom/play.py examples/checkpoints/joint-imitation.pt --episodes 10 --game-seconds 35.3 --device cpu --capture-resolution 640x480 --output runs/doom.mp4 --trace runs/doom-trace.json > /tmp/doom-out.txt 2>&1); echo rc=$?; tail -c 1200 /tmp/doom-out.txt; ls -la runs", "cd && ls -la .coldpass runs 2>&1; ls 2>&1", "cd && rm -f runs/doom.mp4 runs/doom-trace.json && V= && cat > .coldpass/probe.json <\",\"expected_text\":\"amber badger\"}\nEOF\ncat > .coldpass/claims.json <\"},\n{\"kind\":\"claim\",\"claim\":\"Score one new menu with the trained model\",\"source\":\"They create local synthetic data, train on it, evaluate the saved model and score one new menu.\",\"input\":\"context about amber badger with three options\",\"expected\":\"amber badger receives probability near 1.0\",\"probe_kind\":\"cli\",\"argv\":[\"$V/jevlike-predict\",\"runs/synthetic.pt\",\"--context\",\"Choose the exact badge amber badger. Badge: amber badger.\",\"--option\",\"azure crane\",\"--option\",\"amber badger\",\"--option\",\"gold heron\"],\"expected_text\":\"amber badger\",\"cwd\":\"\"},\n{\"kind\":\"claim\",\"claim\":\"Shuffled-context control is reported alongside the model\",\"source\":\"The command also prints a shuffled-context control, which pairs each menu with the wrong context.\",\"input\":\"runs/synthetic.pt data/synthetic/test.jsonl\",\"expected\":\"shuffled_context top1 printed as 0.2275\",\"probe_kind\":\"cli\",\"argv\":[\"$V/jevlike-eval\",\"runs/synthetic.pt\",\"data/synthetic/test.jsonl\"],\"expected_text\":\"\\\"top1\\\": 0.2275\",\"cwd\":\"\"}\n]\nEOF\ncat > .coldpass/examples.json <\",\"expected_text\":\"best_validation_nll\"},\n{\"kind\":\"example\",\"claim\":\"Doom example plays the released joint checkpoint and writes a trace\",\"source\":\"README.md Demo\",\"input\":\"examples/checkpoints/joint-imitation.pt, 10 episodes, 640x480 capture\",\"expected\":\"JSON summary with episodes 10 and video/trace paths\",\"argv\":[\"$V/python\",\"examples/doom/play.py\",\"examples/checkpoints/joint-imitation.pt\",\"--episodes\",\"10\",\"--game-seconds\",\"35.3\",\"--device\",\"cpu\",\"--capture-resolution\",\"640x480\",\"--output\",\"runs/doom.mp4\",\"--trace\",\"runs/doom-trace.json\"],\"cwd\":\"\",\"expected_text\":\"\\\"episodes\\\": 10\"},\n{\"kind\":\"example\",\"claim\":\"Doom example smoke tests\",\"source\":\"AGENTS.md Setup test commands\",\"input\":\"examples/doom/test_smoke.py\",\"expected\":\"2 passed\",\"argv\":[\"$V/pytest\",\"-q\",\"examples/doom/test_smoke.py\"],\"env\":{\"PYTHONPATH\":\"examples/doom\"},\"cwd\":\"\",\"expected_text\":\"2 passed\"},\n{\"kind\":\"example\",\"claim\":\"Chess example smoke test\",\"source\":\"AGENTS.md Setup test commands\",\"input\":\"examples/chess/test_smoke.py\",\"expected\":\"ok\",\"argv\":[\"$V/python\",\"test_smoke.py\"],\"cwd\":\"\",\"expected_text\":\"ok\"},\n{\"kind\":\"example\",\"claim\":\"Repository offline test suite\",\"source\":\"AGENTS.md Setup test commands\",\"input\":\"tests/test_smoke.py\",\"expected\":\"1 passed\",\"argv\":[\"$V/pytest\",\"-q\"],\"cwd\":\"\",\"expected_text\":\"1 passed\"},\n{\"kind\":\"example\",\"claim\":\"Film rendering from the Doom trace\",\"source\":\"README.md Demo\",\"reason\":\"not run: needs Node/npm (absent in guest) and a separate npm/npx setup step that fetches an extra tool; that step was not performed\",\"deferred\":true},\n{\"kind\":\"example\",\"claim\":\"Wikispeedia next-click data example\",\"source\":\"README.md Wikispeedia example\",\"reason\":\"not run: scripts/get_wikispeedia.sh downloads external SNAP archives; not needed for the core quickstart\",\"deferred\":true},\n{\"kind\":\"example\",\"claim\":\"Frozen Hugging Face encoder training\",\"source\":\"README.md Use a frozen pretrained encoder\",\"reason\":\"not run: requires transformers install and downloading Qwen/Qwen2.5-0.5B from Hugging Face (large model download)\",\"deferred\":true}\n]\nEOF\ncat > .coldpass/cycles.json </dev/null && echo \"$f ok\"; done; ls runs", "cd && = timeout 1500 python3 -I --validate --replay 2>&1 | tail -80; echo \"rc=${PIPESTATUS[0]}\"", "cd && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Train, evaluate and score a one-pass option scorer with the jevlike CLIs from the README Quickstart (jevlike-data, jevlike-train, jevlike-eval, jevlike-predict), plus the documented Doom and chess example checks.\",\"operation_scope\":\"Linux Ubuntu 24.04, Python 3.12.3, CPU only, pinned commit 94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452. Installed uv 0.13.5 via pip (user install) and python3-pip/python3-venv via apt. Game extras installed via uv. No Node/npm, no external datasets or Hugging Face models.\",\"steps\":[\"git init; git remote add origin https://github.com/vinnylarouge/jevlike; git fetch --depth 1 origin 94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452; git reset --mixed FETCH_HEAD\",\"sudo apt-get install -y python3-pip python3-venv\",\"python3 -m pip install --user --break-system-packages uv\",\"uv venv\",\"source .venv/bin/activate && uv pip install -e '.[dev]'\",\"jevlike-data synthetic --output data/synthetic\",\"jevlike-train data/synthetic/train.jsonl --validation data/synthetic/validation.jsonl --output runs/synthetic.pt\",\"jevlike-eval runs/synthetic.pt data/synthetic/test.jsonl\",\"jevlike-predict runs/synthetic.pt --context \\\"Choose the exact badge amber badger. Badge: amber badger.\\\" --option \\\"azure crane\\\" --option \\\"amber badger\\\" --option \\\"gold heron\\\"\",\"uv pip install -e '.[dev,games]' (AGENTS.md setup)\",\"pytest -q; PYTHONPATH=examples/doom pytest -q examples/doom/test_smoke.py; cd examples/chess && python test_smoke.py\",\"python examples/doom/play.py examples/checkpoints/joint-imitation.pt --episodes 10 --game-seconds 35.3 --device cpu --capture-resolution 640x480 --output runs/doom.mp4 --trace runs/doom-trace.json\"],\"deviations\":[\"uv was not present; installed via pip (apt python3-pip first, since pip was missing). Setup only.\",\"Quickstart eval: top1 0.9975 for the model vs 0.2275 for the shuffled-context control. Predict gave 'amber badger' probability 1.0.\",\"Doom play run: 10 episodes gave mean_kills 0.4 and mean_reward -94.78; the README cites 0.60 kills and -97.50 reward for the same checkpoint. Results vary between runs, so this is not treated as a mismatch.\",\"README Demo film step not run: it needs Node/npm, which is absent, and a separate tool download that this guest does not permit. This is a prerequisite gap for that step only; the core operation is unaffected.\",\"Wikispeedia and frozen Hugging Face encoder examples deferred: they download external data or a large model; not needed for the core operation.\",\"The README's frozen-encoder path was not exercised, so its Hugging Face download behaviour is unverified.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"None needed for the core operation. To run the README film step, provide Node/npm and allow its separate tool download.\"}\nEOF\npython3 -m json.tool .coldpass/report.json >/dev/null && echo report ok; ls -la .coldpass", "cd && = timeout 1500 python3 -I --validate --replay > /tmp/final-check.txt 2>&1; echo \"rc=$?\"; python3 -I -c \"import json;d=json.load(open('/tmp/final-check.txt'));print(d['valid'],d['problems'],d['replay']['status'])\" 2>&1 | tail -3" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Train, evaluate and score a one-pass option scorer with the jevlike CLIs from the README Quickstart (jevlike-data, jevlike-train, jevlike-eval, jevlike-predict), plus the documented Doom and chess example checks.", "suggested_fix": null, "tokens_in": 410118, "tokens_out": 18440, "cost_usd": 0.02017675, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "runs/synthetic.pt", "--context", "Choose the exact badge amber badger. Badge: amber badger.", "--option", "azure crane", "--option", "amber badger", "--option", "gold heron" ], "kind": "cli", "returncode": 0, "stdout": "[\n {\n \"option\": \"azure crane\",\n \"probability\": 1.0349932466624523e-08\n },\n {\n \"option\": \"amber badger\",\n \"probability\": 1.0\n },\n {\n \"option\": \"gold heron\",\n \"probability\": 4.9812562963325036e-08\n[excerpt truncated]", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks.", "findings": [], "context": [], "limitations": [ "A short run cannot establish that code is safe.", "Connections show IP addresses; proxies can hide the final hostname.", "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=vinnylarouge--jevlike-claude-haiku-5-5-1792803213193376094", "evidence_file": "/data/safety/vinnylarouge--jevlike-claude-haiku-5-5-1792803213193376094.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 18, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452", "url": "https://github.com/vinnylarouge/jevlike" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 18, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/vinnylarouge/jevlike", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "Entry points inspected (jevlike-data, jevlike-train, jevlike-eval, jevlike-predict in pyproject.toml; jevlike/*.py; examples). No cron, scheduler, --once/--now, loop or webhook exists in the product. The only sleep calls are game-pacing loops in examples/doom/play.py and examples/chess/play.py, which are not product cycles. Each CLI runs once when invoked.", "evidence": "Entry points inspected (jevlike-data, jevlike-train, jevlike-eval, jevlike-predict in pyproject.toml; jevlike/*.py; examples). No cron, scheduler, --once/--now, loop or webhook exists in the product. The only sleep calls are game-pacing loops in examples/doom/play.py and examples/chess/play.py, which are not product cycles. Each CLI runs once when invoked.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Evaluation prints top-1 accuracy on the held-out test file", "source": "The evaluation prints top-1 accuracy, which is the fraction of correct first choices.", "input": "runs/synthetic.pt data/synthetic/test.jsonl", "expected": "model top1 printed as 0.9975", "command": " runs/synthetic.pt data/synthetic/test.jsonl", "verdict": "yes", "outcome": "Real input produced the expected result: \"top1\": 0.9975", "evidence": "\"top1\": 0.9975,\n \"top3\": 1.0,\n \"ece\": 0.004109287678147666,\n \"examples\": 400\n },\n \"shuffled_context\": {\n \"top1\": 0.2275,\n \"top3\": 0.6825,\n \"ece\": 0.6250180058996193,\n \"examples\": 400\n },\n \"device\": \"cpu\"\n}\n", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Score one new menu with the trained model", "source": "They create local synthetic data, train on it, evaluate the saved model and score one new menu.", "input": "context about amber badger with three options", "expected": "amber badger receives probability near 1.0", "command": " runs/synthetic.pt --context 'Choose the exact badge amber badger. Badge: amber badger.' --option 'azure crane' --option 'amber badger' --option 'gold heron'", "verdict": "yes", "outcome": "Real input produced the expected result: amber badger", "evidence": "amber badger\",\n \"probability\": 1.0\n },\n {\n \"option\": \"gold heron\",\n \"probability\": 4.9812562963325036e-08\n }\n]\n", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Shuffled-context control is reported alongside the model", "source": "The command also prints a shuffled-context control, which pairs each menu with the wrong context.", "input": "runs/synthetic.pt data/synthetic/test.jsonl", "expected": "shuffled_context top1 printed as 0.2275", "command": " runs/synthetic.pt data/synthetic/test.jsonl", "verdict": "yes", "outcome": "Real input produced the expected result: \"top1\": 0.2275", "evidence": "\"top1\": 0.2275,\n \"top3\": 0.6825,\n \"ece\": 0.6250180058996193,\n \"examples\": 400\n },\n \"device\": \"cpu\"\n}\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Quickstart training on synthetic data writes a checkpoint", "source": "README.md Quickstart", "input": "data/synthetic/train.jsonl with validation; fresh output runs/replay-train.pt", "command": " data/synthetic/train.jsonl --validation data/synthetic/validation.jsonl --output runs/replay-train.pt", "evidence": "h\": 4, \"train_nll\": 0.042619120180606845, \"validation_nll\": 0.0345140016078949, \"device\": \"cpu\"}\n{\"epoch\": 5, \"train_nll\": 0.019992097705602646, \"validation_nll\": 0.028758792504668236, \"device\": \"cpu\"}\n{\"epoch\": 6, \"train_nll\": 0.021846030103042723, \"validation_nll\": 0.019645809847861528, \"device\": \"cpu\"}\n{\"epoch\": 7, \"train_nll\": 0.009171441148966552, \"validation_nll\": 0.007989753340370952, \"device\": \"cpu\"}\n{\"epoch\": 8, \"train_nll\": 0.003976261492818594, \"validation_nll\": 0.008053538376116194, \"device\": \"cpu\"}\n{\"checkpoint\": \"runs/replay-train.pt\", \"best_validation_nll\": 0.007989753340370952}", "deferred": false, "expected": "checkpoint written with best_validation_nll", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Doom example plays the released joint checkpoint and writes a trace", "source": "README.md Demo", "input": "examples/checkpoints/joint-imitation.pt, 10 episodes, 640x480 capture", "command": " examples/doom/play.py examples/checkpoints/joint-imitation.pt --episodes 10 --game-seconds 35.3 --device cpu --capture-resolution 640x480 --output runs/doom.mp4 --trace runs/doom-trace.json", "evidence": "{\"episodes\": 10, \"mean_reward\": -94.78393249511718, \"mean_kills\": 0.4, \"mean_wall_game_ratio\": 1.0215097106955706, \"online_inference_ms\": 2.748335302327975, \"cpu_ms\": 1.0682277600000134, \"video\": \"runs/doom.mp4\", \"trace\": \"runs/doom-trace.json\"}", "deferred": false, "expected": "JSON summary with episodes 10 and video/trace paths", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Doom example smoke tests", "source": "AGENTS.md Setup test commands", "input": "examples/doom/test_smoke.py", "command": " -q examples/doom/test_smoke.py", "evidence": ".. [100%]\n2 passed in 5.91s", "deferred": false, "expected": "2 passed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Chess example smoke test", "source": "AGENTS.md Setup test commands", "input": "examples/chess/test_smoke.py", "command": " test_smoke.py", "evidence": "ok", "deferred": false, "expected": "ok", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Repository offline test suite", "source": "AGENTS.md Setup test commands", "input": "tests/test_smoke.py", "command": " -q", "evidence": ". [100%]\n1 passed in 11.19s", "deferred": false, "expected": "1 passed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Film rendering from the Doom trace", "source": "README.md Demo", "input": "", "command": "", "evidence": "not run: needs Node/npm (absent in guest) and a separate npm/npx setup step that fetches an extra tool; that step was not performed", "deferred": true, "expected": "documented command completes successfully", "verdict": "deferred", "outcome": "not run: needs Node/npm (absent in guest) and a separate npm/npx setup step that fetches an extra tool; that step was not performed" }, { "kind": "example", "claim": "Wikispeedia next-click data example", "source": "README.md Wikispeedia example", "input": "", "command": "", "evidence": "not run: scripts/get_wikispeedia.sh downloads external SNAP archives; not needed for the core quickstart", "deferred": true, "expected": "documented command completes successfully", "verdict": "deferred", "outcome": "not run: scripts/get_wikispeedia.sh downloads external SNAP archives; not needed for the core quickstart" }, { "kind": "example", "claim": "Frozen Hugging Face encoder training", "source": "README.md Use a frozen pretrained encoder", "input": "", "command": "", "evidence": "not run: requires transformers install and downloading Qwen/Qwen2.5-0.5B from Hugging Face (large model download)", "deferred": true, "expected": "documented command completes successfully", "verdict": "deferred", "outcome": "not run: requires transformers install and downloading Qwen/Qwen2.5-0.5B from Hugging Face (large model download)" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-09-16T18:12:49Z", "commits_90d": 3, "merged_prs_90d": 0, "open_issues": 3, "open_prs": 5, "reply_share": 0.0, "reply_threads": 8, "median_reply_hours": null, "last_release_at": null, "archived": false, "verdict": "slow", "note": "slow: last commit 37 days ago; 3 commits and 0 merged PRs in 90 days; 3 open issues, 5 open PRs; 0 of 8 recent threads got a maintainer reply; no releases" }, "maintenance_verdict": "slow", "maintenance_note": "slow: last commit 37 days ago; 3 commits and 0 merged PRs in 90 days; 3 open issues, 5 open PRs; 0 of 8 recent threads got a maintainer reply; no releases", "maintained": "active", "maintained_note": "last commit 37 days ago; 3 open issues, 0 answered or closed", "last_commit_at": "2026-09-16T18:12:53Z", "last_release_at": null, "open_issues": 3, "answered_issues": 0, "platforms_claimed": [ "linux" ], "topic": "other", "agent_interfaces": [ { "interface": "cli", "evidence": "independent checker", "observed": true, "operation_checked": true } ], "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.", "mcp_context": null, "tested_at": "2026-10-24T01:14:12.302207+00:00", "tested_commit": "94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452", "tested_with": { "agent": "claude-code", "agent_version": "2.1.300 (Claude Code)", "model": "claude-haiku-5-5", "model_route": "claude-haiku-5-5", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "vinnylarouge/jevlike", "source": "https://github.com/vinnylarouge/jevlike", "commit": "94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "94f5fd1b0b11d52bbdfdf4e0ee6aa96b568f8452", "url": "https://github.com/vinnylarouge/jevlike" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Train, evaluate and score a one-pass option scorer with the jevlike CLIs from the README Quickstart (jevlike-data, jevlike-train, jevlike-eval, jevlike-predict), plus the documented Doom and chess example checks.", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/vinnylarouge--jevlike-claude-haiku-5-5-1792803213193376094.json" }