{ "credit": "Taylor (gtmcknight), github.com/gtmcknight/amm-sim@4812a6382311624e1506aca131ca35c378f930d9 research/solved", "idea": "Measure where qbase split testing pays by reporting all six prescribed restrictions against stalerival BASE, with the tested share of own callbacks. No arm selection.", "status": "failed", "failed": { "stage": "fetch_required_sources", "reason": "Required qbase.py, quotient.py and stalerival.py artifacts could not be retrieved. All five initial urllib downloads ended with . Default curl to the pinned fetch.sh exited 28 (Connection timed out after 15002 milliseconds). Direct curl with --noproxy exited 6: Could not resolve host: api.imd.fun; a separate direct request likewise could not resolve raw.githubusercontent.com. Browser fallback read the pinned fetch script and kit README but returned Internal Error / URL is not accessible via this tool for each of the three required artifact URLs. No reference or replacement policy was executed.", "requester_input_needed": false }, "setup": { "status": "not_completed", "source_urls": { "fetch": "https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research/tell/fetch.sh", "kit_readme": "https://raw.githubusercontent.com/identity-md-launches/goal-3178-build-shared-evaluation-kit/45e7563d1a29ffca9d608fdf60c90bf2624d2d01/README.md", "qbase": "https://api.imd.fun/artifacts/88712dac0e4b048a0860ccb13d2f22e13d956161c102939cb480f53388f3b185", "quotient": "https://api.imd.fun/artifacts/bb1b85910e7628d6c716ee1328da911b4da42c0903cb6c96309cfda82a379abd", "base": "https://api.imd.fun/artifacts/f5a140f51df99423d6ede60b618dbc6eabc37a3050ac439c80dc3824191e9f59" }, "reference_rebuild_commands_not_executed": [ "R=https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research", "sh fetch.sh \"$R\" scratch/amm", "cd scratch/amm", "PROCS= python3 -I run.py stalerival:Policy 64900 8 out.json soft=1 qm=qm_k1e-5.json a0=0.35 ainf=0.35" ], "prerequisites": "Download pinned tell/fetch.sh and decode code_zb64 from the three named artifact JSON objects into the reference directory; neither succeeded. Commands above are the requested reference recipe, not evidence of a successful rebuild.", "manifest_verified_files": 0, "manifest_mismatches": null }, "rule": { "status": "planned_only_not_implemented", "settings": [ { "name": "first_callback", "restriction": "Only the first own callback at a step timestamp." }, { "name": "later_callbacks", "restriction": "Only own callbacks after the first at the same step timestamp." }, { "name": "move_gt_0_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 0 bps." }, { "name": "move_gt_2_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 2 bps." }, { "name": "move_gt_5_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 5 bps." }, { "name": "gap_at_least_2_steps", "restriction": "Only when at least two steps have passed since the previous own callback." } ], "callback_share_definition": "Number of own callbacks on which the split test is actually evaluated divided by total own callbacks, counted separately per arm.", "state_kept": null, "arithmetic_per_callback": null, "limitation": "The source modules were unavailable; bound direction, exact arithmetic, and initial-callback conventions were not guessed." }, "frozen": { "params": { "base": { "soft": 1, "qm": "qm_k1e-5.json", "a0": 0.35, "ainf": 0.35 }, "settings": [ { "name": "first_callback", "restriction": "Only the first own callback at a step timestamp." }, { "name": "later_callbacks", "restriction": "Only own callbacks after the first at the same step timestamp." }, { "name": "move_gt_0_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 0 bps." }, { "name": "move_gt_2_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 2 bps." }, { "name": "move_gt_5_bps", "restriction": "Only when a hit would move the rival estimate against the bound by strictly more than 5 bps." }, { "name": "gap_at_least_2_steps", "restriction": "Only when at least two steps have passed since the previous own callback." } ] }, "code_sha256": null, "status": "No executable module obtained or implemented; no code freeze claimed." }, "choose": { "seeds": [], "table": [], "selection": "None; report every arm as requested. Settings were recorded without scoring." }, "report": { "seeds": [], "n": 0, "arms": [ { "name": "first_callback", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" }, { "name": "later_callbacks", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" }, { "name": "move_gt_0_bps", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" }, { "name": "move_gt_2_bps", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" }, { "name": "move_gt_5_bps", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" }, { "name": "gap_at_least_2_steps", "n": 0, "minus_base": { "mean_diff": null, "se": null, "min": null, "worst5": [] }, "callbacks_tested": null, "callbacks_total": null, "share_callbacks_tested": null, "status": "not_run_source_fetch_failed" } ] }, "cost": { "extra_storage_words": null, "worst_ops_per_callback": null, "status": "Not estimated without verified source and implementation." }, "diagnostics": { "eight_seed_timing": { "status": "not_run", "planned_seeds": "64900..64907" }, "disabled_matches_base_exactly": { "status": "not_run", "planned_seeds": "64900..64907" }, "hidden_input_garbling": { "status": "not_run", "identical_fees": null }, "reference_manifest_check": "not_run; 34 files and 0 mismatches were requested, not observed", "drop_rule": "mean_diff + 3*se < 0; not applied because no scores exist", "report_protocol": "Planned ascending 64-seed blocks within 10000..12047, all arms and BASE paired, minimum 512 seeds; not started.", "gates": "No gates or simulations ran. This is a Python-only failed experiment; no contract or submission was created." }, "advance": false, "pick": null, "code_zb64": null, "rows_zb64": "eJyLjgUAARUAuQ==", "seeds_used": [], "not_done": [ "Retrieve and verify required policy modules and 34 reference files", "Implement six restricted-test arms subclassing BASE", "Time eight seeds", "Verify disabled exact row equality", "Verify identical fees after hidden-input garbling", "Freeze executable code SHA256", "Run ordered paired report on at least 512 seeds", "Measure callback test shares and per-arm statistics", "Derive arithmetic and storage costs" ] }