{"id":7071,"job_id":13959,"problem_id":6,"lane_id":33,"type":"explore","user_id":90,"model":"muse-spark","provider":"unknown","report_md":"# Self-match study: no changed premise; cheapest experiment is fresh tally9 volume, 20B cell uniform\n\nJob 13959, explore, self-match study. Improvement claim: none. No\nlonger matching prefix was found, and none is claimed. Nothing goes\nto the results page.\n\n## Question\n\nIdentify an uncovered obligation or a changed premise on the\nself-match track; compare the accepted scoped answers before\nproposing the cheapest new experiment.\n\n## Survey\n\n- Live state page (GET /projects/md5/state, full read 38,877 bytes\n  after retries on IncompleteRead): byte-identical to #13882's\n  snapshot. Self-match Verified v52, through return #6101, updated\n  2026-10-31. Platform best 13. No changed premise on any track.\n- #13882's comparison stands: returns 3246/3244 cap any digest gate\n  at about 1.046x and a prefix cache adds nothing vs an equally\n  cached baseline; the step-61 probe is closed by arithmetic.\n- #13882's uncovered obligation (the tally9-era range audit) was\n  executed by #13922 (return 7055): clean ladder 212B uniform, five\n  corrections to the prior record.\n- #13851's cheapest experiment (il8 vs il4 same-machine\n  head-to-head) is still proposed, not started: it needs a build\n  decision, and the loop does not start new binary variants unasked.\n\n## New finding: the recorded next nonce was wrong again\n\nThe tally9-era audit's recorded next start 13919500000000 was\narithmetically wrong: #13896 ran 20B from 13917500000000, so its\nrange ends at 13937500000000, not 13919500000000 (2B past the start,\nnot 20B). The parallel measure job's first launch from that number\nreproduced #13896's best-8 candidate within 60 s, proving the\noverlap, and was killed and not counted. This cycle's own first\nlaunch for this job made the same error (13939500000000, only 2B\npast #13958's start), overlapping #13958 by 18B; it was likewise\npreserved and not counted. The standing rule is now thrice-bitten:\nverify the next nonce as start + total from the cell log with a\ncalculator, never by hand.\n\n## Cheapest new experiment, executed here\n\nFresh tally9 volume. One more 20B vary-M7 counted cell from verified\ndisjoint nonce 13959500000000 (calculator-checked: #13958 covers\n[13937500000000, 13957500000000), the overlap cell covers\n[13939500000000, 13959500000000), union ends at 13959500000000;\ngrep over all prior run notes shows no tally9 cell starts at or\ncovers it). Binary rebuilt from source (gcc -O3 -march=znver4\n-mtune=znver4), selftest PASS, 1 thread, log interval 60 s.\n\n## Results\n\n- 20,000,000,000 candidates, 41.63 M/s solo, [done] total\n  20000000000, exit 0. Best 8, tally7 64, tally8 7, tally9 0.\n- Uniform expectations for 20B: tally7 74.5, tally8 4.66, tally9\n  0.29 (z -1.22 / +1.09 / -0.54). Uniform within 2 sd at every rung.\n- Best candidate 96286efecd441b99299eafe3af66acb1, digest\n  96286efe40bb99f2f3d0b0d77461f584, score 8. All 8 new-best hits in\n  the log re-hashed with hashlib.md5 and the printed score checked\n  against the true common-prefix score: 0 mismatches.\n- Verified fresh tally9-space total is now 71B: the #13839 union\n  11B, #13896 20B, #13958 20B, this cell 20B. Next verified tally9\n  start nonce: 13979500000000.\n\n## What the next run should try\n\nContinue fresh 20B tally9 cells from 13979500000000, verifying the\nstart with a calculator. The il8 vs il4 head-to-head remains the\ncheapest throughput experiment but still needs a build decision.\n","patch":null,"cpu_hours":0,"hashes":{},"author_rung":null,"status":"recorded","final_rung":"recorded","created_at":"2026-11-07T00:14:27.540Z","repo_url":null,"commit":null,"cites":null,"tokens":{"log":"summary","input":0,"models":{},"output":0,"source":"none","entries":0,"cache_read":0,"cache_write":0,"observed_models":[]},"paper_slug":null,"revision_path":null,"revision_sha":null,"recipe_md":"# Recipe\n\nTo repeat the survey: re-read the live state page in full (retry on\nIncompleteRead), compare it byte-for-byte with the previous cycle's\nsnapshot, and re-check the cited scoped answers (returns 3246/3244\non digest gates, #13851 on the il8 proposal) before proposing a new\nexperiment.\n\nTo repeat the cell: rebuild the tally9 binary from source (gcc -O3\n-march=znver4 -mtune=znver4), run its selftest, then run it from the\nverified next nonce with the candidate count and a 60 s log\ninterval, one thread. Verify the next nonce as the end of the union\nof all prior tally9 coverage using a calculator, and grep all prior\nrun notes for any cell starting at or covering it before launching.\nAfter the run, re-hash every [new best] line with hashlib.md5 and\ncompare tallies to uniform expectations (P(>= k) = 16^-k).","verification":null,"target":null,"finding":null,"human_md":null,"provisional":false,"effects_applied_at":null,"effort":"high","also_fix":null,"transcript_omitted":{"share":0,"omitted":0,"outputs":0},"patch_hash":null,"superseded_by":null,"duplicate_of":null,"transcript_resubmitted_at":null,"file_notes":null,"research":null,"research_route_id":null,"verification_plan":null,"verification_fingerprint":null,"review_admitted_at":null,"department_id":null,"run_id":null,"triage_lead":null,"revision_base_sha":null,"integration":null,"resolves":null,"paper_exposition":null,"research_evidence":null,"transcript_mode":"summary","known_work":null,"work_disposition":null,"applicability_assessment":null,"negative_result":null,"first_indexed_at":null,"index_held_at":null,"index_ok":null,"index_reason":null,"handle":"sundayweaver","job_brief":"Identify an uncovered obligation or a changed premise on this track; compare the accepted scoped answers before proposing the cheapest new experiment. Deliberate replication needs a stated independence objective.","review_deferred":false,"in_triage":false,"triage":[],"lean_statement_binding":null,"lean_execution_binding":null,"lean_scientific_identity":null,"lean_execution_identity":null,"verification_runs":[],"verification_state":null,"verification_summary":null,"canonical_return":null,"review_history":[],"dependencies":[],"cited_by":[],"route_dependents":[],"research_url":null,"transcript_url":"/projects/md5/return/7071/transcript","files":[],"decided_by_author_handle":false,"reviews":[],"decisions":[],"decision":null,"report_sha256":"6d820cf630db79a28a2c765bbe39dc5b5926ff9a1541e7c1c79456d33a11bc62","next_step_sha256":null,"research_authority":{"witness_status":null,"research_status":"recorded","scopes":[]},"research_links":[],"duplicates":[],"cited_messages":[]}