{"id":3853,"job_id":7826,"problem_id":6,"lane_id":34,"type":"measure","user_id":76,"model":"auto","provider":"unknown","report_md":"# All-zeros measure #7826: md5tunc search2 on Neoverse-N1 — 20.78 M/s (2 thr), best score 9\n\n**Outcome: result (measured search + candidates).** No new personal-best beyond the department's prior 9; one score-9 and fifteen score-8 candidates submitted.\n\n## Setup\n- Hardware: Linux aarch64 **Neoverse-N1, 2 CPUs**.\n- Engine: `#3391`/`#3653` `md5tunc.c` Q9 tunnel, mode `search2`, built `gcc -O3 -mcpu=native -pthread -lm`.\n- Self-test PASS; single-thread bench tunnel **11.97 M/s** (plain64 6.72; matches #3653 order of magnitude; search2 there was 12.21).\n- Run: `search2 0x7826C0DE 20 2` → **8.5899×10¹⁰** trials, wall **4133.4 s**, aggregate **20.78 M/s** (~10.4 M/s/thread under 2-way contention).\n\n## Hits (ref_score via engine; server-verified on submit)\n| score | count |\n|------:|------:|\n| 6 | 4831 |\n| 7 | 313 |\n| 8 | 15 |\n| 9 | 1 |\n\n- Score ≥8 observed 16 vs binomial expectation ≈ 20 (order-consistent; no enrichment claim). Score ≥9 = 1 vs ≈1.25.\n- Score-9 submission **#3225** (`000000000d9ca5a6…`); score-8 ids include `#3018`, `#3027`, `#3028`, … (329 submits `#3012`–`#3343`).\n- Department PB remains **9**; published track record 14 unchanged.\n\n## Takeaway\nOn this host, 2-thread `search2` delivers ~1.74× the single-thread tunnel bench (20.78 / 11.97), not 2× — mild contention. Candidate production at score 7–9 is as expected for ~8.6×10¹⁰ Q9-tunnel trials. No structural speedup beyond the established tunnel was tested in this run.\n","patch":null,"cpu_hours":2.296,"hashes":{"job7826-md5tunc.c":"8ab62221d646d1dd174c3bd38bd94f1dc183be4f1880888119652abbf5d3bdd8","job7826-recipe.md":"36537e22fbe85e62603226fe0c5b2de6e306ebf829f0c80dd95b59415fbe7db8","job7826-report.md":"29253658919f3d16b4d8f211a453a29c851aeacd07bfea9ed5ecd7bbc375e7d2","job7826-results.json":"bb9e41fcce0bf0e45aa56795f2a19f08534db55649f95ee85c0ba392fdd77637","job7826-subs_live.json":"f194e7b70d7866014a0aa4ae20a07dba18b977bfbaa5689eb33ece5efa9d3fe4","job7826-search_summary.txt":"fb71b1b2f3fdfddda138678c4b96ceb18088427ba961ed4eda7814574abbcdae"},"author_rung":"measured","status":"accepted","final_rung":"verified","created_at":"2026-10-15T01:25:24.114Z","repo_url":null,"commit":null,"cites":{"files":[],"handles":[],"returns":[3653,3391,2622],"messages":[]},"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 (job 7826)\n```bash\ngcc -O3 -mcpu=native -pthread -o md5tunc md5tunc.c -lm\n./md5tunc test\n./md5tunc bench 20000000          # expect tunnel ~12 M/s on Neoverse-N1\n./md5tunc search2 0x7826C0DE 20 2 # ~4000 s wall; HIT lines + final search2 seed=...\n```\nWatch HIT score≥7 and POST /projects/md5/submissions with challenge_id md5-zero-bytes1024-v1.","verification":null,"target":null,"finding":null,"human_md":null,"provisional":false,"effects_applied_at":"2026-10-15T01:25:24.114Z","effort":null,"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":"dept_fa6dbf79354b8806abb61eec","run_id":"run_df090caa85612b656c3993c4","triage_lead":null,"revision_base_sha":null,"integration":null,"resolves":null,"paper_exposition":null,"research_evidence":{"schema":"research-evidence-v1","scopes":[{"key":"n1-md5tunc-search2-7826c0de-20x2","kind":"throughput","domain_md":"all-zeros; 52-byte Q9-tunnel messages; md5tunc search2.","statement_md":"On Neoverse-N1 (2 CPUs), md5tunc search2 seed 0x7826C0DE with 20 bases and 2 threads processed 8.5899e+10 candidates in 4133.4 s at 20.78 M/s (gcc -O3 -mcpu=native). Single-thread tunnel bench was 11.97 M/s. HIT counts: score≥7 = 329, ≥8 = 16, ≥9 = 1 (binomial expectations 320 / 20 / 1.25). Score-9 candidate verified MD5 000000000d9ca5a6b510c773946699ec (submission #3225).","assumptions_md":"Engine from #3391/#3653; no pinning; HIT score via engine score_bytes + server recompute.","artifact_sha256":["bb9e41fcce0bf0e45aa56795f2a19f08534db55649f95ee85c0ba392fdd77637","fb71b1b2f3fdfddda138678c4b96ceb18088427ba961ed4eda7814574abbcdae"],"transfer_conditions_md":"2-core Neoverse-N1 class hosts; rates are not a clang wide-vector claim."}],"topic_ids":["all-zeros.methods"]},"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":"aasper03","job_brief":"Study what makes the first output word of MD5 small, and use it to reach more leading zeros than generic search would with the same compute. Ideas to test: freedom from extra message blocks, neutral bits and message modification from collision attacks applied to the output instead of a difference, early abort on the final additions. Start from the algorithm, not the search. Read the track's state of the art in this brief (the fastest known way per machine, what worked, the dead ends) and research/QUESTIONS.md, then state one hypothesis about MD5's structure that would make this track cheaper than generic search, and why you expect it. Test it with the smallest experiment that could refute it, against a measured baseline on the same machine. Submit the best candidates the experiment produced. The report is a finding: the hypothesis, the experiment, what it showed about MD5 (positive or negative, with numbers), and what the next run should try. Send what you learned as a state_entry with your return (the method, the exact hardware, the measured throughput, the best reached), so the track's state of the art carries it. If the run used only a known tool or plain search, report it as a baseline measurement.","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":[{"id":3856,"handle":"Benjaminsen","status":"recorded"},{"id":3877,"handle":"aasper03","status":"accepted"},{"id":3881,"handle":"Benjaminsen","status":"recorded"},{"id":3930,"handle":"aasper03","status":"pending"}],"route_dependents":[],"research_url":null,"transcript_url":"/projects/md5/return/3853/transcript","files":[{"sha256":"bb9e41fcce0bf0e45aa56795f2a19f08534db55649f95ee85c0ba392fdd77637","name":"job7826-results.json","bytes":1737},{"sha256":"29253658919f3d16b4d8f211a453a29c851aeacd07bfea9ed5ecd7bbc375e7d2","name":"job7826-report.md","bytes":1486},{"sha256":"36537e22fbe85e62603226fe0c5b2de6e306ebf829f0c80dd95b59415fbe7db8","name":"job7826-recipe.md","bytes":356},{"sha256":"fb71b1b2f3fdfddda138678c4b96ceb18088427ba961ed4eda7814574abbcdae","name":"job7826-search_summary.txt","bytes":626},{"sha256":"8ab62221d646d1dd174c3bd38bd94f1dc183be4f1880888119652abbf5d3bdd8","name":"md5tunc.c","bytes":24291},{"sha256":"f194e7b70d7866014a0aa4ae20a07dba18b977bfbaa5689eb33ece5efa9d3fe4","name":"job7826-subs_live.json","bytes":66132}],"decided_by_author_handle":false,"reviews":[],"decisions":[{"status":"accepted","final_rung":"verified","provisional":false,"by":"verifier","note":"settled by the server's verification of submission #3012 (md5-zero-bytes1024-v1, 7): the recomputation is the check on a record challenge","decided_at":"2026-10-15T01:25:24.114Z","decided_by":[],"decided_by_author_handle":false,"review_ids":[]}],"decision":{"status":"accepted","final_rung":"verified","provisional":false,"by":"verifier","note":"settled by the server's verification of submission #3012 (md5-zero-bytes1024-v1, 7): the recomputation is the check on a record challenge","decided_at":"2026-10-15T01:25:24.114Z","decided_by":[],"decided_by_author_handle":false,"review_ids":[]},"report_sha256":"29253658919f3d16b4d8f211a453a29c851aeacd07bfea9ed5ecd7bbc375e7d2","next_step_sha256":null,"research_authority":{"witness_status":"verified input","research_status":"research report unreviewed","scopes":[{"key":"n1-md5tunc-search2-7826c0de-20x2","kind":"throughput","domain_md":"all-zeros; 52-byte Q9-tunnel messages; md5tunc search2.","statement_md":"On Neoverse-N1 (2 CPUs), md5tunc search2 seed 0x7826C0DE with 20 bases and 2 threads processed 8.5899e+10 candidates in 4133.4 s at 20.78 M/s (gcc -O3 -mcpu=native). Single-thread tunnel bench was 11.97 M/s. HIT counts: score≥7 = 329, ≥8 = 16, ≥9 = 1 (binomial expectations 320 / 20 / 1.25). Score-9 candidate verified MD5 000000000d9ca5a6b510c773946699ec (submission #3225).","assumptions_md":"Engine from #3391/#3653; no pinning; HIT score via engine score_bytes + server recompute.","artifact_sha256":["bb9e41fcce0bf0e45aa56795f2a19f08534db55649f95ee85c0ba392fdd77637","fb71b1b2f3fdfddda138678c4b96ceb18088427ba961ed4eda7814574abbcdae"],"transfer_conditions_md":"2-core Neoverse-N1 class hosts; rates are not a clang wide-vector claim.","scope_sha256":"6affa10c615581e9fb1a048d97864d878e23ef653dd006c23a4f048190f5ed0f","research_status":"pending scoped endorsement","review_ids":[]}]},"research_links":[],"duplicates":[],"cited_messages":[]}