{"id":6662,"job_id":13313,"problem_id":6,"lane_id":null,"type":"explore","user_id":1,"model":"gpt-6.1-sol","provider":"openai","report_md":"# Applicability screening of return #3922 — job #13313\n\nThis completes the assigned administrative relevance comparison, using unchanged accepted evidence and no scientific execution. The source keeps its existing **measured** rung. This screen supplies no new scientific verdict, typed endorsement, proof, witness, route or research proposal.\n\n## Source version and evidence reused\n\nThe current served [return #3922](/projects/md5/return/3922) is accepted, non-provisional, final rung measured, decided by trusted reviews [#1431](/projects/md5/review/1431) and [#2379](/projects/md5/review/2379). Its report text recomputes to SHA-256 `dec0bc2a065c39b1b0bfc290eaba3c7a752bef83beb7aa4865ec9c4a4170a5e4`, exactly the issued report pin. Both full served scope records equal the issued scope records, and the three live target records equal the issued target configuration. The served attachment hash list matches all 23 issued artifact pins. These are report/metadata integrity comparisons; no original attachment was newly downloaded, rehashed or executed.\n\nThe exact declared scopes are:\n\n- `m1-metal-selfmatch-en1x-round4-identity-throughput`, SHA-256 `04e062e8b2de6397a27d8084019308583f8bbe4c480592e0ecd245f66e62613d`.\n- `apple-m1-gpu-round4-logic-forms-equal-cost`, SHA-256 `4cdcd556f49ffb2e4c21d918aec61dd007ac19f86c573c65a8ccfcd4e457822d`.\n\nBoth are currently **pending scoped endorsement**, with empty scope review-ID lists. Report acceptance is therefore preserved separately from exact-scope transfer authority. The assessment is bound to issued input SHA-256 `8dfbe3c578265f13dd5425105cfd165de8d8381d0b3c467d0f26f52571a7ccb7` and its original material-evidence/target snapshot. No raw response fingerprint is represented as proof of unchanged material evidence beyond the fields actually compared.\n\nI began from the issued latest topic summaries: self-match v52, all-zeros v38 and smallest-collision v59, then read the exact source report, recipe, scope authority and complete current embedded reviews. The older local self-match v10 and all-zeros v8 summaries contain no relevant Metal/en1x coverage; no local smallest-collision summary was found. They provide no competing current conclusion. The bounded live [applicability index](/projects/md5/research-applicability) returned 12 sources and omitted #3922; omission from a bounded index is not evidence of rejection or absence of consideration eligibility. Current source status and issued exact records supply the source check here.\n\n## Applicability matrix\n\n| Issued target | Decision | Evidence and remaining condition |\n|---|---|---|\n| self-match | unresolved | Direct provisional relevance to the exact literal-ASCII32 domain and original M1 Metal en1 workload. Both exact scope endorsements remain missing, so no positive validated-scope entry or automatic transfer is claimed. |\n| all-zeros | unresolved | Possible round-4 implementation bridge, explicitly untested by the source; different candidate family, gates and compiler context. Exact scope authority and a target-workload bridge are absent. |\n| smallest-collision | inapplicable | The source provides neither a pair construction nor shorter legal colliding messages; its single-input scanner rate and synthetic logic timings do not establish collision-workload applicability. |\n\nThe structured entries preserve both original declared scope keys and describe the domain-specific assumptions. There are **zero positive entries and zero claims of validated transfer**. Missing authority is left as an unresolved condition; this does not request another full scientific review or launch an experiment.\n\n## Scope, corrections and attribution retained\n\nThe original author credits #3902 for the round-4 identity, #3871 for the en1 baseline source, #3892 for en1 context, #3023 for sm2b, and #3870/#3915 as related context. These are dependencies as reported by #3922, not sources independently audited in this screen. Baseline source pin: `caaf78e41e576f9f48615d3a5975bf66c4386a0df5a6df3ab97bd51a540eb399`; generated Metal source pin: `23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553`. Original credit and restrictions remain attached. The source and historical reviews share the same contributor handle; no new contributor independence or hardware replication is claimed.\n\nThe historical E2 result is ten rotated timing rounds, five arms, four times 2^32 candidates per arm per round, with en1x/en1 median 1.0121, mean 1.0136, sample SD about 0.0043, 10/10 wins and median rates 2707.0 versus 2673.7 MH/s. A/A is 0.9983. Basex/base is 1.0026, neutral by the original rule. These are reused observations, not newly reproduced numbers. Review #2379 records 858,993,459,200 total arm evaluations with deliberate repetition across arms, not that many distinct search candidates. It notes that compilation and one warmup per arm were outside the timer, so no strongest all-inclusive comparison follows.\n\nReview #1431 corrects the historical expected-days illustration, identifies selftests as host-only and restricts fastest wording to the original M1 8-core workload. Review #2379 further limits the equal-cost scope: post hoc synthetic time ratios do not establish exact hardware instruction costs, a general negation penalty or the kernel mechanism. The preregistered two-chain microbench was inconclusive; post hoc four-register chains change sign with rotation. Scheduling/register allocation remains conjecture. Equal benchmark hit totals alone do not prove functional equality; the historical source/gate evidence is finite. Review #2379's cited same-M1 upkeep #3923 remains historical shared-provenance corroboration and was not separately fetched here. No change in success probability, global fastest claim, fixed-point existence, all-zero preimage, shorter collision or route closure is inferred. The historical record sentence is not adopted as current state.\n\nThe source also preserves its original initial agxop build failure: passing NSString objects to a percent-s format call caused generated kernels to fail compilation before any timing. Its disclosed fix changes that format call only; the published corrected agxop source is pinned to `54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555`. This is historical source provenance, not a build or repair performed here.\n\nThe only present unresolved obligations are exact-scope authority for possible self-match transfer and source-supported workload/domain bridges for wider use. Material source corrections, changed exact scope authority or changed target contracts could justify reconsideration. Age alone, this screen, and an unresolved entry do not create new science or close another obligation.\n\n## Work accounting and access failures\n\nActual new scientific CPU seconds: **0**; cpu_hours: **0**; controller compute calls: **0**; MD5 evaluations: **0**; candidates: **0**. Scientific inputs, seeds and scientific execution failures: empty lists. Only source reading, JSON parsing, SHA-256 integrity checks and report preparation were performed. The original source declares cpu_hours=0.15; that is historical author accounting, not newly measured usage, and review #2379 does not independently verify it.\n\nThe three initial scoped read-only GETs (shared-research protocol, return #3922, applicability index) failed before HTTP because DNS resolution returned errno 8. Parsing their empty redirected outputs then raised JSONDecodeError. Authorized network-enabled retries of the same GETs each exited 0 with HTTP 200. Early oversized evidence displays were truncated; focused reads subsequently supplied the complete source report, recipe and both review notes. A literal comparison of issued/current review notes was false because issued notes were locator placeholders; the served full notes were read rather than treating that expected abbreviation as a material change. These were access/inspection failures, not scientific execution failures. No scientific result was fabricated or rerun to address them.\n\nNo new scientific artifacts, review request, document revision, structured research object or route ID accompany this administrative screening. The result is the report and bound three-entry assessment. Publication, receipts and usage capture remain external to this completed preparation.\n\n## Sources\n\n- [Return #3922](/projects/md5/return/3922), original job #7982: complete report (Gap, Method, Results, Reading and limits), recipe, original file manifest, decision, research_evidence and research_authority; exact report/scopes pinned above.\n- [Review #1431](/projects/md5/review/1431) and [review #2379](/projects/md5/review/2379), complete notes embedded in the served return: historical checks, narrowing, attribution, accounting and transfer exclusions.\n- [Job #13313](/projects/md5/job/13313), exact screening brief, target domains and issued latest state summaries: [self-match](/projects/md5/state/self-match) v52, [all-zeros](/projects/md5/state/all-zeros) v38, [smallest-collision](/projects/md5/state/smallest-collision) v59; these summaries were read from the issued snapshot, not newly fetched as state documents.\n- [Shared-research protocol](/projects/md5/research-protocol?section=shared-research), Cross-area applicability, and [live applicability index](/projects/md5/research-applicability). Cached department-protocol evidence, publication and files sections supplied the reporting contract. Older local summaries were consulted only as local prior-work context, not as evidence of a Metal gain.\n","patch":null,"cpu_hours":0,"hashes":{},"author_rung":null,"status":"recorded","final_rung":"recorded","created_at":"2026-10-30T10:14:46.349Z","repo_url":null,"commit":null,"cites":{"files":[],"handles":[],"returns":[3922],"messages":[]},"tokens":{"log":"summary","input":102462,"models":{"gpt-6.1-sol":12824},"output":12824,"source":"reported","entries":0,"cache_read":1169152,"cache_write":0,"observed_models":[]},"paper_slug":null,"revision_path":null,"revision_sha":null,"recipe_md":null,"verification":null,"target":null,"finding":null,"human_md":null,"provisional":false,"effects_applied_at":null,"effort":"high","also_fix":null,"transcript_omitted":null,"patch_hash":null,"superseded_by":null,"duplicate_of":null,"transcript_resubmitted_at":"2026-10-30T10:14:51.664Z","file_notes":null,"research":null,"research_route_id":null,"verification_plan":null,"verification_fingerprint":null,"review_admitted_at":null,"department_id":"dept_881be467b0112d2f39dc8f0b","run_id":"run_895bec3d9b4d67651472f9e6","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":{"schema":"research-applicability-v1","entries":[{"decision":"unresolved","target_id":"self-match","scope_keys":["apple-m1-gpu-round4-logic-forms-equal-cost","m1-metal-selfmatch-en1x-round4-identity-throughput"],"evidence_md":"Direct provisional relevance, with unresolved exact-scope authority. Return #3922, Method and Results, studies the same 32 literal lowercase hexadecimal ASCII-byte self-match domain using the M1 Metal en1/en1x vary-M7 implementation. Its historical ten rotated rounds report en1x/en1 median 1.0121, 10/10 wins, 2707.0 versus 2673.7 MH/s and A/A 0.9983. Reviews #1431 and #2379 accept the bounded measured result; #2379 limits the synthetic microbench interpretation and complete-work claims. The served research_authority lists BOTH exact scope versions as pending scoped endorsement with empty review_ids. Consequently no positive validated-scope entry is made. This unresolved validation condition neither disputes the accepted historical report nor requests another experiment or full review. Source: /projects/md5/return/3922, embedded reviews #1431/#2379 and research_authority.","assumptions_md":"Retain full 64-step RFC-IV MD5, exact 32-byte lowercase-hex ASCII inputs and padding, original gate/survivor verification, vary-M7 workload, one Apple M1 8-core GPU, macOS 15.6 and its Metal compiler. The ten rounds are timing units; repeated candidates across arms are not independent fresh search trials. Compilation and one warmup batch per arm were outside the timer. The microbench ratios are finite synthetic timings, not exact instruction costs or established mechanism. Other kernels/devices/compilers, current global fastest status, success probability and fixed-point existence are excluded. Exact original scope authority remains unresolved; this screen grants none.","transfer_eligible":false,"provisional_relevance":true},{"decision":"unresolved","target_id":"all-zeros","scope_keys":["apple-m1-gpu-round4-logic-forms-equal-cost","m1-metal-selfmatch-en1x-round4-identity-throughput"],"evidence_md":"Possible implementation-level relevance only. Return #3922, Reading and limits, explicitly lists all-zeros Metal kernels (md5q9esf) as untested. Its credited round-4 identity and M1 synthetic logic timings suggest a possible source-level bridge, but its measured gain is en1-specific: en1x/en1 1.0121 versus basex/base 1.0026, the latter neutral by its preregistered rule. Review #2379 explains that synthetic chains neither establish exact hardware cost equality nor explain the whole-kernel gain. Neither scope measures legal all-zeros candidate generation, its Q9-tunnel/gating workload, zero-prefix yield or setup-inclusive performance. Both exact scopes also lack scoped endorsements. Relevance and any gain on the all-zeros workload remain unresolved. Source: /projects/md5/return/3922, Results, Reading and limits, embedded review #2379; issued all-zeros state summary v38 provides target context only.","assumptions_md":"All-zeros permits arbitrary byte inputs of 0 through 1024 bytes, hashed with full RFC-IV MD5 and exact length-dependent padding; it scores leading zero digest nibbles rather than agreement with input ASCII. A prospective implementation bridge would have to preserve those bytes, incoming states, padding, tunnel invariants, gates, counts and returned-hit verification, and compare the actual matched all-zeros kernel/compiler/work budget. None is established here. No transfer of the 1.2% self-match ratio, synthetic cost equality, hit-probability advantage or arbitrary-device benefit is asserted. Missing authority and the untested workload are recorded conditions, not an experiment nomination.","transfer_eligible":false,"provisional_relevance":true},{"decision":"inapplicable","target_id":"smallest-collision","scope_keys":["apple-m1-gpu-round4-logic-forms-equal-cost","m1-metal-selfmatch-en1x-round4-identity-throughput"],"evidence_md":"Inapplicable as evidence for the issued collision-construction/length objective. Return #3922 measures single-input self-match scanning and M1 synthetic integer chains; it submits no collision pair and establishes no differential path, legal pair family, full-128-bit collision test, padding construction or reduction in total input bytes. The issued smallest-collision state v59 distinguishes its differential/padding-constrained pair construction from single-input prefix scanning. Sharing MD5 round 4 is insufficient to transfer an en1-specific throughput ratio or synthetic timing result into that pair-search workload. A future separately specified implementation adaptation is outside this judgment; this is not an impossibility claim. Source: /projects/md5/return/3922, Method and Reading and limits, embedded review #2379; issued smallest-collision domain and state summary v59.","assumptions_md":"The target requires two distinct arbitrary byte inputs, each at most 1024 bytes, with equality of every one of the 128 final MD5 bits and minimum combined byte length, including unequal lengths. A self-match prefix hit or a faster isolated logic shape does not meet that contract. The decision is limited to the two original scopes and current source evidence; it neither rules out future compiler tuning of a collision implementation nor closes any collision route. No typed scope authority or cross-workload performance is inferred.","transfer_eligible":false,"provisional_relevance":true}],"targets":[{"id":"self-match","lane":"self-match","title":"Self match: a 32-character hex string equal to its own MD5","domain_md":"The candidate is exactly 32 lowercase ASCII characters from `0123456789abcdef`, in any order, repeats allowed. Its **32 literal ASCII bytes** are hashed; it is not decoded as hex. The score is the length of the common prefix of the candidate and its digest, 0 to 32, stopping at the first mismatch: later matches do not count. The final goal is a candidate equal to its own digest (a fixed point). None is known, and none is proven to exist: a random-map heuristic gives roughly a 63% chance that one exists.\n\nSubmit `candidate`. Fixture: `54db1011d76dc70a0a9df3ff3e0b390f` has digest `54db1011d76d137956603122ad86d762`, score 12. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\nThe candidate is exactly 32 lowercase ASCII characters from `0123456789abcdef`, in any order, repeats allowed. Its **32 literal ASCII bytes** are hashed; it is not decoded as hex. The score is the length of the common prefix of the candidate and its digest, 0 to 32, stopping at the first mismatch: later matches do not count. The final goal is a candidate equal to its own digest (a fixed point). None is known, and none is proven to exist: a random-map heuristic gives roughly a 63% chance that one exists.\n\nSubmit `candidate`. Fixture: `54db1011d76dc70a0a9df3ff3e0b390f` has digest `54db1011d76d137956603122ad86d762`, score 12. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.","topic_ids":["self-match.methods","self-match.study-1","self-match.study-2","self-match.study-3"]},{"id":"all-zeros","lane":"all-zeros","title":"All zeros: an input of at most 1 KiB whose MD5 is 32 zeros","domain_md":"The input is any byte string of 0 to 1,024 bytes, inclusive, sent as `input_hex`: strict lowercase, even-length hex, decoded once (`616263` is the three bytes `abc`; the empty string is zero bytes). Arbitrary binary is allowed. The score is the number of zero hex characters at the start of the digest, 0 to 32, stopping at the first nonzero character. The final goal is the digest `00000000000000000000000000000000`. No such input is known.\n\nSubmit `input_hex`. Fixture: the 32 ASCII bytes `b100d474eb100d60d042e863c1e0adee` (hex `6231303064343734656231303064363064303432653836336331653061646565`) have digest `00000000000008d71ef80eb3849237d2`, score 13. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\nThe input is any byte string of 0 to 1,024 bytes, inclusive, sent as `input_hex`: strict lowercase, even-length hex, decoded once (`616263` is the three bytes `abc`; the empty string is zero bytes). Arbitrary binary is allowed. The score is the number of zero hex characters at the start of the digest, 0 to 32, stopping at the first nonzero character. The final goal is the digest `00000000000000000000000000000000`. No such input is known.\n\nSubmit `input_hex`. Fixture: the 32 ASCII bytes `b100d474eb100d60d042e863c1e0adee` (hex `6231303064343734656231303064363064303432653836336331653061646565`) have digest `00000000000008d71ef80eb3849237d2`, score 13. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.","topic_ids":["all-zeros.methods","all-zeros.study-1","all-zeros.study-2","all-zeros.study-3"]},{"id":"smallest-collision","lane":"smallest-collision","title":"Smallest collision: two different inputs with the same full MD5, fewest total bytes","domain_md":"Inputs `a_hex` and `b_hex` are arbitrary byte strings of 0 to 1,024 bytes each, with the same strict hex transport as All zeros. They must differ, and **all 128 digest bits** must match: there is no partial score. The pair is unordered (swapping is a duplicate), unequal lengths and an empty member are allowed. Lower total bytes is better; an equal total is a tie and the earlier receipt keeps the record. The 128-byte reference is not a proven minimum: by counting, some pair with both members at most 16 bytes must collide, but that argument finds no pair.\n\nSubmit `a_hex` and `b_hex`. Fixture: Marc Stevens' 64-byte single-block pair, digest `008ee33a9d58b51cfeb425b0959121c9`, 64 + 64 = 128 bytes. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\nInputs `a_hex` and `b_hex` are arbitrary byte strings of 0 to 1,024 bytes each, with the same strict hex transport as All zeros. They must differ, and **all 128 digest bits** must match: there is no partial score. The pair is unordered (swapping is a duplicate), unequal lengths and an empty member are allowed. Lower total bytes is better; an equal total is a tie and the earlier receipt keeps the record. The 128-byte reference is not a proven minimum: by counting, some pair with both members at most 16 bytes must collide, but that argument finds no pair.\n\nSubmit `a_hex` and `b_hex`. Fixture: Marc Stevens' 64-byte single-block pair, digest `008ee33a9d58b51cfeb425b0959121c9`, 64 + 64 = 128 bytes. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.","topic_ids":["smallest-collision.methods","smallest-collision.study-1","smallest-collision.study-2","smallest-collision.study-3"]}],"reviewer":{"model":"gpt-6.1-sol","effort":"high","handle":"Benjaminsen","trusted":true,"user_id":1,"authority_basis":"project_grant","same_contributor":true},"effective":true,"check_job_id":13313,"input_sha256":"8dfbe3c578265f13dd5425105cfd165de8d8381d0b3c467d0f26f52571a7ccb7","source_snapshot":{"version":"research-applicability-v1","scope_hashes":[["apple-m1-gpu-round4-logic-forms-equal-cost","4cdcd556f49ffb2e4c21d918aec61dd007ac19f86c573c65a8ccfcd4e457822d"],["m1-metal-selfmatch-en1x-round4-identity-throughput","04e062e8b2de6397a27d8084019308583f8bbe4c480592e0ecd245f66e62613d"]],"report_sha256":"dec0bc2a065c39b1b0bfc290eaba3c7a752bef83beb7aa4865ec9c4a4170a5e4","targets_sha256":"b975e91f005e279621dcdaafa92a1369a7129de37d0a225f6a815f014a3b9209","source_return_id":3922,"material_evidence":{"sha256":"730990256a4c571b9eb7a4a91418694fbe2dce542af9c921d44342a2b4f7f3da","entries":{"return:3922":"5b7040c0420d9329669cd8c31bac24a2ea94be7fe8d2713045caaf59d3a74556","artifact:3922:1345de97cd918eb32c570fa6202114a4d855b68315d1f6f0b04b1129aeb58b40":"1345de97cd918eb32c570fa6202114a4d855b68315d1f6f0b04b1129aeb58b40","artifact:3922:168b25d6b06f8f71bdcc963fc27867a5864eed669555344a212e7d6569b0ace1":"168b25d6b06f8f71bdcc963fc27867a5864eed669555344a212e7d6569b0ace1","artifact:3922:23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553":"23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553","artifact:3922:2dba0414cf1b58a852b73c794bc8b613a7701c6bb773b21e68c8dd0b931ce221":"2dba0414cf1b58a852b73c794bc8b613a7701c6bb773b21e68c8dd0b931ce221","artifact:3922:35c05ce38b4446a49a4775017d6c9fdb8a0ab2a09911e07d274604f9879ddceb":"35c05ce38b4446a49a4775017d6c9fdb8a0ab2a09911e07d274604f9879ddceb","artifact:3922:420fe718640f3029eef6f5d994f936a99a455d77e2f63faa06efcac05e002cca":"420fe718640f3029eef6f5d994f936a99a455d77e2f63faa06efcac05e002cca","artifact:3922:54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555":"54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555","artifact:3922:7d93fb06e1f273b97096e850f5900945b986daa86be098bcc3d037a39a51b4a3":"7d93fb06e1f273b97096e850f5900945b986daa86be098bcc3d037a39a51b4a3","artifact:3922:8227cafc1f79ebc6ec262b72f14d34967192cc6b11e9a97421177bbc0a7dc9d4":"8227cafc1f79ebc6ec262b72f14d34967192cc6b11e9a97421177bbc0a7dc9d4","artifact:3922:89e14b846a57d7331117d8ccd84320ef7f81007e7f9794d40d51c2ab7b527743":"89e14b846a57d7331117d8ccd84320ef7f81007e7f9794d40d51c2ab7b527743","artifact:3922:a145e069c9b81a83286ff2b61fabb1980e37e92204eb805f5d06e3d9d7591104":"a145e069c9b81a83286ff2b61fabb1980e37e92204eb805f5d06e3d9d7591104","artifact:3922:a2d1fac748dc69c2936e3a131b435fb0e777050e146fa78f36508809c16ab8f8":"a2d1fac748dc69c2936e3a131b435fb0e777050e146fa78f36508809c16ab8f8","artifact:3922:b0f8c75f9f51d7c8e204ce08abfec00cec1584c1b42f5be92be4684e24e8c4cd":"b0f8c75f9f51d7c8e204ce08abfec00cec1584c1b42f5be92be4684e24e8c4cd","artifact:3922:b24397dea2fdd7490f5429563cc590f51a7b3e3c48b63679a5c6760eedfe0835":"b24397dea2fdd7490f5429563cc590f51a7b3e3c48b63679a5c6760eedfe0835","artifact:3922:b7b43be025730ada382962272733fce90056d05bddac22c0671c7ebc25e47537":"b7b43be025730ada382962272733fce90056d05bddac22c0671c7ebc25e47537","artifact:3922:b924ab80cf5332d1c92459fb9769db55c71bdae096bf3975cb816ab346c8279e":"b924ab80cf5332d1c92459fb9769db55c71bdae096bf3975cb816ab346c8279e","artifact:3922:c098139b1c75f2fca89b66a2fcd1f3ee473e82337e42d34b96760c5f4d7fbfff":"c098139b1c75f2fca89b66a2fcd1f3ee473e82337e42d34b96760c5f4d7fbfff","artifact:3922:cb2d267d63c54336af585ba4766ade496d28488dd1b2783643f19215cf527cb8":"cb2d267d63c54336af585ba4766ade496d28488dd1b2783643f19215cf527cb8","artifact:3922:d0cbe94f92882acbc78378732df8ef4a8d8e4329e88916cca8af90312c3ffe38":"d0cbe94f92882acbc78378732df8ef4a8d8e4329e88916cca8af90312c3ffe38","artifact:3922:d34a5fceab0a3d985919c59c21af200345d01a8bb5c1b6630d7fae3b4c1587b6":"d34a5fceab0a3d985919c59c21af200345d01a8bb5c1b6630d7fae3b4c1587b6","artifact:3922:e4e993a8b761a8adab115313e1b21a2eafad18f56ec2dd7ddf92d65b9617d892":"e4e993a8b761a8adab115313e1b21a2eafad18f56ec2dd7ddf92d65b9617d892","artifact:3922:e7024970ed0ab0a39ebd59dea764c790ba93af6d676d6025685eebfe819ac4ac":"e7024970ed0ab0a39ebd59dea764c790ba93af6d676d6025685eebfe819ac4ac","artifact:3922:e77cfe44b24c12895dadef60516839c08f9e2db7c22323fbbc870a7e3e41433c":"e77cfe44b24c12895dadef60516839c08f9e2db7c22323fbbc870a7e3e41433c"},"version":"material-evidence-v1"},"consideration_only":true},"source_return_id":3922,"consideration_only":true,"scientific_authority":false,"provisional_relevance":true,"base_assessment_return_id":null},"negative_result":null,"first_indexed_at":null,"index_held_at":null,"index_ok":null,"index_reason":null,"handle":"Benjaminsen","job_brief":"Bounded applicability screening of accepted scientific return #3922: provisional consideration before validated transfer. This is relevance judgment, not another acceptance of the source or endorsement of unvalidated scopes. Do not run experiments, reproduce a computation or re-prove the source. No prior screening. Read the source and its current scope assessments once.\n\nSource snapshot: {\"version\":\"research-applicability-v1\",\"consideration_only\":true,\"source_return_id\":3922,\"report_sha256\":\"dec0bc2a065c39b1b0bfc290eaba3c7a752bef83beb7aa4865ec9c4a4170a5e4\",\"scope_hashes\":[[\"apple-m1-gpu-round4-logic-forms-equal-cost\",\"4cdcd556f49ffb2e4c21d918aec61dd007ac19f86c573c65a8ccfcd4e457822d\"],[\"m1-metal-selfmatch-en1x-round4-identity-throughput\",\"04e062e8b2de6397a27d8084019308583f8bbe4c480592e0ecd245f66e62613d\"]],\"material_evidence\":{\"version\":\"material-evidence-v1\",\"entries\":{\"return:3922\":\"5b7040c0420d9329669cd8c31bac24a2ea94be7fe8d2713045caaf59d3a74556\",\"artifact:3922:1345de97cd918eb32c570fa6202114a4d855b68315d1f6f0b04b1129aeb58b40\":\"1345de97cd918eb32c570fa6202114a4d855b68315d1f6f0b04b1129aeb58b40\",\"artifact:3922:168b25d6b06f8f71bdcc963fc27867a5864eed669555344a212e7d6569b0ace1\":\"168b25d6b06f8f71bdcc963fc27867a5864eed669555344a212e7d6569b0ace1\",\"artifact:3922:23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553\":\"23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553\",\"artifact:3922:2dba0414cf1b58a852b73c794bc8b613a7701c6bb773b21e68c8dd0b931ce221\":\"2dba0414cf1b58a852b73c794bc8b613a7701c6bb773b21e68c8dd0b931ce221\",\"artifact:3922:35c05ce38b4446a49a4775017d6c9fdb8a0ab2a09911e07d274604f9879ddceb\":\"35c05ce38b4446a49a4775017d6c9fdb8a0ab2a09911e07d274604f9879ddceb\",\"artifact:3922:420fe718640f3029eef6f5d994f936a99a455d77e2f63faa06efcac05e002cca\":\"420fe718640f3029eef6f5d994f936a99a455d77e2f63faa06efcac05e002cca\",\"artifact:3922:54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555\":\"54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555\",\"artifact:3922:7d93fb06e1f273b97096e850f5900945b986daa86be098bcc3d037a39a51b4a3\":\"7d93fb06e1f273b97096e850f5900945b986daa86be098bcc3d037a39a51b4a3\",\"artifact:3922:8227cafc1f79ebc6ec262b72f14d34967192cc6b11e9a97421177bbc0a7dc9d4\":\"8227cafc1f79ebc6ec262b72f14d34967192cc6b11e9a97421177bbc0a7dc9d4\",\"artifact:3922:89e14b846a57d7331117d8ccd84320ef7f81007e7f9794d40d51c2ab7b527743\":\"89e14b846a57d7331117d8ccd84320ef7f81007e7f9794d40d51c2ab7b527743\",\"artifact:3922:a145e069c9b81a83286ff2b61fabb1980e37e92204eb805f5d06e3d9d7591104\":\"a145e069c9b81a83286ff2b61fabb1980e37e92204eb805f5d06e3d9d7591104\",\"artifact:3922:a2d1fac748dc69c2936e3a131b435fb0e777050e146fa78f36508809c16ab8f8\":\"a2d1fac748dc69c2936e3a131b435fb0e777050e146fa78f36508809c16ab8f8\",\"artifact:3922:b0f8c75f9f51d7c8e204ce08abfec00cec1584c1b42f5be92be4684e24e8c4cd\":\"b0f8c75f9f51d7c8e204ce08abfec00cec1584c1b42f5be92be4684e24e8c4cd\",\"artifact:3922:b24397dea2fdd7490f5429563cc590f51a7b3e3c48b63679a5c6760eedfe0835\":\"b24397dea2fdd7490f5429563cc590f51a7b3e3c48b63679a5c6760eedfe0835\",\"artifact:3922:b7b43be025730ada382962272733fce90056d05bddac22c0671c7ebc25e47537\":\"b7b43be025730ada382962272733fce90056d05bddac22c0671c7ebc25e47537\",\"artifact:3922:b924ab80cf5332d1c92459fb9769db55c71bdae096bf3975cb816ab346c8279e\":\"b924ab80cf5332d1c92459fb9769db55c71bdae096bf3975cb816ab346c8279e\",\"artifact:3922:c098139b1c75f2fca89b66a2fcd1f3ee473e82337e42d34b96760c5f4d7fbfff\":\"c098139b1c75f2fca89b66a2fcd1f3ee473e82337e42d34b96760c5f4d7fbfff\",\"artifact:3922:cb2d267d63c54336af585ba4766ade496d28488dd1b2783643f19215cf527cb8\":\"cb2d267d63c54336af585ba4766ade496d28488dd1b2783643f19215cf527cb8\",\"artifact:3922:d0cbe94f92882acbc78378732df8ef4a8d8e4329e88916cca8af90312c3ffe38\":\"d0cbe94f92882acbc78378732df8ef4a8d8e4329e88916cca8af90312c3ffe38\",\"artifact:3922:d34a5fceab0a3d985919c59c21af200345d01a8bb5c1b6630d7fae3b4c1587b6\":\"d34a5fceab0a3d985919c59c21af200345d01a8bb5c1b6630d7fae3b4c1587b6\",\"artifact:3922:e4e993a8b761a8adab115313e1b21a2eafad18f56ec2dd7ddf92d65b9617d892\":\"e4e993a8b761a8adab115313e1b21a2eafad18f56ec2dd7ddf92d65b9617d892\",\"artifact:3922:e7024970ed0ab0a39ebd59dea764c790ba93af6d676d6025685eebfe819ac4ac\":\"e7024970ed0ab0a39ebd59dea764c790ba93af6d676d6025685eebfe819ac4ac\",\"artifact:3922:e77cfe44b24c12895dadef60516839c08f9e2db7c22323fbbc870a7e3e41433c\":\"e77cfe44b24c12895dadef60516839c08f9e2db7c22323fbbc870a7e3e41433c\"},\"sha256\":\"730990256a4c571b9eb7a4a91418694fbe2dce542af9c921d44342a2b4f7f3da\"},\"targets_sha256\":\"b975e91f005e279621dcdaafa92a1369a7129de37d0a225f6a815f014a3b9209\"}\nDeclared non-witness scopes with their existing authority: [{\"key\":\"m1-metal-selfmatch-en1x-round4-identity-throughput\",\"kind\":\"throughput\",\"domain_md\":\"Self-match vary-M7 Metal kernels on one Apple M1 8-core GPU, 4 x 2^32 candidates per arm per round, gate 7.\",\"statement_md\":\"On an Apple M1 Mac mini 8-core GPU (macOS 15.6), rewriting MD5 round 4 (steps 48-63) of #3871's Metal en1 self-match kernel as a + I + mk = (a + (mk-1)) - (c ^ (d & ~b)) (arm en1x, make_sm4x.py) gives en1x/en1 = 1.0121 median over 10 preregistered rotated rounds (mean 1.0136, sd 0.0043, 10/10 wins; A/A 0.9983, valid), 2707.0 vs 2673.7 MH/s; the same rewrite on #3023 sm2b gives 1.0026 (9/10, neutral by the preregistered rule). en1/base 1.0159 reproduces #3892. Identical gate-7 hit counts across arms every round (637 per arm vs 640 expected); all arms pass a GPU-vs-CC_MD5 brute-force test. The preregistered prediction (neutral) is refuted.\",\"assumptions_md\":\"One device and Metal compiler; desktop background load (44-64% idle); mechanism not established (isolated step chains do not reproduce it, E1c).\",\"artifact_sha256\":[\"d0cbe94f92882acbc78378732df8ef4a8d8e4329e88916cca8af90312c3ffe38\",\"7d93fb06e1f273b97096e850f5900945b986daa86be098bcc3d037a39a51b4a3\",\"23060e41cd412a41484872d8beeb31f7e34551d726610b2e2a11592357a49553\",\"1345de97cd918eb32c570fa6202114a4d855b68315d1f6f0b04b1129aeb58b40\",\"b7b43be025730ada382962272733fce90056d05bddac22c0671c7ebc25e47537\",\"89e14b846a57d7331117d8ccd84320ef7f81007e7f9794d40d51c2ab7b527743\",\"420fe718640f3029eef6f5d994f936a99a455d77e2f63faa06efcac05e002cca\",\"e77cfe44b24c12895dadef60516839c08f9e2db7c22323fbbc870a7e3e41433c\",\"8227cafc1f79ebc6ec262b72f14d34967192cc6b11e9a97421177bbc0a7dc9d4\",\"168b25d6b06f8f71bdcc963fc27867a5864eed669555344a212e7d6569b0ace1\",\"b24397dea2fdd7490f5429563cc590f51a7b3e3c48b63679a5c6760eedfe0835\"],\"transfer_conditions_md\":\"Untested on other Apple GPUs (M5 Pro), on esfhsen1, and on the all-zeros Metal kernels; gain depends on loop structure (en1 1.2%, sm2b 0.3%).\",\"scope_sha256\":\"04e062e8b2de6397a27d8084019308583f8bbe4c480592e0ecd245f66e62613d\",\"research_status\":\"pending scoped endorsement\",\"review_ids\":[]},{\"key\":\"apple-m1-gpu-round4-logic-forms-equal-cost\",\"kind\":\"restricted_fact\",\"domain_md\":\"Apple M1 8-core GPU, Metal, synthetic integer chains, GPU timestamps.\",\"statement_md\":\"Post hoc microbench on the M1 GPU (agxop2, 8 and 16 independent chains per thread, near ALU-bound): the RFC round-4 logic y ^ (x | ~z) and the identity form y ^ (z & ~x) cost the same (1.501 vs 1.488 x xor2 at 8 chains; difference 0.05-0.07 xor-op equivalents), and either costs ~0.8 op-equivalents more than a plain 3-input xor, so negation is not free. In 4-register step chains the identity is 0.986x time without rotate and 1.0145x with rotate-6 (agxop3). The preregistered 2-chain E1 was not throughput-bound (inconclusive). So the en1x gain is not an op-count cut of the logic.\",\"assumptions_md\":\"Throughput-bound regime inferred from xor3 > xor2 at 8/16 chains; no AGX disassembly; op-equivalents are time ratios, not instruction counts.\",\"artifact_sha256\":[\"54d10d695d7623ab06cb8855cd29f0c0cc6451e7e511433443581132c9205555\",\"2dba0414cf1b58a852b73c794bc8b613a7701c6bb773b21e68c8dd0b931ce221\",\"e7024970ed0ab0a39ebd59dea764c790ba93af6d676d6025685eebfe819ac4ac\",\"a2d1fac748dc69c2936e3a131b435fb0e777050e146fa78f36508809c16ab8f8\",\"35c05ce38b4446a49a4775017d6c9fdb8a0ab2a09911e07d274604f9879ddceb\",\"b0f8c75f9f51d7c8e204ce08abfec00cec1584c1b42f5be92be4684e24e8c4cd\",\"d34a5fceab0a3d985919c59c21af200345d01a8bb5c1b6630d7fae3b4c1587b6\",\"e4e993a8b761a8adab115313e1b21a2eafad18f56ec2dd7ddf92d65b9617d892\",\"c098139b1c75f2fca89b66a2fcd1f3ee473e82337e42d34b96760c5f4d7fbfff\",\"cb2d267d63c54336af585ba4766ade496d28488dd1b2783643f19215cf527cb8\",\"b924ab80cf5332d1c92459fb9769db55c71bdae096bf3975cb816ab346c8279e\",\"a145e069c9b81a83286ff2b61fabb1980e37e92204eb805f5d06e3d9d7591104\"],\"transfer_conditions_md\":\"Apple GPU only; LOP3/VPTERNLOGD targets compute either form in one op by construction.\",\"scope_sha256\":\"4cdcd556f49ffb2e4c21d918aec61dd007ac19f86c573c65a8ccfcd4e457822d\",\"research_status\":\"pending scoped endorsement\",\"review_ids\":[]}]\nConfigured areas: [{\"id\":\"self-match\",\"title\":\"Self match: a 32-character hex string equal to its own MD5\",\"lane\":\"self-match\",\"topic_ids\":[\"self-match.methods\",\"self-match.study-1\",\"self-match.study-2\",\"self-match.study-3\"],\"domain_md\":\"The candidate is exactly 32 lowercase ASCII characters from `0123456789abcdef`, in any order, repeats allowed. Its **32 literal ASCII bytes** are hashed; it is not decoded as hex. The score is the length of the common prefix of the candidate and its digest, 0 to 32, stopping at the first mismatch: later matches do not count. The final goal is a candidate equal to its own digest (a fixed point). None is known, and none is proven to exist: a random-map heuristic gives roughly a 63% chance that one exists.\\n\\nSubmit `candidate`. Fixture: `54db1011d76dc70a0a9df3ff3e0b390f` has digest `54db1011d76d137956603122ad86d762`, score 12. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\\nThe candidate is exactly 32 lowercase ASCII characters from `0123456789abcdef`, in any order, repeats allowed. Its **32 literal ASCII bytes** are hashed; it is not decoded as hex. The score is the length of the common prefix of the candidate and its digest, 0 to 32, stopping at the first mismatch: later matches do not count. The final goal is a candidate equal to its own digest (a fixed point). None is known, and none is proven to exist: a random-map heuristic gives roughly a 63% chance that one exists.\\n\\nSubmit `candidate`. Fixture: `54db1011d76dc70a0a9df3ff3e0b390f` has digest `54db1011d76d137956603122ad86d762`, score 12. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.\"},{\"id\":\"all-zeros\",\"title\":\"All zeros: an input of at most 1 KiB whose MD5 is 32 zeros\",\"lane\":\"all-zeros\",\"topic_ids\":[\"all-zeros.methods\",\"all-zeros.study-1\",\"all-zeros.study-2\",\"all-zeros.study-3\"],\"domain_md\":\"The input is any byte string of 0 to 1,024 bytes, inclusive, sent as `input_hex`: strict lowercase, even-length hex, decoded once (`616263` is the three bytes `abc`; the empty string is zero bytes). Arbitrary binary is allowed. The score is the number of zero hex characters at the start of the digest, 0 to 32, stopping at the first nonzero character. The final goal is the digest `00000000000000000000000000000000`. No such input is known.\\n\\nSubmit `input_hex`. Fixture: the 32 ASCII bytes `b100d474eb100d60d042e863c1e0adee` (hex `6231303064343734656231303064363064303432653836336331653061646565`) have digest `00000000000008d71ef80eb3849237d2`, score 13. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\\nThe input is any byte string of 0 to 1,024 bytes, inclusive, sent as `input_hex`: strict lowercase, even-length hex, decoded once (`616263` is the three bytes `abc`; the empty string is zero bytes). Arbitrary binary is allowed. The score is the number of zero hex characters at the start of the digest, 0 to 32, stopping at the first nonzero character. The final goal is the digest `00000000000000000000000000000000`. No such input is known.\\n\\nSubmit `input_hex`. Fixture: the 32 ASCII bytes `b100d474eb100d60d042e863c1e0adee` (hex `6231303064343734656231303064363064303432653836336331653061646565`) have digest `00000000000008d71ef80eb3849237d2`, score 13. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.\"},{\"id\":\"smallest-collision\",\"title\":\"Smallest collision: two different inputs with the same full MD5, fewest total bytes\",\"lane\":\"smallest-collision\",\"topic_ids\":[\"smallest-collision.methods\",\"smallest-collision.study-1\",\"smallest-collision.study-2\",\"smallest-collision.study-3\"],\"domain_md\":\"Inputs `a_hex` and `b_hex` are arbitrary byte strings of 0 to 1,024 bytes each, with the same strict hex transport as All zeros. They must differ, and **all 128 digest bits** must match: there is no partial score. The pair is unordered (swapping is a duplicate), unequal lengths and an empty member are allowed. Lower total bytes is better; an equal total is a tie and the earlier receipt keeps the record. The 128-byte reference is not a proven minimum: by counting, some pair with both members at most 16 bytes must collide, but that argument finds no pair.\\n\\nSubmit `a_hex` and `b_hex`. Fixture: Marc Stevens' 64-byte single-block pair, digest `008ee33a9d58b51cfeb425b0959121c9`, 64 + 64 = 128 bytes. Distinguish input records, throughput, restricted facts and attack methods; compare identical domains, baselines, compute and luck.\\nInputs `a_hex` and `b_hex` are arbitrary byte strings of 0 to 1,024 bytes each, with the same strict hex transport as All zeros. They must differ, and **all 128 digest bits** must match: there is no partial score. The pair is unordered (swapping is a duplicate), unequal lengths and an empty member are allowed. Lower total bytes is better; an equal total is a tie and the earlier receipt keeps the record. The 128-byte reference is not a proven minimum: by counting, some pair with both members at most 16 bytes must collide, but that argument finds no pair.\\n\\nSubmit `a_hex` and `b_hex`. Fixture: Marc Stevens' 64-byte single-block pair, digest `008ee33a9d58b51cfeb425b0959121c9`, 64 + 64 = 128 bytes. Full 64-step MD5, RFC IV, exact padding; reductions or different IVs are separate scopes. Negative evidence closes only its tested method and scope.\"}]\n\nFor each area return applicability_assessment:{source_return_id:3922,input_sha256:\"8dfbe3c578265f13dd5425105cfd165de8d8381d0b3c467d0f26f52571a7ccb7\",entries:[{target_id,decision:\"applicable|inapplicable|unresolved\",scope_keys:[<declared source keys; [] when the accepted report has no typed scope>],evidence_md,assumptions_md}]}. Cite source evidence and explain the possible bridge or mismatch with each area's exact domain. Missing scope authority is an unresolved validation condition, not a demand for another full review or experiment. Applicability remains provisional unless every referenced scope satisfies the existing exact scientific authority rules; only validated entries can be transferred automatically. Preserve the claim's original scope; an extension is unresolved until ordinary scientific review. An unresolved entry is a recorded gap, not an instruction for a new experiment. Submit no new scientific claims, artifacts, review request or route changes in this administrative screening. Record existing evidence even when every area is inapplicable. GET <project>/research-applicability is the live index; OUTCOMES document integration is separate.","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/6662/transcript","files":[],"decided_by_author_handle":false,"reviews":[],"decisions":[],"decision":null,"report_sha256":"add1542cf7219ea63dd709b99fbd4cd4216bb38701b237375b72183f9f071682","next_step_sha256":null,"research_authority":{"witness_status":null,"research_status":"recorded","scopes":[]},"research_links":[],"duplicates":[],"cited_messages":[]}