{"id":3469,"job_id":7126,"problem_id":1,"lane_id":3,"type":"explore","user_id":1,"model":"deepseek-v4-flash","provider":"deepseek","report_md":"# Route 52 step check (job #7126): the fifth-fold T_41 census is still on no return — the held step stands, unchanged\n\n**Outcome: `promising`.** Reuse #2553's certificate; compare only the new candidate the brief names,\n**#3278** (route 180, progress). **`cpu_hours` 0** — documentary comparison only: no experiment, no\ncensus recomputed, no candidate claim independently validated, inherited grades unchanged.\n\n## What was asked\n\nRoute 52's next experiment was set by #2065 and is still held. Before a pursuit is spent on it, decide\nwhether returns already on record answer it. The step asks for the fifth fold T_37 → T_41: validate all\n88 T_37 classes against #2005's `tc37.json`; then the T_41 class census `N_g(T_41)` (91 classes) with\n`sum_g N_g = D(T_41) = 39*D(T_37)`, `N_6(T_41) = 37*N_6(T_37)`, `G2 = 546` with `N_546 = 4`, nothing\nabove 546; then `C_g = N_g(T_41) - 39*N_g(T_37)`, its negative segment K, `D(12)`, and `rho_g/cop_g`\nat the tracked classes. \"Earlier step check #2553: reuse its conclusions.\"\n\n## Decisive comparison\n\n### 1. The step is byte-identical to the one #2553 certified (nothing changed underneath)\n\nThe served route 52 record is revision 16, `state: active`, `last_return_id: \"2553\"`, 16 events, the\nnewest `2026-10-08T14:08:11.207Z`. Canonical SHA-256 (`sort_keys`, compact separators) of its\n`next_step` is\n\n```\n5d429faa117b2eff83328f2697f2241d0625a940d96956eae7499bd3c7a22c37\n```\n\n— exactly the value #2553 recorded for \"the exact issued next_step equals route52 revision15 and\n#2499's next_step\", and the step issued to this run parses to the same object. So the object under\ncheck is unchanged, and #2553's conclusion can be reused as instructed: *\"No new candidate supplies\nall-88-class T37 COUNT validation, N_g(T41), specified total/endpoint/support identities, C_g/K/D(12),\nor rho_g/cop_g. Thus neither known nor a partially replaced progress step is supported; preserve the\nissued step exactly.\"*\n\n### 2. The new candidate #3278 is a non-carrier\n\n#3278 (route 180, job #5322, 2026-10-12, progress) is the continuation of **#2536's** line — ordinary\nreduced-residue gap moments at wheels 11#..31#: it closes the second-moment merge for `V` and `C_1`,\ncloses the map `T: (rho_1, rho_2, kappa)`, and iterates `A(x) = -rho_1(x#) ln x`, which drifts and\nplateaus near 0.461 rather than 1/2. #2553 already separated exactly this line from the held step:\nits `rho_1` is a moment of ordinary wheel gaps, not route 52's in-between-opener correction\n`rho_g = cop_g - N_g(T_x)`, and its statistics are not twin-tile gap-class counts.\n\nA token census over #3278's full served text (report, evidence, hashes, file names) finds **zero**\noccurrences of any required output identifier: `T_41`, `tc37`, `tc41`, `census4495`, `cop_g`, `rho_g`,\n`C_g`, `D(12)`, `N_g(T_41)`, `N_546`, `39*D(T_37)`. Its declared dependencies\n`[2536, 2396, 2428, 2517, 3260]` are the same route-180 line (#3260 is route 180's own `promising`\nstep check; #2536/#3260 are likewise token-free). It therefore supplies **none** of: the 88-class T_37\nCOUNT calibration, `N_g(T_41)` for the 91 classes, the total/endpoint/support identities, `C_g`, the\nnegative segment K, `D(12)`, or the `rho/cop` trend at T_41.\n\n### 3. The step setter already recorded the decisive fact\n\n#2065 (the setter, job #4607) states it explicitly: *\"No return has a class census at T_41\"* — and\nprices one at about 3 CPU-h for all 91 classes, consistent with the step's own declared compute\n(`cpu_hours` 4). Its pricing check validated **3 of 88** T_37 classes (g = 6, 36, 120), which it labels\n\"enough to price the new step, not to replace the census\". Everything recorded on route 52 after\n#2065 (#2192, #2198, #2203, #2208, #2217, #2280, #2335, #2499, #2553) is a record-comparison step\ncheck that preserved the step; none ran a census.\n\n### 4. The step's own `g = 546` facts are pre-setter and are cross-checks, not the obligation\n\nThe step itself credits `G2 = 546 with N_546 = 4` to **#1791/#2061** (both pre-setter, accepted):\n#1791 certifies the 41# attaining set — four positions in two σ-orbits over one T_19 slot residue and\nits mirror — and #2061's covering census over the same 378,675 T_19 slot residues certifies\n`G2`, `nmax` and every attaining position at 23#..43#. Those returns give the **maximal** class only;\nthe uncovered obligation is the per-class table (`N_g(T_41)` for all 91 classes) and the derived\n`C_g / K / D(12) / rho / cop`. The route's file inventory confirms the asymmetry: `tc37.json` is on\nrecord (via #2005/#4159), no `tc41` artifact is.\n\n## Still required (unchanged; = the issued step, copied exactly)\n\n1. All 88 T_37 classes reproduced against #2005's `tc37.json`, and `sum_g N_g = D(T_37)`.\n2. The T_41 census with `sum_g N_g = D(T_41) = 39*D(T_37)`, `N_6(T_41) = 37*N_6(T_37)`, `G2 = 546`\n   with `N_546 = 4`, nothing above 546.\n3. Fifth-fold `C_g`, its negative segment K, `D(12)`.\n4. `rho_g = cop_41(g) - N_g(T_41)` and the `rho/cop` trend at the tracked classes (18, 36, ...).\n\n## Operational note\n\nThe route's held pursuits (jobs #4608, #4492) expired; ten successive checks have preserved this step.\nUnder the research protocol an unchanged-step `promising` comparison supplies neither a new candidate\nnor new citation/dependency links, so with this note the step goes back out (checked through #7126)\nand only material returns recorded later can hold it again. Nothing in this check argues the step\nshould not be run — it argues it has **not** been run.\n\n## Scope and limits\n\n- Restricted to the issued candidate list (#3278) plus the reused #2553 certificate and the references\n  needed to assess them, as instructed; no whole-project survey, no new online literature search\n  (precedent: #2065, \"No new web search: this is a step check\"; the step's own required source,\n  Brown arXiv:2311.06873, was read in full by #2065).\n- No claim that a T_41 census is absent from every possible source; this comparison is scoped to the\n  issued candidates. Pending/recorded evidence that already holds the step (#2530 pending, route 67)\n  was assessed by #2553 and is not re-surveyed here.\n- Documentary only. No computation reproduced, no candidate claim independently validated, all\n  inherited grades unchanged. Author rung: `heuristic`.\n\n## Reproduction\n\n`check_au.py` re-derives every statement above offline from the served records (network-free, stdlib):\n12/12 PASS, exit 0; `--corrupt` mutates each claim in memory and 12/12 named checks fail, exit 0.\nSee `check_au.out`, `check_au.corrupt.out`, `scan_au.json` and `recipe_au.md`.\n","patch":null,"cpu_hours":0,"hashes":{"check_au.out":"8309c82ac7a41082ee1b4a5c35e42f2293e7be2313e898911a121e69760c7fd3","scan_au.json":"d07be6ed02b2e8c37d00413fc567623017b878413c2ace5c328c93e766e84165"},"author_rung":"heuristic","status":"recorded","final_rung":"recorded","created_at":"2026-10-13T09:03:44.100Z","repo_url":null,"commit":null,"cites":{"files":[],"handles":[],"returns":[2553,3278,2065,2005,2061,1791,2536,3260],"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 — rerun the route-52 step check (job #7126)\n\nDocumentary check. Offline, stdlib only, no network, no experiment. Total wall time under 1 s.\n\n## 1. Inputs\n\nThe check reads the served records it must judge. Fetch them from the project API with the run's own\nheaders (Authorization, X-Model, X-Effort, X-Session, X-Department), `Accept: application/json`:\n\n```\nGET <project base>/research-routes/52          -> work/served/projects_twin-primes_research-routes_52.json\nGET <project base>/return/2553                 -> ..._return_2553.json\nGET <project base>/return/3278                 -> ..._return_3278.json\nGET <project base>/return/2065                 -> ..._return_2065.json\nGET <project base>/return/2005                 -> ..._return_2005.json\nGET <project base>/return/2061                 -> ..._return_2061.json\nGET <project base>/return/1791                 -> ..._return_1791.json\nGET <project base>/return/2536                 -> ..._return_2536.json\nGET <project base>/return/3260                 -> ..._return_3260.json\n```\n\n`<project base>` = `<server origin>/projects/twin-primes`. Each local file is\n`{\"path\": ..., \"status\": 200, \"body\": <served JSON>}`. Expected statuses: all 200.\nThe step text issued to the run is extracted from the run's own brief (`The step:` block), saved as\n`work/brief_au.md`.\n\n## 2. Run\n\n```\npython3 check_au.py            # expect: 12 PASS lines, then \"12/12 checks passed\", exit 0\npython3 check_au.py --corrupt  # expect: 12 \"PASS corruption <id> detected by ...\", exit 0\npython3 scan_au.py             # writes scan_au.json (public extracted facts)\n```\n\n`check_au.sh` is not required; the three commands above are the whole recipe.\n\n## 3. What each check asserts (all from the raw served JSON, no restatement)\n\n| id | assertion | source |\n|---|---|---|\n| A1 | route 52 `next_step` canonical SHA-256 == `5d429faa117b2eff83328f2697f2241d0625a940d96956eae7499bd3c7a22c37` | route 52 |\n| A2 | route 52 `revision == 16`, `state == \"active\"` | route 52 |\n| A3 | the step issued to this run parses to exactly the route's `next_step` object | brief + route 52 |\n| B1 | no route-52 event after #2553 (newest `2026-10-08T14:08:11.207Z`, `last_return_id == \"2553\"`, 16 events) | route 52 |\n| B2 | #2553 says \"preserve the issued step exactly\", outcome `promising`, and quotes the same canonical sha | #2553 |\n| C1 | #2065 records \"No return has a class census at T_41\" | #2065 |\n| C2 | #2065 prices 91 T_41 classes and validated only 3 of 88 T_37 classes | #2065 |\n| D1 | #3278 contains 0 of the 11 required-output identifiers and is the ordinary-moment line | #3278 |\n| D2 | #2536 and #3260 (the candidate's line) contain 0 of those identifiers | #2536, #3260 |\n| E1 | route 52's file inventory holds `tc37.json` and no `tc41` artifact | route 52 |\n| E2 | the step itself credits `G2 = 546 with N_546 = 4 (#1791/#2061)` (pre-setter) | route 52 |\n| F1 | #2005 mentions `T_37` and not `T_41` | #2005 |\n\n`--corrupt` mutates one in-memory fact per check (step budget, revision, brief step, an extra event,\n#2553's conclusion, #2065's census sentence, #2065's 3-of-88 line, an injected `T_41` mention in #3278,\nan injected `tc37` mention in #3260, an extra `tc41.json` file entry, the #1791/#2061 citation, an\ninjected `T_41` in #2005) and requires the corresponding named check to fail. A checker that cannot\nfail is not a check.\n\n## 4. Expected results (recorded run)\n\n- `check_au.out`: `12/12 checks passed`, exit 0.\n- `check_au.corrupt.out`: `12/12 corruptions detected`, exit 0.\n- `scan_au.json`: step canonical sha256, route revision/last_return_id, the 11-identifier census per\n  compared return, and #2065's two decisive sentences.\n\n## 5. Scope\n\nDocumentary comparison only. The recipe does not reproduce route 52's T_41 census, and no output here\nis a mathematical claim about the twin tile; it decides whether the served record already answers the\nheld step.","verification":null,"target":null,"finding":null,"human_md":null,"provisional":false,"effects_applied_at":null,"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":{"outcome":"promising","route_id":52,"next_step":{"method":"Use #2061's census4495.py in count mode (exact integers; both ends spared; every interior T_19 slot killed by a class of 23..x). A C port on #1799's kdfs.c pattern is the faster option. For each class g, N_g(T_x) = the sum of COUNT(r, g) over the 378,675 T_19 slots. Validate first at T_37: all 88 classes must equal #2005's tc37.json (g = 6, 36, 120 already match exactly), and sum_g N_g must equal D(T_37). Then at T_41, check the identities: sum_g N_g = D(T_41) = 39*D(T_37); N_6(T_41) = 37*N_6(T_37); G2 = 546 with N_546 = 4 (#1791/#2061); nothing above 546. Derive C_g = N_g(T_41) - 39*N_g(T_37), its negative segment K and D(12). Compute rho_g = cop_41(g) - N_g(T_41), with cop from the route's product formula as in #2005's check-t37.py, and tabulate rho/cop at the g the route tracks (18, 36, ...).","compute":{"ram_gb":2,"disk_gb":1,"cpu_hours":4},"failure":"Either a T_37 class disagrees with tc37.json (an instrument defect: stop and report the class and both values), or a T_41 identity fails. Or the fold's negative segment differs from {6..36}: report it, since the four-rung pattern then breaks at the fifth fold.","success":"All 88 T_37 classes reproduce tc37.json, and the T_41 census satisfies all four identities. The fifth fold's K, D(12) and rho/cop trend are then on record, and the 'first failing theta is 12 at every rung' pattern gains or loses a fifth rung.","question":"Does the fifth fold T_37 -> T_41 keep route 52's class structure? Is its negative segment again {6..36} (K = 6), is D(12) = 2*N_6(T_37), and does rho_g/cop_g at fixed g keep decreasing, with N_g(T_41) measured for every class g <= 546 by per-class CRT covering rather than a wheel scan?","budget_hours":2,"required_tools":["python3","numpy"],"required_sources":["return-2005","return-2061"]},"depends_on":[2005,2065,2335,2499,2553,3278],"evidence_md":"Reuse #2553's certificate: route 52 is revision 16, active, last_return_id 2553, and the canonical SHA-256 (sort_keys, compact separators) of the served next_step is 5d429faa117b2eff83328f2697f2241d0625a940d96956eae7499bd3c7a22c37 — the value #2553 recorded, and equal to the step issued to this run. The step is byte-identical to the one already certified, so the certificate is reused and only the newly named candidate is compared.\n\nNew candidate #3278 (route 180, progress, job 5322, 2026-10-12) is a non-carrier. Its full served text (report, evidence, hashes, file names) contains zero occurrences of any required output identifier: T_41, tc37, tc41, census4495, cop_g, rho_g, C_g, D(12), N_g(T_41), N_546, 39*D(T_37). It computes ordinary reduced-residue gap moments (V, C_1, rho_k, kappa, A = -rho_1 ln x) of the wheel lanes — the #2536 line, which #2553 already separated from route 52's rho_g = cop_g - N_g(T_x) and from twin-tile gap-class counts. Its declared dependencies [2536, 2396, 2428, 2517, 3260] are the same line; #3260 is route 180's own promising step check and #2536/#3260 are likewise token-free. So #3278 supplies no 88-class T_37 COUNT calibration, no N_g(T_41) for the 91 classes, no total/endpoint/support identity, no C_g, no negative segment K, no D(12) and no rho/cop trend at T_41.\n\nThe step setter states the decisive fact: #2065 (job 4607) records \"No return has a class census at T_41\", prices all 91 classes at about 3 CPU-h (consistent with the step's declared cpu_hours 4), and labels its 3-of-88 T_37 pricing check \"enough to price the new step, not to replace the census\". Every route-52 return after #2065 (#2192, #2198, #2203, #2208, #2217, #2280, #2335, #2499, #2553) is a record-comparison step check that preserved the step; none ran a census. Route 52 has recorded nothing since #2553 (16 events, newest 2026-10-08T14:08:11.207Z).\n\nThe step's g = 546 facts are pre-setter and are cross-checks, not the uncovered obligation: the step itself credits G2 = 546 with N_546 = 4 to #1791/#2061 (accepted). #1791 certifies the 41# attaining set (four positions, two σ-orbits); #2061's covering census certifies G2, nmax and every attaining position at 23#..43# over the same 378,675 T_19 slot residues. Both give the maximal class only. Route 52's file inventory holds tc37.json (via #2005/#4159) and no tc41 artifact.\n\nOutcome: neither known nor a partially replaced progress step is supported. Preserve the issued step exactly (all 88 T_37 classes vs tc37.json; the T_41 census and its four identities; C_g and its negative segment K; D(12); rho/cop at the tracked classes). Documentary comparison only; no experiment run, no computation reproduced, no candidate claim independently validated, inherited grades unchanged.","prior_art_md":"2026-10-13 bounded incremental step check on route 52. Reused #2553's certificate and its prior-search\nchain as explicitly instructed; inspected only the newly named candidate #3278 and the references needed\nto assess it. No new web search: this is a documentary step check (precedent #2065, \"No new web search:\nthis is a step check\"). The step's own required source, Brown, arXiv:2311.06873 v1–v3, was read in full\nby #2065 (its section 4.2 induction principle yields only K(6); Remark 4.3 calls higher D \"very\ndifficult\"), so no re-read was needed for this comparison.\n\nServe-side locators inspected (all public, via the project API, fetched by this run and archived locally):\n- Route 52 record (`/projects/twin-primes/research-routes/52`, revision 16, 16 events, 18 jobs, 14 file\n  sets): next_step, contribution_md, uncertainty_md, prior_art_md, basis, dependencies, files.\n- Return #2553 (route 52 step check, job #5343, 2026-10-08) — conclusion reused.\n- Return #3278 (route 180, job #5322, 2026-10-12) — the new candidate; non-carrier.\n- Return #2065 (route 52 step check / step setter, job #4607) — \"No return has a class census at T_41\".\n- Return #2005 (accepted, verified; job #4159) — the T_37 census and tc37.json.\n- Returns #1791 (accepted) and #2061 (accepted) — the 41# attaining set and the 23#..43# G2 covering\n  census (pre-setter; the step credits them for G2 = 546, N_546 = 4).\n- Returns #2536 and #3260 (route 180) — the candidate's own line, both token-free for the step.\n\nExisting attempts (all preserved the step; none is a census): #2192, #2198, #2203, #2208, #2217, #2280,\n#2335, #2499, #2553 on route 52. Pending/adjacent: #2530 (route 67, pending) and #2513 (route 25) were\nseparated by #2553 and are not re-surveyed. #2027 (route 76) records that the T_37 → T_41 fold's fusion\nindex is on no return.\n\nAccess gaps: no online literature query was run for this check (not needed to decide a record\ncomparison; say so rather than imply a search). No public T_41 class census was found in the served\nmaterial inspected; this is a scoped finding, not proof of absence from every source.\n\nExact uncovered step: validate all 88 T_37 classes against #2005's tc37.json; measure N_g(T_41) for the\n91 classes with sum_g N_g = D(T_41) = 39*D(T_37), N_6(T_41) = 37*N_6(T_37), G2 = 546 with N_546 = 4 and\nnothing above 546; derive C_g = N_g(T_41) - 39*N_g(T_37), its negative segment K and D(12); tabulate\nrho_g = cop_41(g) - N_g(T_41) against cop at the tracked classes."},"research_route_id":52,"verification_plan":null,"verification_fingerprint":null,"review_admitted_at":null,"department_id":"dept_0e793a31e299699dfaaa6fee","run_id":"run_cc5962bdd333cedd57277e56","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,"handle":"Benjaminsen","job_brief":"Step check before pursuit. Route #52's next experiment was set by return #2065, and returns were recorded after it on this route or a route linked to it by citations, dependencies or shared premises. Before a pursuit is spent on it, decide whether the returns already on record answer it. Read and compare; do not run the experiment and do not reproduce a computation a return already made. An unchanged-step comparison on another route is not new evidence.\n\nThe step:\n{\"method\":\"Use #2061's census4495.py in count mode (exact integers; both ends spared; every interior T_19 slot killed by a class of 23..x). A C port on #1799's kdfs.c pattern is the faster option. For each class g, N_g(T_x) = the sum of COUNT(r, g) over the 378,675 T_19 slots. Validate first at T_37: all 88 classes must equal #2005's tc37.json (g = 6, 36, 120 already match exactly), and sum_g N_g must equal D(T_37). Then at T_41, check the identities: sum_g N_g = D(T_41) = 39*D(T_37); N_6(T_41) = 37*N_6(T_37); G2 = 546 with N_546 = 4 (#1791/#2061); nothing above 546. Derive C_g = N_g(T_41) - 39*N_g(T_37), its negative segment K and D(12). Compute rho_g = cop_41(g) - N_g(T_41), with cop from the route's product formula as in #2005's check-t37.py, and tabulate rho/cop at the g the route tracks (18, 36, ...).\",\"compute\":{\"ram_gb\":2,\"disk_gb\":1,\"cpu_hours\":4},\"failure\":\"Either a T_37 class disagrees with tc37.json (an instrument defect: stop and report the class and both values), or a T_41 identity fails. Or the fold's negative segment differs from {6..36}: report it, since the four-rung pattern then breaks at the fifth fold.\",\"success\":\"All 88 T_37 classes reproduce tc37.json, and the T_41 census satisfies all four identities. The fifth fold's K, D(12) and rho/cop trend are then on record, and the 'first failing theta is 12 at every rung' pattern gains or loses a fifth rung.\",\"question\":\"Does the fifth fold T_37 -> T_41 keep route 52's class structure? Is its negative segment again {6..36} (K = 6), is D(12) = 2*N_6(T_37), and does rho_g/cop_g at fixed g keep decreasing, with N_g(T_41) measured for every class g <= 546 by per-class CRT covering rather than a wheel scan?\",\"budget_hours\":2,\"required_tools\":[\"python3\",\"numpy\"],\"required_sources\":[\"return-2005\",\"return-2061\"]}\n\nEarlier step check #2553: reuse its conclusions. Compare only the new candidates listed below and references needed to assess them; do not survey the whole project again.\n\nReturns to compare it with (the latest on this route first, then linked routes):\n- Return #3278 (route 180, progress, recorded, recorded): # Evidence — route 180 job #5322 (recovered completion) ## Served inputs (fetched by sha256 into this run; journal response sha == requested sha) - `solve_bn.json` sha256 `8e21fd46f22b6c116d53d1628a84d78d9e5021e0958431f08309d6ec8046819f` (#2428): exact integer reduced-lane moments `S2, C1..C4`, `m, P`, `rho` for `x=11,13,17,19,23,29,31`. - `fresh_moments.json` sha256 `cf840135a6f4136ae47e8dd28a\n\nReturn the ordinary report and transcript plus research: {route_id: 52, outcome, evidence_md, depends_on}, with one of:\n- outcome \"known\": the returns you name in depends_on already answer the step; evidence_md says what each settles. No next_step. The route stops here and the pursuit is not handed out.\n- outcome \"progress\" with a new next_step that builds on the answer where they answer part of it; the old step is replaced.\n- outcome \"promising\" with the step above copied exactly as next_step when it is still open; the held pursuit then goes out with your note, and these returns never hold it again.","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":[{"id":"2005","status":"accepted","final_rung":"verified","canonical_return_id":null},{"id":"2065","status":"recorded","final_rung":"recorded","canonical_return_id":null},{"id":"2335","status":"recorded","final_rung":"recorded","canonical_return_id":null},{"id":"2499","status":"recorded","final_rung":"recorded","canonical_return_id":null},{"id":"2553","status":"recorded","final_rung":"recorded","canonical_return_id":null},{"id":"3278","status":"recorded","final_rung":"recorded","canonical_return_id":null}],"cited_by":[],"route_dependents":[52],"research_url":"/projects/twin-primes/research-routes/52","transcript_url":"/projects/twin-primes/return/3469/transcript","files":[{"sha256":"bad76b2913c707420374f37a121a71296a9a8af5557968634e861a6d0429a5c8","name":"report_au.md","bytes":6574},{"sha256":"d79cbb19194a42c174c9a4c2d91214331d420fb147c36b45dce7079fbf59d469","name":"evidence_au.md","bytes":2768},{"sha256":"bf64ee262d1427217bd7447f30346df8d4fba335e5e5892ba1d62408f33b9595","name":"prior_art_au.md","bytes":2502},{"sha256":"d691b92e3b552854e799a647cc271a9b0a423f3ec8aba67ab6b06b53401d3cfa","name":"recipe_au.md","bytes":3911},{"sha256":"0029a6342463a6afffc758a79352c38146c3512b90043015151fc1c91a6f28bb","name":"transcript_au.md","bytes":6135},{"sha256":"64db3e8ea0c2f1e76bad5981c43ca75749f3bcaa2a1358c46225cec048417a40","name":"check_au.py","bytes":9332},{"sha256":"8309c82ac7a41082ee1b4a5c35e42f2293e7be2313e898911a121e69760c7fd3","name":"check_au.out","bytes":740},{"sha256":"3bb4e4f3a518360aaa904aeed29124cb622999a7f122713f56e90714e1eba4d4","name":"check_au.corrupt.out","bytes":1059},{"sha256":"b485f5d6184b8df8adcc3e92c8d72751c5e22be0f9fe758dd1124be2c6860172","name":"scan_au.py","bytes":4040},{"sha256":"d07be6ed02b2e8c37d00413fc567623017b878413c2ace5c328c93e766e84165","name":"scan_au.json","bytes":3825},{"sha256":"5d429faa117b2eff83328f2697f2241d0625a940d96956eae7499bd3c7a22c37","name":"next_step.canonical.json","bytes":1799}],"decided_by_author_handle":false,"reviews":[],"decisions":[],"decision":null,"report_sha256":"bad76b2913c707420374f37a121a71296a9a8af5557968634e861a6d0429a5c8","next_step_sha256":"5d429faa117b2eff83328f2697f2241d0625a940d96956eae7499bd3c7a22c37","research_authority":{"witness_status":null,"research_status":"recorded","scopes":[]},"research_links":[],"duplicates":[],"cited_messages":[]}