{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"slug":"pw-0003-the-retrofit","title":"A published article was dragged through the proof standard it argues for — one check failed","body":"The standard this site published had only ever been applied forward — new work, built inside it from the first keystroke. This article records the harder test: a piece of work that already existed, written before the standard settled, dragged backward through it. The subject is [[custody-of-the-answer]], the comparative survey published the same day. The instrument is the five-check checklist at [[proven-work]]. The result is proven work object PW-0004: seven of eight declared requirements resolve to evidence. One fails, honestly, and the failure is the most useful thing in the record.\n\n## The four steps, run on finished work\n\nThe canonical page claims existing work migrates in four steps: write the claim as a requirement manifest, bind each requirement to the records that exist, name every gap where the record is missing, mint the door. That claim is now tested, not asserted.\n\n**Step one — the manifest.** Eight requirements, mirroring the family's shared shape so the objects stay comparable: demand, deliverable, formation, considerations, source_boundary, result_checks, robustness, surety. The manifest lives on the article itself as `meta.extra.proven_work`, so the object and its claim travel together.\n\n**Step two — the binding.** Each requirement carries the ids it resolves to. The deliverable binds to the article. Formation binds to the creation event, the generated hero (`img/gen/arcads-gpt-image-704d78a0-cfe7-4e4b-916d-2afb65e394d2.png`), the distribution receipt ([the X post](https://x.com/i/web/status/2084180317531943088)), and — because the record keeps errors — the first X attempt's refusal (`inv_t7j7drn0tb`, cut 24 characters, trimmed, reposted). Result checks bind to the article's live health endpoint. Sources bind to the sources ledger.\n\n**Step three — the gaps, named.** One requirement could not bind. The demand — what the owner actually asked for, 2026-08-02 23:39 UTC — was spoken to a Kimi Desktop session, and that session does not write its turns to the build ledger. The original request exists in a wire the record cannot reach. The standard's own rule covers this: a claim reconstructed afterward is work product and says so. The demand was recorded post-hoc through the thread intake (`thread:custody-of-the-answer#B7:T0`), and the requirement prints PARTIAL with the gap named rather than PASS with the gap hidden.\n\n**Step four — the door.** The projection computes its own status at [the proof endpoint](https://miscsubjects.com/api/proven-work/custody-of-the-answer). Inspection doors mint from the object's drop lane; a stranger's walk through it, receipted, is `inv_2prgwtaztd`.\n\n## The stranger\n\nA model that has never authored anything on this site — Llama 3.3 70B, reached through the versioned adjudication row `ADJUDICATE_ATTEST_LLAMA_33` — was handed the projection and one question: does the article's claim resolve against its formation record, with the two gaps honestly stated rather than concealed? Its finding opens: *\"DECISION: AFFIRM; the claim under test is supported by the evidence named in the manifest, with two gaps honestly stated rather than concealed.\"* Receipt `inv_gqvj1xprdv`. The verdict is signed onto the object itself through the certify lane — certification costs proof of reading, and the inspection receipt paid it.\n\nThe record also keeps the attempt that failed. The first fixed-packet run (`inv_bagw2j9n61`) returned a structurally complete finding whose durable copy was truncated at 795 characters — the verdict line never made it into the record, which under the instrument's own law makes the finding void. The repair was an output law, not a rerun: the verdict now travels on the first line, before any field that can be cut. A proof system is only as good as what its records survive; this one now survives its own truncation ceiling.\n\n## What the family now shows\n\nThree objects, three verdicts, and the standard discriminates between them:\n\n- **PW-0001** — PARTIAL: considerations reconstructed after publication; no independent challenge.\n- **PW-0002** — PROVEN: eight of eight, a sealed multi-model statutory panel.\n- **PW-0004** — PARTIAL: seven of eight; the demand was never ledgered at origin.\n\nNone of the three statuses was asserted by the worker. Each is computed from the manifest by the projection, and the two PARTIALs print their gaps in the open. That spread is the point: a standard that hands everything a pass is a stamp, and a standard that fails everything is a wall. This one separates work by what the record bears.\n\n## The gap that matters most\n\nThe one unresolved requirement is not a writing defect — it is a build defect, and the standard caught it in its own house. Kimi Desktop sessions do not land on the events ledger; the loop law (LP26) says every agent session must. Until that hook exists, any work this surface produces starts with a demand gap by construction. PW-0004 is the receipt that makes the missing hook undeniable: the record proved the article, and in doing so proved the hole the next repair has to close.\n\n## Sources\n\n- https://miscsubjects.com/a/proven-work — the canonical standard and its five-check checklist.\n- https://miscsubjects.com/a/custody-of-the-answer — the work object under test.\n- https://miscsubjects.com/api/proven-work/custody-of-the-answer — the PW-0004 projection; computes status from the manifest.\n- https://miscsubjects.com/receipt/inv_gqvj1xprdv — the Llama 3.3 finding: DECISION AFFIRM.\n- https://miscsubjects.com/receipt/inv_bagw2j9n61 — the void first attempt; verdict lost to record truncation.\n- https://x.com/i/web/status/2084180317531943088 — the distribution receipt bound to formation.\n","register":"standard","hero":"img/gen/arcads-gpt-image-f93e9a28-1864-4595-8d0f-9c456de059a5.png","hero_brief":"photorealistic editorial photograph, gpt-image 16:9 via arcads (f93e9a28): dossier through an X-ray inspection scanner, monitor rendering its contents as an annotated digital outline","editorial_review":{"headline_subject":"a published article retrofitted to the proof standard it argues for, with one honest failure","hero_subject":"an open paper dossier with loose ledger pages on an airport X-ray baggage-scanner conveyor entering the tunnel","visual_action":"the scanner's side monitor renders the dossier as a cool-blue digital outline marked with inspection checklist ticks","rationale":"literal machine inspection of an existing record — the article's act — in a composition unlike any prior hero (no boxes, seals, laptop, door, server, printer)","inspected":true,"inspection_note":"hero f93e9a28 viewed: open dossier on conveyor before scanner tunnel; monitor shows annotated checklist outline; cool X-ray blue vs warm tungsten room; no people","hero_brief":"photorealistic editorial photograph, gpt-image 16:9 via arcads (f93e9a28): dossier through an X-ray inspection scanner, monitor rendering its contents as an annotated digital outline"},"tags":["proven-work","standard","migration","PW-0003","live-receipts"],"category":"build","style":{},"claims":[{"id":"c1","text":"Existing work migrates to the proven work standard in four steps: claim manifest, evidence binding, named gaps, minted door; PW-0003 executed all four on an already-published article.","tier":"speculative","source_ids":["s1","s3"],"source_status":"sourced"},{"id":"c2","text":"PW-0003 evaluates PARTIAL with 7 of 8 requirements passed, computed by the projection from the manifest rather than asserted.","tier":"speculative","source_ids":["s3"],"source_status":"sourced"},{"id":"c3","text":"The unresolved requirement is demand: the original request was made to a Kimi Desktop session, which does not write turns to the build ledger; it was recorded post-hoc via the thread intake and prints PARTIAL.","tier":"speculative","source_ids":["s3"],"source_status":"sourced"},{"id":"c4","text":"Llama 3.3 70B, a model with no authorship on the site, returned DECISION: AFFIRM on the claim under test, receipt inv_gqvj1xprdv, and the verdict is certified onto the object.","tier":"speculative","source_ids":["s4"],"source_status":"sourced"},{"id":"c5","text":"The first adjudication attempt (inv_bagw2j9n61) was void because its durable record truncated at 795 characters, losing the verdict line; the repair places the verdict on the first line of output.","tier":"speculative","source_ids":["s5"],"source_status":"sourced"},{"id":"c6","text":"The three-object family now discriminates: PW-0001 PARTIAL (two gaps), PW-0002 PROVEN (8/8), PW-0003 PARTIAL (one gap); no status was asserted by a worker.","section":"who_claims_what","tier":"speculative","source_ids":["s1","s3"],"source_status":"sourced"},{"id":"c7","text":"The demand gap evidences a build defect: Kimi Desktop sessions do not land on the events ledger as loop law LP26 requires.","tier":"speculative","source_ids":["s3"],"source_status":"sourced"},{"id":"c8","text":"The failed first X post (inv_t7j7drn0tb) is retained in the formation binding as part of the record, which keeps errors alongside successes.","section":"who_claims_what","tier":"speculative","source_ids":["s6"],"source_status":"sourced"},{"id":"c9","text":"The work object under test, custody-of-the-answer, argues that nine proof disciplines each prove origin, integrity, or observation while none opens the record of the work for reconstruction.","section":"who_claims_what","tier":"system","source_ids":["s2"],"source_status":"sourced","why_material":"posted via claim protocol — prompt injection into ledger"}],"sources":[{"id":"s1","type":"article","url":"https://miscsubjects.com/a/proven-work","title":"Proven work: the base unit","quote":"write the claim as a requirement manifest; bind each requirement to the records that already exist; name every gap; mint the door","summary":"The canonical standard and checklist.","claim_ids":["c1","c6"]},{"id":"s2","type":"article","url":"https://miscsubjects.com/a/custody-of-the-answer","title":"Custody of the answer","quote":"every system proves custody of the answer; none opens the record of the work","summary":"The work object under test.","claim_ids":["c9"]},{"id":"s3","type":"api","url":"https://miscsubjects.com/api/proven-work/custody-of-the-answer","title":"PW-0003 projection","quote":"PARTIAL, 8 declared requirements, 7 passed, unresolved: demand","summary":"Computed status from the manifest.","claim_ids":["c1","c2","c3","c6","c7"]},{"id":"s4","type":"receipt","url":"https://miscsubjects.com/receipt/inv_gqvj1xprdv","title":"Llama 3.3 finding","quote":"DECISION: AFFIRM; the claim under test is supported by the evidence named in the manifest, with two gaps honestly stated rather than concealed","summary":"Independent fixed-packet adjudication.","claim_ids":["c4"]},{"id":"s5","type":"receipt","url":"https://miscsubjects.com/receipt/inv_bagw2j9n61","title":"Void first attempt","quote":"record truncated before the verdict line","summary":"Finding void under its own contract; repaired by verdict-first output law.","claim_ids":["c5"]},{"id":"s6","type":"receipt","url":"https://x.com/i/web/status/2084180317531943088","title":"Distribution receipt","quote":"Nine proof systems surveyed. Every one proves custody of the answer.","summary":"The X post bound to formation.","claim_ids":["c8"]}],"prov":{"model":"unattributed","action":"write"}}