feat(ms-ai-architect): #32 ratifisert — entryens egen referent var selv oppdiktet, og klassen var 3 ikke 2 [skip-docs]
idx-27c + idx-27d adjudisert sammen; idx-27e opprettet og lukket i samme
commit fordi maalingen viste at den var samme defekt.
MAALT FOER SPOERSMAALET (#29-disiplinen):
- korpus-bredt: "disclosure widget" = 1 fil / 2 instanser; "generative AI
toolkit" = samme fil / 1 instans
- MCP microsoft-learn, fire oppslag, hvorav TO er lukkede enumerasjoner og
derfor bevis for fravaer, ikke bare fravaer av bevis:
* authoring-system-topics enumererer ALLE system-temaer i begge dialekter.
Ingen "AI disclosure". Sida sier selv "You can't create system topics".
Predefinerte custom-temaer er ogsaa enumerert - heller ikke der.
* responsible-ai-overview - FILA SIN EGEN OPPGITTE KILDE - enumererer hver
AI-drevet feature i Copilot Studio. Ingen "generative AI toolkit".
* Foundry Agent Service Transparency Note enumererer 5 knowledge tools og
10 action tools uttoemmende. Ingen embeddable disclosure-widget.
HVA DETTE VELTET: idx-27d var bokfoert som intra-fil navnedrift, paa premisset
at "this same file's Copilot Studio section documents a pre-built 'AI
disclosure' TOPIC". Den referenten (l.436) er selv en uverifisert flate, og
INGEN entry dekket den. Navnedrift krever et navn aa drifte FRA. Klassen er
3 instanser i 1 fil, og den tredje er nettopp grunnen begge entryene stolte paa.
Arve-argumentet feilet for FJERDE gang, i ny retning: her lot det ikke bare
vaere aa lisensiere en reparasjon - det skjulte en defekt ved aa faa den ene
instansen til aa se ut som korreksjonen av den andre.
TRE INSTANSER, TRE ULIKE OPERASJONER (koherens maalt, ikke antatt):
- l.418 slettet -> "Agent transparency" staar igjen med 2 punkter
- l.436 slettet -> "Customization" staar igjen med 1 punkt
- l.621 KUNNE IKKE slettes: "+"-konjunksjonen binder to verktoey, saa fjerning
av ett gir hengende konjunksjon. Omskrevet til aa navngi standardmeldingen
fila selv dokumenterer paa l.218/425, som er kildebekreftet.
Ingenting teller eller refererer de tre stedene; footeren teller 17 URL-er.
Suite 1052/1052. Koea: 58 entries (6 aapne, 52 resolved), 12 former (#21-#32).
Alle 12 GOVERNS-pekere haandverifisert -> eksisterende, resolvede entries.
[skip-docs]: ren KB-korrektur, ingen endring i kommandoer/agenter/skills/hooks.
This commit is contained in:
parent
b290022c59
commit
bae9c70d50
2 changed files with 22 additions and 8 deletions
|
|
@ -18,7 +18,8 @@
|
|||
"#28": "A KEEP-CLASS COUNT WHOSE TRUE HALF IS BOTH TRUE AND UNIQUE. Ratified 2026-08-12. This is the residual case #23 explicitly declined to ratify and sent back as a new question; this is its first instance, and it is decided rather than inherited.\nTHE FORM: where a keep-class line carries several counts, some measured FALSE and at least one measured TRUE, and that true part is NOT restated anywhere else in the file, CORRECT the false numbers to their measured values. Do not delete the line.\nTHIS IS THE PROGRAMME FIRST AUTHORED NUMBER, and the operator decided it deliberately on 2026-08-12. Until now every resolution deleted, on the idx-26v ground that a repair must not author the defect class it closes. That ground still holds where deletion is FREE - which is why idx-26t, decided in the same session, deletes. It stops holding where deletion destroys a true and unique claim, because then silence is not the cheap option, it is a second defect.\nTHE INSTANCE, rag-document-preprocessing.md:791 (the entry evidence and STATE both said :792 - off by one; the anchor is verbatim text, so nothing depended on it). \"8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**\" -> \"8 Microsoft Learn-artikler + 2 GitHub-repos = **10 kilder**\".\nMEASURED, and the population was re-checked after the edit rather than assumed: 8 distinct learn.microsoft.com articles after /en-us normalisation (TRUE as written), 2 distinct github.com URLs (NOT 4), therefore 10 named source URLs (NOT 12). The three azure.microsoft.com pricing URLs are excluded because the line states its own referent - Learn articles plus GitHub repos - and never claimed to cover them.\nTHE POPULATION CHECK THAT COULD HAVE INVALIDATED THIS: the file does not end at the footer - a further section runs :795-803 - so the footer might have been a section total measured over the wrong span. Measured: ZERO Learn or GitHub URLs occur after :791. All 11 occurrences precede it. The count covers what it claims.\nTHE LIMIT: this form applies only where the true part is BOTH true AND unique. Where the true part is restated elsewhere, deletion remains free and #23 governs. Where every part is false, #24 governs. A keep-class count that is merely unverifiable, rather than measurably wrong, is not reached by this form at all - that is still the idx-26j class.\nGOVERNS: idx-26at.",
|
||||
"#29": "A FILE-PROPERTY FIELD THAT NO EDIT CAN KEEP TRUE. Ratified 2026-08-12.\nSCOPE FIRST, and the scope was MEASURED BEFORE THE QUESTION WAS PUT rather than after - the discipline idx-26j's scope addendum named after booking stopped at 7 of 21. Only idx-26u was booked, but \"**File size:**\" occurs in THREE files corpus-wide, and the operator ratified the form over all three in one decision instead of over the one that happened to be on the queue.\nTHE FORM: where a footer or metadata field states a physical property of the file itself - its byte size - DELETE THE LINE. Nothing is authored and nothing is renamed.\nTHE GROUND, and it is NOT #22's ground. #22 deletes because nothing can adjudicate the claim; git adjudicates this one exactly, which is why the form needed its own ratification and why idx-26u's own inheritance argument (\"deletion follows from idx-26j rather than requiring a new ratification\") was NOT accepted - the same premise type this programme falsified twice on 2026-08-12. Three grounds, each measured:\n (1) EVERY PART IS FALSE, so there is no true half to preserve. #28 sends this case onward in its own words: \"Where every part is false, #24 governs.\"\n (2) DELETION COSTS NO TRUE INFORMATION. A byte size has no use in a knowledge-base reference file and is trivially measurable by anyone who wants it. STATE's rule - delete where deletion is free, correct where deletion costs true and unique information - lands on delete.\n (3) THE ONLY AVAILABLE REPAIR IS SELF-INVALIDATING. Restating \"~18 KB\" writes a line that the very next edit to the file makes false again. That is not a repair; it is authoring a future instance of the defect class being closed - the idx-26v hazard in a new costume.\nMEASURED, all three, against the working tree: azure-cost-management-ai.md:295 claimed ~14 KB against 18499 bytes (18.0 KB, 29% off); budget-forecasting-ai-projects.md:530 claimed ~14 KB against 20001 bytes (19.5 KB, 39% off); agent-evaluation-testing-frameworks.md:565 claimed ~29 KB against 27864 bytes (27.2 KB, 6.6% off - defensible under the tilde, and deleted anyway BECAUSE THE GROUND IS THE FIELD TYPE, NOT THE SIZE OF THE ERROR). idx-26u's git history is the strongest form of ground (1): the line read ~14 KB in the EARLIEST version the repo can observe (baa2d02, 17388 bytes) and at every commit since, so it was never true at any observable point.\nONE CORRECTION TO idx-26u's OWN EVIDENCE, made before the form was applied: the entry recorded \"the working tree today is 18554\". It is 18499 - commit 30d4340 touched the file after the entry was written. The conclusion is unchanged; the number was re-measured rather than carried forward.\nEXPLICITLY NOT COVERED, booked rather than swept: \"- **Word count:** ~3200 ord\" at agent-evaluation-testing-frameworks.md:564 sits DIRECTLY ABOVE one of the deleted lines and is arguably the same self-invalidating class (measured: ~3200 against 3374 actual, 5.2% off). It was NOT in the ratification question, so extending this form to it would be the silent widening #22 refused and #26 refused after it. Booked as idx-26aw, open. It is the only word-count field in the corpus.\nTHE SURVIVING KEEP-CLASS NEIGHBOURS WERE MEASURED, NOT ASSUMED, since a deletion that leaves a false line behind is the residue class G7 exists for. All three are TRUE under the /en-us/ normalisation #28 established: \"**Total sources:** 8 unique Microsoft Learn URLs\" (8 distinct articles, 9 raw strings - the header **Source:** at :7 repeats tutorial-acm-create-budgets without the locale), \"**Unique sources:** 8 Microsoft Learn URLs\" (8 of 9), \"- **Unique sources:** 10 Microsoft Learn URLs\" (10 of 11). Nothing was booked against them.\nTHE LABEL \"**Document metadata:**\" IS KEPT UNCHANGED, per #22's label rule: its words name content, not the generation, so it is the \"Research Coverage\" case rather than the \"MCP Calls\" case. It still labels two surviving lines.\nGOVERNS: idx-26u, idx-26au, idx-26av.",
|
||||
"#30": "A MEASURABLE FILE PROPERTY THAT NO MECHANISM MAINTAINS. Ratified 2026-08-13. This is the widening of #29's ground that #29 itself refused to take silently, and it was put as its own question.\nTHE FORM: where a footer or metadata field states a MEASURABLE PROPERTY OF THE FILE ITSELF - its byte size, its word count - and no mechanism in this repository keeps that value true, DELETE THE LINE. Nothing is authored and nothing is renamed. #29 is the byte-size instance of this form; #30 is the ground stated at the width the evidence supports.\nTHE BOUNDARY, MEASURED BEFORE THE QUESTION WAS PUT, because the widest reading of \"self-invalidating\" is far larger than the class and would have swept the corpus. \"**Last updated:**\" occurs in 385 files and a later edit falsifies it exactly as it falsifies a word count - it is NOT reached by this form, on two measured grounds: it is contract-mandated (buildHeader emits it; validateKbFile requires it) and it is actively re-stamped by /architect:kb-update on every refresh (commands/kb-update.md:24, :192). It has a maintaining mechanism; a word count and a byte size have none. \"**Document version:** 1.0\" is likewise outside: a version string is a process assertion, not a property measurable against the file. ONE CANDIDATE BOUNDARY WAS TESTED AND DISCARDED rather than carried: backfill-last-updated.mjs was first taken to be the maintaining mechanism, and is not - it is a ONE-FILE backfill (decision-trees.md). The boundary rests on the header contract and the refresh path instead.\nTHE CLASS WAS MEASURED WITH THREE INDEPENDENT NETS, not with the one word the entry happened to use: (1) named variants (\"**Word count\", \"**Ordtelling\", \"**Antall ord\", \"**Words\", \"**Ordantall\", \"**Lengde\"); (2) case-insensitive \"word count\"; (3) a full enumeration of EVERY bold-label field carrying a numeric value across all 394 skills/**/*.md, grouped by label. The third net is the one that can see a field whose name nobody guessed: it returned no line count, no character count, no page count, no section count, no reading time. The class is ONE under every net.\nTHE INSTANCE, agent-evaluation-testing-frameworks.md:564: \"- **Word count:** ~3200 ord\" against a measured 3369 words (5.3% off). All three of #29's grounds hold here: (1) no part is true, so #28 sends the case onward in its own words; (2) deletion costs no true information - a word count has no use in a knowledge-base reference file and wc -w answers it in a second; (3) the only available repair is self-invalidating.\nGROUND (3) IS NO LONGER AN ARGUMENT, IT IS AN OBSERVATION, and that is what this ratification adds to #29. The entry and STATE both recorded wc -w = 3374. It is 3369. The five-word difference is the \"- **File size:** ~29 KB\" line that #29 DELETED FROM THIS SAME FILE the previous session (35ac933). The programme falsified its own freshly-measured word count inside one day, by doing the very work the form governs. A corrected \"~3370\" would have been false again at the next edit - authoring a future instance of the defect class being closed, the idx-26v hazard #29 named.\nWHAT WAS RE-MEASURED RATHER THAN INHERITED, since a deletion that leaves a false line behind is the residue class G7 exists for: \"- **Unique sources:** 10 Microsoft Learn URLs\" is TRUE - 10 distinct learn.microsoft.com URLs after /en-us normalisation (11 raw occurrences; one repeat). THE LABEL \"**Document metadata:**\" IS KEPT UNCHANGED per #22's label rule, and #22's PROMOTE CLAUSE DOES NOT FIRE: it is conditioned on the label itself being deleted, and this label is keep-class. It now heads a single surviving line, which no ratified form treats as a defect.\nGOVERNS: idx-26aw.",
|
||||
"#31": "A CHANNEL-DEFINED SOURCE BLOCK: THE CHANNEL ADJUDICATES, NOT THE PLACEMENT. Ratified 2026-08-13.\nTHE FORM: where a source list is partitioned into blocks whose OWN HEADER names the verification channel (\"Verified sources (MCP: microsoft-learn)\"), and a source's block membership conflicts with its per-source status label, the source's ACTUAL channel decides - read from its URL and compared against the channel the block header names. MOVE the source into the block its channel puts it in. Do NOT rewrite the label to match the placement.\nTHE GROUND, and it is not a preference between two defensible readings. idx-26s was deferred on the stated premise that \"neither direction is derivable from the file\". That premise was FALSIFIED by a measurement the entry never ran: the block header names a channel, and the channel is readable per source. In transparency-documentation-standards.md, 11 of the 12 Verified-block sources are learn.microsoft.com and the single exception is nr. 7 (blogs.microsoft.com, a June 2022 PDF); 0 of the 5 Baseline-block sources are learn.microsoft.com and the single exception is nr. 17 (learn.microsoft.com). The two channel outliers are EXACTLY the two status outliers. The labels agree with the channel in both cases; the placement disagrees in both. The opposite direction - rewriting the two labels to match their blocks - would AUTHOR two false claims: that a blogs.microsoft.com PDF was fetched via MCP microsoft-learn, and that a learn.microsoft.com page is mere model knowledge.\nTHE BOUNDARY, MEASURED BEFORE THE QUESTION WAS PUT. The form reaches ONLY blocks whose own header names the channel. 389 reference files swept; 31 carry both a verified-kind and a baseline-kind source block; both per-source marker dialects were run - \"(Status: X ...)\" and the bare/italic \"(X ...)\" - with block bounds tightened to the contiguous list. Exactly 3 conflicts surfaced across 2 files. One was HAND-VERIFIED AS A FALSE POSITIVE and is explicitly outside the form: language-services-question-answering.md:646 reads \"(verifisert via Microsoft Trust Center)\" under \"**Baseline (modellkunnskap):**\", naming a channel OTHER than the one that file's Verified block is defined by (\"**Verified (fra MCP microsoft-learn):**\"). Model knowledge cross-checked against a non-MCP source belongs in Baseline exactly where it sits; the word \"verifisert\" collides lexically, not semantically. THE CLASS IS THEREFORE 1 FILE / 2 INSTANCES.\nTHE INCOMPLETE LABEL VOCABULARY DOES NOT BLOCK THE FORM, and this had to be measured because the entry raised it as an obstacle. Only 14 of the 17 sources carry \"(Status: ...)\" at all - 13, 14 and 16 carry none, and 15 reads \"(Status: Adopted 2024 ...)\", outside the {Verified, Baseline} vocabulary. All four unadjudicable sources sit in the Baseline block and all four are non-learn.microsoft.com, so the channel decides precisely where the label is silent. A rule cannot be authoritative where it says nothing; the channel is not silent anywhere.\nA NET THAT FAILED FIRST, recorded because the failure is the reusable part. The first classifier read provenance tokens ANYWHERE in the header and returned MIX for \"Baseline sources (model knowledge + MCP-inferred)\", which carries BOTH \"Baseline\" and \"MCP\" - so the one file holding the known instance was silently filtered out and the sweep reported 0 conflicts over 27 candidate files. Leading-token precedence fixed it and the candidate set grew to 31. A net that cannot reproduce its own known instance is measuring nothing, and \"0 found\" from such a net reads as \"class closed\".\nGOVERNS: idx-26s."
|
||||
"#31": "A CHANNEL-DEFINED SOURCE BLOCK: THE CHANNEL ADJUDICATES, NOT THE PLACEMENT. Ratified 2026-08-13.\nTHE FORM: where a source list is partitioned into blocks whose OWN HEADER names the verification channel (\"Verified sources (MCP: microsoft-learn)\"), and a source's block membership conflicts with its per-source status label, the source's ACTUAL channel decides - read from its URL and compared against the channel the block header names. MOVE the source into the block its channel puts it in. Do NOT rewrite the label to match the placement.\nTHE GROUND, and it is not a preference between two defensible readings. idx-26s was deferred on the stated premise that \"neither direction is derivable from the file\". That premise was FALSIFIED by a measurement the entry never ran: the block header names a channel, and the channel is readable per source. In transparency-documentation-standards.md, 11 of the 12 Verified-block sources are learn.microsoft.com and the single exception is nr. 7 (blogs.microsoft.com, a June 2022 PDF); 0 of the 5 Baseline-block sources are learn.microsoft.com and the single exception is nr. 17 (learn.microsoft.com). The two channel outliers are EXACTLY the two status outliers. The labels agree with the channel in both cases; the placement disagrees in both. The opposite direction - rewriting the two labels to match their blocks - would AUTHOR two false claims: that a blogs.microsoft.com PDF was fetched via MCP microsoft-learn, and that a learn.microsoft.com page is mere model knowledge.\nTHE BOUNDARY, MEASURED BEFORE THE QUESTION WAS PUT. The form reaches ONLY blocks whose own header names the channel. 389 reference files swept; 31 carry both a verified-kind and a baseline-kind source block; both per-source marker dialects were run - \"(Status: X ...)\" and the bare/italic \"(X ...)\" - with block bounds tightened to the contiguous list. Exactly 3 conflicts surfaced across 2 files. One was HAND-VERIFIED AS A FALSE POSITIVE and is explicitly outside the form: language-services-question-answering.md:646 reads \"(verifisert via Microsoft Trust Center)\" under \"**Baseline (modellkunnskap):**\", naming a channel OTHER than the one that file's Verified block is defined by (\"**Verified (fra MCP microsoft-learn):**\"). Model knowledge cross-checked against a non-MCP source belongs in Baseline exactly where it sits; the word \"verifisert\" collides lexically, not semantically. THE CLASS IS THEREFORE 1 FILE / 2 INSTANCES.\nTHE INCOMPLETE LABEL VOCABULARY DOES NOT BLOCK THE FORM, and this had to be measured because the entry raised it as an obstacle. Only 14 of the 17 sources carry \"(Status: ...)\" at all - 13, 14 and 16 carry none, and 15 reads \"(Status: Adopted 2024 ...)\", outside the {Verified, Baseline} vocabulary. All four unadjudicable sources sit in the Baseline block and all four are non-learn.microsoft.com, so the channel decides precisely where the label is silent. A rule cannot be authoritative where it says nothing; the channel is not silent anywhere.\nA NET THAT FAILED FIRST, recorded because the failure is the reusable part. The first classifier read provenance tokens ANYWHERE in the header and returned MIX for \"Baseline sources (model knowledge + MCP-inferred)\", which carries BOTH \"Baseline\" and \"MCP\" - so the one file holding the known instance was silently filtered out and the sweep reported 0 conflicts over 27 candidate files. Leading-token precedence fixed it and the candidate set grew to 31. A net that cannot reproduce its own known instance is measuring nothing, and \"0 found\" from such a net reads as \"class closed\".\nGOVERNS: idx-26s.",
|
||||
"#32": "AN ENTRY'S OWN REFERENT IS A PREMISE. Ratified 2026-08-13.\nTHE FORM: where an entry justifies its class by pointing at a referent IN THE SAME FILE (\"the file contradicts itself\", \"this same file documents X\"), MEASURE THE REFERENT BEFORE ADJUDICATING THE DRIFT. If the referent does not survive measurement, the two places are not a drift and its correction - they are the SAME defect in two instances, plus a third instance nobody booked, and all of them are deleted together under one class.\nMEASURED BEFORE THE QUESTION WAS PUT (the #29 discipline). Corpus-wide, \"disclosure widget\" occurred in 1 file / 2 instances; \"generative AI toolkit\" in the same file / 1 instance. Four MCP microsoft-learn lookups, of which two are CLOSED ENUMERATIONS and therefore evidence of absence, not merely absent evidence:\n (a) authoring-system-topics enumerates ALL Copilot Studio system topics in both dialects - Web app: Conversation Start, Conversational boosting, End of Conversation, Escalate, Fallback, Multiple Topics Matched, On Error, Reset Conversation, Sign in; Teams plan: Greeting, Thank you, Goodbye, Start over, Escalate, End of Conversation, Confirmed Success, Confirmed Failure, Fallback. No \"AI disclosure\" topic exists, and the page states outright \"You can't create system topics.\" The predefined CUSTOM topics are enumerated too (greeting, ending, restarting) - also no AI disclosure.\n (b) responsible-ai-overview - THE FILE'S OWN CITED HUB - enumerates every AI-driven feature in Copilot Studio. No \"generative AI toolkit\" is among them; Learn calls the capability set \"generative AI features\" / \"AI capabilities\" throughout.\n (c) The Foundry Agent Service Transparency Note enumerates 5 knowledge tools and 10 action tools exhaustively. No embeddable disclosure widget. Learn documents in-product disclosure as a DESIGN PRACTICE with example labels (\"AI-generated content may be incorrect\" in Business Chat), never as a component you embed.\nWHAT THIS OVERTURNED. idx-27d was booked as intra-file NAME DRIFT of the idx-26d shape: line 621's \"Copilot Studio disclosure widget\" was said to drift from \"this same file's\" pre-built \"AI disclosure\" TOPIC in the generative AI toolkit. That referent - line 436 - is itself an unverified product surface, and NO entry covered it. So the class is 3 instances in 1 file, not 2, and the third is precisely the ground both entries treated as trustworthy. Name drift requires a name to drift FROM.\nTHE INHERITANCE ARGUMENT FAILED A FOURTH TIME, in a new direction: here it did not merely fail to license a repair, it concealed a defect by making one instance look like the correction of another.\nWHAT SURVIVES: the standard Copilot Studio transparency message (\"Just so you are aware, I sometimes use AI to answer your questions.\") at lines 218 and 425 is source-confirmed and untouched - it is what line 621 now names.\nCOHERENCE MEASURED, not assumed (a provably correct deletion can still leave a broken paragraph). Nothing in the file or corpus counts or cross-references these three places; the footer counts 17 URLs, not product claims. Deleting line 418 leaves a 2-bullet \"Agent transparency\" list (Trace, Log - both hold). Deleting line 436 leaves a 1-bullet \"Customization\" list (Adaptive cards). Line 621 could NOT be closed by deletion: its \"+\" conjunction binds two tools, so removing one leaves a dangling conjunction - it was REWRITTEN to name the verified message instead. Same class, three instances, three different operations.\nGOVERNS: idx-27c, idx-27d, idx-27e."
|
||||
}
|
||||
},
|
||||
"entries": [
|
||||
|
|
@ -182,25 +183,27 @@
|
|||
"id": "idx-27c",
|
||||
"file": "skills/ms-ai-governance/references/responsible-ai/transparency-documentation-standards.md",
|
||||
"class": "replacement",
|
||||
"status": "open",
|
||||
"status": "resolved",
|
||||
"raised": "2026-08-03",
|
||||
"summary": "Surfaced by the neighbourhood sweep for idx-27b and deliberately excluded from it. The Microsoft Foundry \"Agent transparency\" list asserts \"Disclosure widgets: \\\"This chatbot uses AI\\\" embeddable component\" - a named product artefact carrying a verbatim-looking user-facing string. Same class as idx-27 and idx-27b (a plausible disclosure phrasing asserted as a built-in surface), but a different platform section against a different source, so it cannot be repaired by copying the ratified Copilot Studio formulation. Needs its own live fetch against Foundry documentation to establish whether an embeddable disclosure widget exists and, if so, what string it actually carries. Repair is a replacement, outside the delete-only envelope.",
|
||||
"evidence": "docs/r11-pilot-results.md §9.10",
|
||||
"anchors": [
|
||||
"- Disclosure widgets: \"This chatbot uses AI\" embeddable component"
|
||||
]
|
||||
],
|
||||
"resolution": "Operator-ratified 2026-08-13 under form #32 (see _meta.ratified_forms). The entry asked for \"its own live fetch against Foundry documentation to establish whether an embeddable disclosure widget exists\" - it was run, and the answer is no. The Foundry Agent Service Transparency Note enumerates its 5 knowledge tools and 10 action tools exhaustively and lists no disclosure component; Learn documents in-product disclosure as a design practice with example labels, not as an embeddable artefact. The bullet was DELETED, not replaced: there is no corrected string to put in its place, because the surface itself does not exist. The remaining \"Agent transparency\" list (Trace agent actions / Log reasoning steps) was read after the edit and stands on its own. Deliberately NOT done: copying the ratified Copilot Studio formulation across, which the entry itself warned against - it belongs to a different platform and a different source."
|
||||
},
|
||||
{
|
||||
"id": "idx-27d",
|
||||
"file": "skills/ms-ai-governance/references/responsible-ai/transparency-documentation-standards.md",
|
||||
"class": "replacement",
|
||||
"status": "open",
|
||||
"status": "resolved",
|
||||
"raised": "2026-08-03",
|
||||
"summary": "Surfaced by the neighbourhood sweep for idx-27b and deliberately excluded from it. The scenario 1 tooling line names a \"Copilot Studio disclosure widget\", but this same file's Copilot Studio section documents a pre-built \"AI disclosure\" TOPIC in the generative AI toolkit - not a widget. This is intra-file name drift of the same shape as idx-26d, not a source-attribution error: the file contradicts itself about what the artefact is called. Note the context differs from idx-27/idx-27b - this line sits inside a worked scenario recommendation rather than a product-capability claim, so the repair should decide whether to name the toolkit topic or drop the artefact name, not merely restate a source. Repair is a replacement, outside the delete-only envelope.",
|
||||
"evidence": "docs/r11-pilot-results.md §9.10",
|
||||
"anchors": [
|
||||
"**Tooling:** Azure OpenAI Transparency Note + Copilot Studio disclosure widget"
|
||||
]
|
||||
],
|
||||
"resolution": "Operator-ratified 2026-08-13 under form #32. THE ENTRY'S OWN CLASSIFICATION WAS FALSE. It booked this as intra-file name drift of the idx-26d shape, on the stated premise that \"this same file's Copilot Studio section documents a pre-built 'AI disclosure' TOPIC in the generative AI toolkit - not a widget\". Measurement falsified that premise: no such topic exists (authoring-system-topics enumerates all system topics in both dialects and the page states you cannot create them), and no product called a \"generative AI toolkit\" exists (the file's own cited hub, responsible-ai-overview, enumerates every AI-driven feature). The line was therefore not drifting from a correct name - it was a third instance of the same fabricated surface, and its referent was a second. Repair could NOT be a deletion: \"**Tooling:** Azure OpenAI Transparency Note + Copilot Studio disclosure widget\" binds two tools with a \"+\", so dropping one leaves a dangling conjunction. Rewritten to \"**Tooling:** Azure OpenAI Transparency Note + Copilot Studios innebygde transparensmelding\", naming the message this same file documents at lines 218 and 425 and which is source-confirmed. The entry's suggested choice - \"whether to name the toolkit topic or drop the artefact name\" - was moot: naming the toolkit topic would have written a fourth false claim."
|
||||
},
|
||||
{
|
||||
"id": "idx-26g",
|
||||
|
|
@ -1003,6 +1006,19 @@
|
|||
"- **Word count:** ~3200 ord"
|
||||
],
|
||||
"resolution": "Operator-ratified 2026-08-13 as #30, a NEW FORM rather than an extension of #29 - the question named the widening explicitly and the alternative of leaving it to adjacency was on the ballot. DELETED at :564.\nTHE ENTRY'S OWN EVIDENCE WAS RE-MEASURED BEFORE IT WAS USED, and it was stale: this entry and STATE both said wc -w = 3374; the working tree is 3369. The cause is the resolution of idx-26av in the previous session, which deleted \"- **File size:** ~29 KB\" (five words) from this same file. The error against the claim is therefore 5.3%, not 5.2% - and the staleness is the strongest evidence for the form, not a blemish on it: the self-invalidation was demonstrated on this very line inside one day.\nTHE CLASS WAS RE-MEASURED WITH A NET THAT DOES NOT DEPEND ON THE FIELD'S NAME: every bold-label field with a numeric value across all 394 ref files, grouped by label. Still exactly one. Zero word-count fields remain corpus-wide after this edit.\nWHOLE-LINE PROOF: \"- **Word count:** ~3200 ord\" now occurs in 0 files corpus-wide; \"- **Unique sources:** 10 Microsoft Learn URLs\" occurs in exactly 1 and was re-measured TRUE (10 distinct URLs after /en-us normalisation). The label and the surviving line are byte-identical to before; the diff is one deletion and the file still ends in a newline."
|
||||
},
|
||||
{
|
||||
"id": "idx-27e",
|
||||
"file": "skills/ms-ai-governance/references/responsible-ai/transparency-documentation-standards.md",
|
||||
"class": "replacement",
|
||||
"status": "resolved",
|
||||
"raised": "2026-08-13",
|
||||
"summary": "Surfaced by MEASURING idx-27d's own referent rather than accepting it. The Copilot Studio \"Customization\" list asserted 'Copilot Studio generative AI toolkit: Pre-built \"AI disclosure\" topic'. No entry covered this line - both idx-27c and idx-27d treated it as the trustworthy ground against which the other two places drifted. It is itself an unverified product surface: Copilot Studio has no product called a \"generative AI toolkit\" (the file's own cited hub, responsible-ai-overview, enumerates every AI-driven feature and it is not among them), and no \"AI disclosure\" topic exists in the closed enumeration of system topics or predefined custom topics. This is the instance that made the class 3 rather than 2.",
|
||||
"evidence": "docs/r11-pilot-results.md §9.10 (neighbourhood of idx-27c/idx-27d); measured 2026-08-13",
|
||||
"anchors": [
|
||||
"- Copilot Studio generative AI toolkit: Pre-built \"AI disclosure\" topic"
|
||||
],
|
||||
"resolution": "Operator-ratified 2026-08-13 under form #32, in the same commit as idx-27c and idx-27d, because it is the same defect class and adjudicating it separately would have left the file asserting a surface we had just measured as nonexistent. DELETED rather than replaced - there is no corrected artefact name, and the verified Copilot Studio disclosure (the standard transparency message) is already documented at lines 218 and 425 in this same file, so restating it here would duplicate rather than repair. The remaining \"Customization\" list (Adaptive cards: Template for transparency notices) was read after the edit and stands."
|
||||
}
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -415,7 +415,6 @@ https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparen
|
|||
**Agent transparency:**
|
||||
- Trace agent actions (tool calls, data access, decisions)
|
||||
- Log reasoning steps for auditability
|
||||
- Disclosure widgets: "This chatbot uses AI" embeddable component
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -433,7 +432,6 @@ https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparen
|
|||
- Bekreftelse før dataendrende verktøy: makers *kan* kreve brukerbekreftelse før verktøy som endrer data kjøres. Kilden oppgir dette blant sikringene makeren konfigurerer **for agenter med generativ orkestrering**, og sier ikke at bekreftelse gis uten slik konfigurasjon.
|
||||
|
||||
**Customization:**
|
||||
- Copilot Studio generative AI toolkit: Pre-built "AI disclosure" topic
|
||||
- Adaptive cards: Template for transparency notices
|
||||
|
||||
**Responsible AI FAQ:**
|
||||
|
|
@ -618,7 +616,7 @@ Typisk krav i kravspesifikasjon:
|
|||
- ✅ FAQ: "Hvordan fungerer chatboten?" med link til Transparency Note
|
||||
- ❌ Ikke nødvendig: Formal Responsible AI Scorecard (ingen high-risk decision)
|
||||
|
||||
**Tooling:** Azure OpenAI Transparency Note + Copilot Studio disclosure widget
|
||||
**Tooling:** Azure OpenAI Transparency Note + Copilot Studios innebygde transparensmelding
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue