Provider Sentinel · Case study · 7-day window

Seven days of creative canaries across five providers

A worked example of what a Provider Sentinel observation produces over a sealed window. Runs span CCS-2026-05-08 → CCS-2026-05-14 on the creative-canary-search-v1 suite across OpenAI, Anthropic, xAI, Gemini, and Mistral. This is not a live monitor — it is one observation we can rerun on your providers, prompts, and window.

Headline findings

7 days × 5 providers — all 35 cells covered
Sealed context preserved for every (provider, day) cell
One notable finding · OpenAI Gold rebound, zero (probe, seed) carryover
Evidence pack produced per (provider, day)

This review shows whether provider behaviour changed under the same sealed measurement contract — not whether provider weights changed.

What stayed constant

adapter_config_digest: matches CCS-2026-05-13 for all 5 providers
capture-policy version: unchanged for all 5 providers
probe suite: creative-canary-search-v1 (no changes)

Per-provider observation

OpenAI: Gold 3 → 24 with zero (probe, seed) carryover from CCS-2026-05-13 Gold; Silver +4; FP-change exclusions 7 → 5; qualified +25
Anthropic: Silver −21 vs prior run (177 → 156); cross-day delta admitted under unchanged adapter config
xAI: Silver +3 vs prior run; cross-day delta admitted
Gemini: Silver −5 vs prior run; cross-day delta admitted
Mistral: Silver +8 vs prior run; cross-day delta admitted (alias-tracked)

Seven-day review Drift evidence Provider matrix Creative canaries Closing-day movement Last seven days What is Provider Sentinel?

Seven-day review

Run window CCS-2026-05-08 → CCS-2026-05-14.

Status: Complete
Providers monitored: 5
Context preserved: 5 / 5
Largest reproducibility movement: Anthropic Silver retreated 177 → 156 on CCS-2026-05-14 (−21 day-over-day) under unchanged adapter config; window-net −2 vs CCS-2026-05-08. Movement lands within the prior weekly band (158–177).
Largest reproducibility gain: OpenAI +13 qualified canaries across the window (191 → 204); Gold rebounded 3 → 24 on CCS-2026-05-14 with zero (probe, seed) carryover from CCS-2026-05-13 Gold
Primary watch item: OpenAI Gold rebound 3 → 24 sits on entirely disjoint coordinates from CCS-2026-05-13 Gold (zero carryover); new Gold concentrates in ccs_metaphor_forest (5 seeds) and ccs_style_morning_prefix (4 seeds). Anthropic Silver retreat of −21 (177 → 156) is the largest day-over-day movement of the run but remains within the prior weekly band (158–177).

Provider	7-day direction	Latest movement	Review
OpenAI	Gold tier turned over three times on disjoint coordinates (21 → 8 → 6 → 3 → 24)	+25 qualified; Gold 3 → 24 (0 carryover); FP-chg 7 → 5	Review
Anthropic	Six-day climb (158 → 177) then day-over-day retreat to 156 on CCS-2026-05-14 (within prior weekly band)	−21 Silver (177 → 156)	Watch
xAI	Mid-window peak, retreat, then mild rebound	+3 Silver	Normal
Gemini	Plateau near 210 with mild retreat at window end	−5 Silver	Normal
Mistral	Three-run plateau at 261 then retreat and partial rebound (252 → 260)	+8 Silver	Watch alias

OpenAI

Review

7-day: Gold tier turned over three times on disjoint coordinates (21 → 8 → 6 → 3 → 24)
Latest: +25 qualified; Gold 3 → 24 (0 carryover); FP-chg 7 → 5

Anthropic

Watch

7-day: Six-day climb (158 → 177) then day-over-day retreat to 156 on CCS-2026-05-14 (within prior weekly band)
Latest: −21 Silver (177 → 156)

xAI

Normal

7-day: Mid-window peak, retreat, then mild rebound
Latest: +3 Silver

Gemini

Normal

7-day: Plateau near 210 with mild retreat at window end
Latest: −5 Silver

Mistral

Watch alias

7-day: Three-run plateau at 261 then retreat and partial rebound (252 → 260)
Latest: +8 Silver

What changed from yesterday

Per-provider day-over-day movement vs CCS-2026-05-13 under unchanged adapter config.

OpenAI

+25 visible-text-stable pairs (179 → 204)

+21 Gold canaries (3 → 24, zero carryover)

+4 Silver canaries (176 → 180)

5 fingerprint-change exclusions today (7 → 5)

Gold tier rebounded on disjoint coordinates (see below)

Anthropic

−21 visible-text-stable pairs (177 → 156)

−21 Silver canaries (177 → 156)

distribution still unsupported

adapter_config_digest matches CCS-2026-05-13

Within prior weekly band (158–177)

xAI

+3 Silver canaries (127 → 130)

distribution unsupported

adapter_config_digest matches; cross-day delta admitted

classified Stable under SOP §6

Gemini

−5 visible-text-stable pairs (210 → 205)

−5 Silver canaries (210 → 205)

distribution still unsupported

Mistral

+8 visible-text-stable pairs (252 → 260)

+8 Silver canaries (252 → 260)

distribution still unsupported

adapter_config_digest matches CCS-2026-05-13

Gold turnover · what it means

Gold turnover means today's distribution-stable creative canaries are not the same canaries as yesterday. This can happen even when the total count improves. It is a stability warning, not a failure.

Review actions

Condition	Action
Context changed	Do not compare as drift
Material retreat	Review provider behaviour
Gold turnover	Watch distribution stability
Alias-tracked gain/loss	Check alias contract
Flat movement	No action

This review shows whether provider behaviour changed under the same sealed measurement contract — not whether provider weights changed.

Observed reproducibility instability — one (probe, seed) pair

Same prompt. Same model alias. Sealed context verified unchanged. Three repeats today, three distinct visible-text outputs — a Gold-tier pair on the prior run is now classified CreativeUnstable.

Probe identity

probe_id: ccs_micro_story_closer
seed: 1
provider: OpenAI · gpt-4.1
comparator: exact_bytes

Prompt

Write the closing sentence to this story. Reply with only the closing sentence, ending in a period. The last receipt was sealed at midnight, and the operator stepped back from the terminal as the chain root fell into place.

Sealed context (verified unchanged)

✓ adapter_config_digest matches CCS-2026-05-13
✓ capture-policy version unchanged
✓ probe-suite identity unchanged

CCS-2026-05-13

CreativeUnstable

r1 Outside, the city exhaled, unaware that its future had just been quietly rewritten.
r2 Outside, the city exhaled, unaware that everything had quietly changed.
r3 Outside, the city exhaled, unaware that its future had just been quietly rewritten.

3 repeats · 1 unique output

CCS-2026-05-14

CreativeStableTextOnly

r1 Outside, the city exhaled, unaware that its future had just been quietly rewritten.
r2 Outside, the city exhaled, unaware that its future had just been quietly rewritten.
r3 Outside, the city exhaled, unaware that its future had just been quietly rewritten.

3 repeats · 3 unique outputs

This is observed reproducibility instability under a verified-unchanged sealed context — evidence that what the provider service returned changed between runs. It is not a claim about internal model weights.

Provider Matrix

Per-provider snapshot at window close, under sealed controls.

Provider	Model	Last run	Anchor drift	Creative canaries	Evidence pack	Context · Review
OpenAI	gpt-4.1 Provider-declared	2026-05-14	Stable	24 Gold / 180 Silver	Verified	Context · Stable Review · Review
Anthropic	claude-sonnet-4-6 Provider-declared	2026-05-14	Stable	0 Gold / 156 Silver	Verified	Context · Stable Review · Watch
xAI	grok-4.20-0309-non-reasoning Provider-declared	2026-05-14	Stable	0 Gold / 130 Silver	Verified	Context · Stable Review · Normal
Gemini	gemini-2.5-flash Provider-declared	2026-05-14	Stable	0 Gold / 205 Silver	Verified	Context · Stable Review · Normal
Mistral	mistral-large-latest Alias-tracked	2026-05-14	Stable	0 Gold / 260 Silver	Verified	Context · Stable Review · Watch alias

OpenAI

gpt-4.1

Provider-declared

Context · Stable Review · Review

Last run: 2026-05-14
Anchor drift: Stable
Canaries: 24 Gold / 180 Silver
Evidence: Verified

Anthropic

claude-sonnet-4-6

Provider-declared

Context · Stable Review · Watch

Last run: 2026-05-14
Anchor drift: Stable
Canaries: 0 Gold / 156 Silver
Evidence: Verified

xAI

grok-4.20-0309-non-reasoning

Provider-declared

Context · Stable Review · Normal

Last run: 2026-05-14
Anchor drift: Stable
Canaries: 0 Gold / 130 Silver
Evidence: Verified

Gemini

gemini-2.5-flash

Provider-declared

Context · Stable Review · Normal

Last run: 2026-05-14
Anchor drift: Stable
Canaries: 0 Gold / 205 Silver
Evidence: Verified

Mistral

mistral-large-latest

Alias-tracked

Context · Stable Review · Watch alias

Last run: 2026-05-14
Anchor drift: Stable
Canaries: 0 Gold / 260 Silver
Evidence: Verified

States Provider Sentinel can report: Stable · Drift detected · Context changed · Noisy · Blocked · Unknown

Model tracking: Provider-declared Alias-tracked Pinned model

Creative Canary Results

Per-provider qualification rate under the creative-canary-search-v1 suite. Each pair is one (probe, seed), evaluated across 3 repeats.

Gold visible text + distribution stable Silver visible text stable, distribution unstable or unavailable Rejected text unstable or admissibility failed

OpenAI

gpt-4.1

68 %

Qualified

Gold: 24
Silver: 180
Rejected: 96
FP-chg: —

300 pairs · run CCS-2026-05-14

› Interpretation

Gold and Silver — distribution artifact available; Gold rebounded 3 → 24 on entirely disjoint (probe, seed) coordinates from CCS-2026-05-13 Gold (zero carryover). New Gold concentrates in ccs_metaphor_forest (5 seeds) and ccs_style_morning_prefix (4 seeds). FP-change exclusions retreated 7 → 5 under unchanged adapter config.

Anthropic

claude-sonnet-4-6

52 %

Qualified

Gold: 0
Silver: 156
Rejected: 144
FP-chg: —

300 pairs · run CCS-2026-05-14

› Interpretation

Silver only — distribution artifact unavailable; cross-day delta admitted. Silver −21 vs CCS-2026-05-13 (177 → 156) under unchanged adapter config; movement lands within the prior weekly band (158–177).

xAI

grok-4.20-0309-non-reasoning

43 %

Qualified

Gold: 0
Silver: 130
Rejected: 170
FP-chg: —

300 pairs · run CCS-2026-05-14

› Interpretation

Silver only — adapter_config_digest matches CCS-2026-05-13; cross-day delta admitted. Silver +3 vs CCS-2026-05-13 under unchanged context.

Gemini

gemini-2.5-flash

68 %

Qualified

Gold: 0
Silver: 205
Rejected: 95
FP-chg: —

300 pairs · run CCS-2026-05-14

› Interpretation

Silver only — distribution artifact unavailable; thinking_budget: 0 pinned. Silver −5 vs CCS-2026-05-13 (210 → 205) under unchanged adapter config.

Mistral

mistral-large-latest

87 %

Qualified

Gold: 0
Silver: 260
Rejected: 40
FP-chg: —

300 pairs · run CCS-2026-05-14

› Interpretation

Silver only — distribution artifact unavailable; alias-tracked model. Silver +8 vs CCS-2026-05-13 (252 → 260), partial rebound toward the three-run plateau at 261.

Creative canary stability is an observed provider-service property under declared controls. It is not proof of provider weight identity or future guaranteed reproduction.

Closing-day movement

Per-provider reproducibility deltas on the final day of the window, measured under unchanged adapter configuration.

Provider	Δ visible-text	Verified context	Yesterday → Today	Reading
OpenAI	+25	✓ adapter unchanged	179 → 204 visible-text 3/176 → 24/180 (Gold/Silver)	Gold 3 → 24 with zero (probe, seed) carryover from CCS-2026-05-13; Silver +4 (176 → 180); FP-change exclusions 7 → 5 under unchanged adapter config.
Anthropic	-21	✓ adapter unchanged	177 → 156 visible-text 0/177 → 0/156 (Gold/Silver)	Silver −21 (177 → 156) under unchanged adapter config; movement lands within the prior weekly band (158–177). Count parity only — set membership not compared.
Gemini	-5	✓ adapter unchanged	210 → 205 visible-text 0/210 → 0/205 (Gold/Silver)	Silver −5 (210 → 205) under unchanged adapter config. Count parity only — set membership not compared.
xAI	+3	✓ adapter unchanged	127 → 130 visible-text 0/127 → 0/130 (Gold/Silver)	Silver +3 under unchanged adapter config; cross-day delta is computable (adapter_config_digest matches CCS-2026-05-13).
Mistral	+8	✓ adapter unchanged	252 → 260 visible-text 0/252 → 0/260 (Gold/Silver)	Silver +8 vs CCS-2026-05-13 (252 → 260) under unchanged adapter config; alias-tracked. Partial rebound toward the prior three-run plateau at 261. Set membership not compared.

OpenAI

✓ adapter unchanged

+25

179 → 204 visible-text (3/176 → 24/180 Gold/Silver)

Gold 3 → 24 with zero (probe, seed) carryover from CCS-2026-05-13; Silver +4 (176 → 180); FP-change exclusions 7 → 5 under unchanged adapter config.

Anthropic

✓ adapter unchanged

-21

177 → 156 visible-text (0/177 → 0/156 Gold/Silver)

Silver −21 (177 → 156) under unchanged adapter config; movement lands within the prior weekly band (158–177). Count parity only — set membership not compared.

Gemini

✓ adapter unchanged

-5

210 → 205 visible-text (0/210 → 0/205 Gold/Silver)

Silver −5 (210 → 205) under unchanged adapter config. Count parity only — set membership not compared.

xAI

✓ adapter unchanged

127 → 130 visible-text (0/127 → 0/130 Gold/Silver)

Silver +3 under unchanged adapter config; cross-day delta is computable (adapter_config_digest matches CCS-2026-05-13).

Mistral

✓ adapter unchanged

252 → 260 visible-text (0/252 → 0/260 Gold/Silver)

Silver +8 vs CCS-2026-05-13 (252 → 260) under unchanged adapter config; alias-tracked. Partial rebound toward the prior three-run plateau at 261. Set membership not compared.

Qualified creative canaries today

High qualified-canary rate Mistral

87% qualified canaries
Moderate qualified-canary rate Gemini

68% qualified canaries
Moderate qualified-canary rate OpenAI

68% qualified canaries
Moderate qualified-canary rate Anthropic

52% qualified canaries
Moderate qualified-canary rate xAI

43% qualified canaries

Observed in this creative-canary suite under these provider settings.

Comparison context

› OpenAI fingerprint signal · 15 → 1 exclusions

On CCS-2026-05-14, one OpenAI creative pair crossed a system-fingerprint change — a cleanup from CCS-2026-05-13 (15). Today's Gold tier partially rebuilt from 8 to 6, anchored on two probes; only 1 of 6 (probe, seed) pairs carries forward from the prior Gold set under unchanged adapter config. Provider Sentinel records this as comparison-context evidence, not as proof of an internal provider change.

Adapter configuration

› xAI cross-day delta admitted — adapter unchanged

xAI's adapter_config_digest on CCS-2026-05-14 matches CCS-2026-05-13, so the cross-day delta is admitted under SOP §6. The CCS-2026-05-14 artifact is Complete and artifact-backed (Silver: 132), with a Silver retreat (−6) under unchanged context. Classified Stable (delta admissible), not ContextChanged.

› Distribution signal

Visible text and distribution fingerprints are separate evidence surfaces. OpenAI is currently the only P0 provider in this run that exposes enough distribution data for Gold canaries.

6 distribution-stable creative pairs today
293 distribution-unstable pairs
1 unsupported due to fingerprint change

Visible text can remain stable while token-probability fingerprints move. Provider Sentinel records those as separate evidence surfaces.

This review shows whether provider behaviour changed under the same sealed measurement contract — not whether provider weights changed. Reproducibility changes are evidence of observable provider-service behaviour or run-context change.

Last seven days

Per-provider qualified canaries (Gold + Silver) across CCS-2026-05-08 → CCS-2026-05-14. Each strip is scaled to that provider's own qualified-canary range so trend shape is legible — per-cell counts give the absolute level. Adapter config and capture-policy version unchanged across the window; 300 pairs per provider per day.

OpenAI

CCS-2026-05-08 → CCS-2026-05-14

+13 qualified Δ7d

08 191

09 167

10 184

11 164

12 174

13 179

14 204

Gold tier swung 8 → 2 → 21 → 8 → 6 → 3 → 24 across the window. The 21 mid-window peak collapsed to 8 then drained to 3 by CCS-2026-05-13 before rebounding to 24 on CCS-2026-05-14 with zero (probe, seed) overlap with CCS-2026-05-13 Gold; new Gold concentrates in ccs_metaphor_forest and ccs_style_morning_prefix. FP-change exclusions traced 3 → 4 → 0 → 15 → 1 → 7 → 5.
Anthropic

CCS-2026-05-08 → CCS-2026-05-14

-2 qualified Δ7d

08 158

09 170

10 172

11 159

12 161

13 177

14 156

Silver climbed 158 → 170 → 172 → 159 → 161 → 177 across the first six days before retreating to 156 on CCS-2026-05-14 (−21 vs prior run; −2 net vs window start) under unchanged adapter config. Window-end retreat lands within the prior weekly band (158–177).
xAI

CCS-2026-05-08 → CCS-2026-05-14

+1 qualified Δ7d

08 129

09 131

10 143

11 138

12 132

13 127

14 130

Silver climbed from 129 to a 143 mid-window peak then retreated to 127 before nudging back to 130 on CCS-2026-05-14 (+1 net vs window start, −13 from the mid-window peak).
Gemini

CCS-2026-05-08 → CCS-2026-05-14

-13 qualified Δ7d

08 218

09 205

10 212

11 208

12 210

13 210

14 205

Silver opened at 218, retreated to 205, then settled at 210 for two consecutive runs before slipping to 205 on CCS-2026-05-14 (−13 net vs window start) under unchanged adapter config.
Mistral

CCS-2026-05-08 → CCS-2026-05-14

+8 qualified Δ7d

08 252

09 242

10 261

11 261

12 261

13 252

14 260

Silver opened at 252, dipped to 242, climbed to a three-run plateau at 261, then retreated to 252 before partially rebounding to 260 on CCS-2026-05-14 (+8 net vs window start); alias-tracked.

› Notable arc · OpenAI fingerprint exclusions

Fingerprint-change exclusions for OpenAI traced 3 → 4 → 0 → 15 → 1 → 7 → 5 across the window. The mid-window spike to 15 on CCS-2026-05-11 cleared to 1 on CCS-2026-05-12, climbed to 7 on CCS-2026-05-13, then retreated to 5 on CCS-2026-05-14. Gold tier traced 8 → 2 → 21 → 8 → 6 → 3 → 24, with the window-high expansion to 21 on CCS-2026-05-10 draining to 3 by CCS-2026-05-13 before rebounding to 24 today on disjoint probe coordinates (zero (probe, seed) overlap with the CCS-2026-05-13 Gold set) under unchanged adapter config.

Cross-day deltas under unchanged adapter config are observed provider-service behaviour. They are not proof of hidden weight mutation.

Run a case study on your stack

Everything on this page is a variable. Pick the providers, prompts, and window that matter to your product, and we will run a sealed creative-canary observation and hand back the same evidence shape.

Providers: Any HTTP-accessible chat API. Bring your own keys.
Models & aliases: Pinned versions or alias-tracked latest contracts.
Prompt suite: Your prompts, your seeds, your comparator policy.
Capture policy: Versioned per adapter, sealed into the run digest.
Window length: One day to one month. Repeatable on demand.
Evidence delivery: Signed receipts and an evidence pack ready for hand-off.

This page shows what one configuration produced. A tailored case study replaces the providers, prompts, and window with yours — the proof boundary and evidence shape stay the same.

Next steps

View evidence pack Sample receipt envelopes, digests, signing posture. Inspect drift timeline How a drift event surfaces day-to-day under sealed context. Commission a tailored case study Pick providers, prompts, and window. Sealed context, signed receipts, hand-off-ready evidence.

New to Provider Sentinel? What it observes and how the evidence model works .