← petro-agent · field report · catálogoclaude-fable-5 · summit v3 · class B

Petrophysical Interpretation Report — 15-135-20280


Well (UWI)	15-135-20280
Log date	08/24/69
Acquisition date (header)	8/24/69
BHT (measured)	114 DEGF
Mud resistivity (RM)	0.11 OHMM
Mud filtrate (RMF)	0.08 OHMM
PLSS location	Sec 18 T20S R21W (map precision ±1.6 km)
Larionov variant	old_rocks (degraded)
Convergence status	DID_NOT_CONVERGE
Confidence tier	○ BRACKETED
Engine versions	calc_vsh 0.1.0 · calc_phie 0.1.0 · calc_sw 0.1.0 · formula_registry 0.1.0
Config hash (SHA-256)	`2a9cb78728e386ab…`
Git SHA	`bd23bea18153`
Generated	autonomously, no human in the per-report loop

Confidence legend. Each result is tagged by parameter provenance: ● FIRM (core-calibrated) · ◐ QUALIFIED (offset-derived) · ○ BRACKETED (regional/global default — read as a range, dominant uncertainty stated). The system does not claim *always correct*; it states how well-supported each number is.

1. Executive summary

⚠️ ABSTENTION — this is NOT a confident estimate. The run did not converge to a defensible result; the numbers below are an uncalibrated engineering estimate, reported for transparency only:
- 1 unresolved MECHANICAL objection(s)

The vintage log covers only the deep consolidated section, so the full logged interval is evaluated — there is no overburden on record to exclude. Within that interval the net pay is 6.2 m with average effective porosity 0.133 and average water saturation 0.342. Monte-Carlo places the P50 net pay at 4.6 m within a P10-P90 range of 2.1 to 11.1 m. CLASS-B VINTAGE WELL: porosity comes from a count-rate neutron transform (engine-anchored, validated against sonic on offset wells; structural approximation) — every number is bracketed and must be read as a range. The run ABSTAINS from a confident estimate: the validators keep an unresolved objection, so the result must be read as a bracketed range, not a point value.

Net pay P10 / P50 / P90 = 2.1 / 4.6 / 11.1 m.
Net pay is dominated by 'm', which is a regional DEFAULT (uncalibrated). This is the single largest uncertainty — the result is bracketed, not a confident point estimate.

2. Data inventory (from LAS)

Curves present (canonical ← raw): GR←GR, NEUT←NEUT, RT←RES
Logged interval: 1127.46–1360.32 m
Log date: 08/24/69
Service company: — · Company: PICKRELL DRILLING CO.
Field: SOUTH SCHABEN
Not provided by LAS (out of scope): core, mud logs, pressure tests, production, completion, formation tops.

3. LAS quality control

Edit type	Curve	Detail
range_warn	GR	count 22
spike_removal	—	—
degradation	—	—

4. Standardization

Raw mnemonics mapped to canonical curve names:

Canonical	Raw mnemonic
GR	GR
NEUT	NEUT
RT	RES

5. Per-curve log QC

GR baseline: gr_p5=11.8, gr_p95=179.7
Bad-hole: GOOD=0.993, DEGRADED=0.001, EXCLUDED=0.007
Low-resistivity: rt_threshold=4.14, n_flagged=152, intervals=[[1127.8, 1128.1], [1128.8, 1132.2], [1132.5, 1132.9], [1140.0, 1140.7], [1141.2, 1142.4], [1142.8, 1144.5], [1146.8, 1146.8], [1149.2, 1150.3], [1150.8, 1151.2], [1153.4, 1153.7]]

6. Data preparation

Edits applied before compute (by type): degradation: 1, range_warn: 1, spike_removal: 1.

7. Interval definition

Logged interval: 1127.46–1360.32 m
Gross evaluated interval: 232.9 m
Computed net-pay runs (pre-merge): 11
Zonation is computed by depth (no formation tops in LAS).

8. Methodology

All numbers are produced by the deterministic, golden-tested engine. The LLM only selects methods/parameters and writes prose — it never computes a number. Figures are deterministic renderings of these computed numbers for the human reader; the agent reasons over the numeric EDA digest, not images (the models have no vision).

Step	Method (frozen)	Version
Vsh	Larionov 1969 (old rocks)	`vsh_larionov_old 0.1.0`
PHIE	Vintage count-rate neutron, two-point semilog (class-B, engine-anchored)	`phi_neutron_countrate 0.1.0`
Sw	Archie 1942	`sw_archie 0.1.0`
Net pay	Vsh/PHIE/Sw cutoffs → net sand → net reservoir → net pay	`netpay 0.1.0`
Uncertainty	Monte Carlo P10/P50/P90 + parameter sensitivity	`mc 0.1.0`

9. Gamma-ray analysis

Clean baseline gr_min = 20.0 API · shale gr_max = 120.0 API
Shale index IGR = (GR − gr_min)/(gr_max − gr_min), the basis for Vsh.
GR baseline check: gr_p5=11.8, gr_p95=179.7

10. Resistivity analysis

Low-resistivity scan: rt_threshold=4.14, n_flagged=152, intervals=[[1127.8, 1128.1], [1128.8, 1132.2], [1132.5, 1132.9], [1140.0, 1140.7], [1141.2, 1142.4], [1142.8, 1144.5], [1146.8, 1146.8], [1149.2, 1150.3], [1150.8, 1151.2], [1153.4, 1153.7]].

11. Water resistivity (Rw)

Rw = 0.0400 ohm-m · provenance: default
Sourced by the engine (Pickett / SP / default); never authored by the LLM.
Net-pay sensitivity to Rw: 7.2 m swing.
Formation-temperature correction (Arps, gradient from the MEASURED header BHT): Rw ≈ 0.0268 ohm-m at 44.1 °C (evidence only — Sw uses the calibrated Rw).

12. Figures

Composite log

Composite log

Pickett plot

Pickett plot

Buckles plot

Buckles plot

Hingle plot

Hingle plot

Distributions

Distributions

Sensitivity tornado

Sensitivity tornado

Net-pay Monte-Carlo distribution

Net-pay Monte-Carlo distribution

13. Shale volume (Vsh)

Mean Vsh by method (selection is the agent's; the LLM authors no number):

Method	Mean Vsh	Selected
vsh_larionov_old	0.408	✓
vsh_larionov_tertiary	0.365
vsh_linear	0.479
vsh_clavier	0.401
vsh_steiber	0.379

14. Porosity

_Not computed — no RHOB/NPHI curve for the comparison._

15. Water saturation

Mean Sw (Archie 1942) = 0.724 (a=1.00, m=2.00, n=2.00, Rw=0.0349 ohm-m). Electrical parameters are engine-sourced; alternative Sw models are optional sections.

Mean Sw by method (engine-computed comparison; the LLM authors no number):

Method	Mean Sw	Selected
sw_archie	0.724	✓
sw_simandoux	0.441
sw_indonesia	0.514

16. Zonation (net-pay intervals)

Raw net-pay runs merged into 10 geological intervals (gap tolerance 1.5 m).

Interval	Top (m)	Base (m)	Net pay (m)	Avg PHIE	Avg Sw	Avg Vsh
Z1	1128.4	1128.5	0.3	0.170	0.478	0.155
Z2	1166.9	1167.4	0.6	0.129	0.284	0.027
Z3	1193.4	1193.4	0.2	0.101	0.296	0.153
Z4	1222.2	1222.2	0.2	0.118	0.468	0.075
Z5	1230.3	1231.8	1.7	0.157	0.232	0.050
Z6	1274.5	1274.5	0.2	0.104	0.490	0.282
Z7	1310.6	1310.6	0.2	0.115	0.441	0.341
Z8	1344.0	1346.0	2.1	0.113	0.357	0.237
Z9	1348.4	1350.1	0.6	0.150	0.434	0.035
Z10	1352.7	1352.9	0.3	0.123	0.480	0.012

17. Results

Quantity	Value
Gross interval	232.9 m
Net pay (P10/P50/P90)	2.1 / 4.6 / 11.1 m
Net-to-gross	0.027
Avg PHIE (net pay)	0.133
Avg Sw (net pay)	0.342
Avg Vsh (net pay)	0.129

18. Uncertainty and sensitivity

Monte Carlo, 500 realizations (seed 42). Net pay swing per parameter (one-at-a-time):

Parameter	Net-pay swing (m)
m	7.9
Rw	7.2
a	4.6
n	1.2

Dominant uncertainty: m (swing 7.9 m).

Multi-seed robustness: P50 UNSTABLE across seeds (spread 0.7 m across 4 seeds).

Net pay is dominated by 'm', which is a regional DEFAULT (uncalibrated). This is the single largest uncertainty — the result is bracketed, not a confident point estimate.

19. Derived parameters

Bulk-volume water (BVW = PHIE*Sw): mean 0.0532 v/v
Porosity-thickness (Phi·H over net pay): 0.832 m
Hydrocarbon pore thickness (HCPV = Σ PHIE·(1−Sw)·step): 0.554 m
Buckles constant (BVW at P10 of net pay): 0.0296 → Swirr (mean) ≈ 0.223 over 41 pay samples

20. Parameters and provenance

Parameter	Value	Unit	Provenance	Source
gr_min	20.000	API	default	—
gr_max	120.000	API	default	—
rho_ma	2.710	g/cc	default	Schlumberger 1989
rho_fl	1.000	g/cc	default	—
phie_max	0.450	v/v	default	—
phi_sh_d	0.100	v/v	default	—
phi_sh_n	0.350	v/v	default	—
a	1.000	-	default	Winsauer et al. 1952
m	2.000	-	default	Archie, G.E. 1942
n	2.000	-	default	Archie, G.E. 1942
Rw	0.040	ohm-m	default	Kansas Geological Survey 2000
rt_hydrocarbon_floor	5.000	ohm-m	default	—
vsh_cutoff	0.350	v/v	default	—
phie_cutoff	0.100	v/v	default	—
sw_cutoff	0.500	v/v	default	—
bit_size_config	7.875	in	default	—
qc_abort_threshold	0.800	-	default	—
circuit_breaker_n	3.000	-	default	—

The citations table (not RAG) gives each cited parameter exactly one frozen source. Parameters tagged default are regional/global — they drive the bracketed tier.

21. Petrophysical cutoffs

Boundary-inclusive criteria applied by the engine (netpay) to flag reservoir:

Stage	Criterion	Cutoff	Provenance
Net sand	Vsh ≤ cutoff	0.350	default
Net reservoir	+ PHIE ≥ cutoff	0.100	default
Net pay	+ Sw ≤ cutoff	0.500	default

Cutoff values are engine parameters (never LLM-authored); the dominant net-pay uncertainty is m — see Uncertainty for the swing.

22. Data quality and validator objections

Curve provenance (canonical ← raw mnemonic): GR←GR, NEUT←NEUT, RT←RES.

QC edits applied before compute — degradation: 1, range_warn: 1, spike_removal: 1.

Validator	Type	Detail
vsh_phie_anticorrelation	support	Vsh-PHIE Pearson 0.98 > 0.3 (dirty rock + high porosity)
rt_sw_consistency	mechanical	58 depths with Sw<0.4 but RT<5.0 ohm-m

23. Methodology (decision graph)

flowchart TD
    dec_1["decision: step: compare_methods"]
    act_1["tool_call: compare_methods"]
    dec_2["decision: step: compute_vsh"]
    act_2["tool_call: compute_vsh"]
    dec_3["decision: step: compute_phie"]
    act_3["tool_call: compute_phie"]
    dec_4["decision: step: compare_methods"]
    act_4["tool_call: compare_methods"]
    dec_5["decision: step: compute_sw"]
    act_5["tool_call: compute_sw"]
    dec_6["decision: step: apply_cutoffs"]
    act_6["tool_call: apply_cutoffs"]
    dec_7["decision: step: run_uncertainty"]
    act_7["tool_call: run_uncertainty"]
    dec_8["decision: step: derived_parameters"]
    act_8["tool_call: derived_parameters"]

24. Data gaps for calibration

This is a LAS-only study. Data that would calibrate the interpretation is absent:

Core (routine + SCAL): would anchor PHIE and Archie m, n, a.
Pressure tests (RFT/MDT): would give true fluid contacts and gradients (log-based).
Production/flow data: would test the net-pay flag against deliverability.
Dominant net-pay uncertainty driver (from the sensitivity): m (calibrated by core SCAL — cementation exponent m).
Standard curves absent: RHOB, NPHI, SP, DT, PEF, CALI, DCAL.

25. Limitations

LAS-only study: no core calibration, no pressure tests (no true fluid contacts), no production, no mud logs, no formation tops (zonation computed by depth).
Standard curves absent in this well: RHOB, NPHI, SP, DT, PEF, CALI, DCAL.
Results are uncalibrated; accuracy depends on data not provided.

26. Conclusions

Vintage class-B well: logged interval covers only the deep consolidated section (no overburden recorded), GR-only clay indicator, count-rate porosity with engine anchors, Archie saturation. Structural-uncertainty caveat applies to every number. Method choices were made against the engine's numeric comparisons, not by preference; the comparison tables show the rejected alternatives beside the selected method. All numbers in this report come from the deterministic engine; the analyst chose the interval, the methods and the analyses, and wrote this prose — nothing more. Remaining uncertainty is dominated by the uncalibrated regional parameters.

Appendix A — Ledger excerpt (traceability)

{
  "net_pay_total_m": 6.248399999997673,
  "net_pay_p10_p50_p90": [
    2.1335999999992055,
    4.571999999998297,
    11.125199999995857
  ],
  "driving_params": {
    "a": 1.0,
    "m": 2.0,
    "n": 2.0,
    "Rw": 0.04
  },
  "claim_verifier": {
    "result": "PASS",
    "flags": [],
    "tone_flags": []
  }
}

Appendix B — Completeness gate

Item	Present
QC edits recorded before compute	✓
Every number ledger-traced	✓
Confidence tier on the run	✓
Parameter citations frozen	✓
Validator objections listed, not hidden	✓
Uncertainty propagated (Monte Carlo)	✓
Claim verifier run on prose	✓