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

Petrophysical Interpretation Report — 15-135-25,602-00-00


Well (UWI)	15-135-25,602-00-00
Log date	Sat Jun 29 21-09-17 2013
Acquisition date (header)	Sat Jun 29 21-09-17 2013
PLSS location	Sec 24 T19S R22W (map precision ±1.6 km)
Larionov variant	old_rocks (degraded)
Convergence status	CONVERGED
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.

⚠️ claim verifier FLAGS: 4 number(s) not traceable to the ledger

1. Executive summary

The evaluation is restricted to the consolidated section between 1100.0 m and 1327.6 m — the interval above it is not evaluated (unconsolidated, washed-out response). Within that interval the net pay is 0.0 m with average effective porosity nan and average water saturation nan. Monte-Carlo places the P50 net pay at 0.0 m within a P10-P90 range of 0.0 to 0.0 m. An independent SP-derived water resistivity of 0.0450 ohm-m (static SP -57.0 mV; offset-median mud-filtrate resistivity 0.110 ohm-m — a declared cross-well assumption) supports the regional default, and the Monte-Carlo Rw range is narrowed to the field SP band with recorded provenance. The Rxo/Rt movable-hydrocarbon index reads a median of 0.839 over 1461 samples — an invasion-based indicator profile, not a saturation. Parameters carry regional-default provenance, so the estimate remains a bracketed range with declared uncertainty, not a certainty.

Net pay P10 / P50 / P90 = 0.0 / 0.0 / 0.0 m.
Net pay is dominated by 'Rw', 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): DCAL←DCAL, DRHO←RHOC, GR←GR, NPHI←CNLS, PHID_SVC←DPOR, RHOB←RHOB, RMED←RILM, RT←RILD, RXO←RLL3, SP←SP
Logged interval: 59.44–1327.56 m
Log date: Sat Jun 29 21-09-17 2013
Service company: — · Company: American Warrior, Inc.
Field: Schaben North
Not provided by LAS (out of scope): core, mud logs, pressure tests, production, completion, formation tops.

3. LAS quality control

Edit type	Curve	Detail
unit_conversion	NPHI	factor 0.01
hard_range_mask	RT	count 136
hard_range_mask	RMED	count 69
hard_range_mask	RXO	count 1
hard_range_mask	RHOB	count 1
range_warn	NPHI	count 4
spike_removal	—	122 edits
degradation	—	—

4. Standardization

Raw mnemonics mapped to canonical curve names:

Canonical	Raw mnemonic
DCAL	DCAL
DRHO	RHOC
GR	GR
NPHI	CNLS
PHID_SVC	DPOR
RHOB	RHOB
RMED	RILM
RT	RILD
RXO	RLL3
SP	SP

Unit conversions: NPHI×0.01.

5. Per-curve log QC

GR baseline: gr_p5=32.0, gr_p95=110.3
Bad-hole: GOOD=0.399, DEGRADED=0.569, EXCLUDED=0.032
Low-resistivity: rt_threshold=1.32, n_flagged=807, intervals=[[104.5, 105.0], [111.9, 112.3], [116.3, 116.9], [124.7, 125.4], [200.3, 201.9], [217.8, 218.8], [225.9, 227.4], [258.5, 258.8], [271.3, 273.3], [275.1, 281.2]]

6. Data preparation

Edits applied before compute (by type): degradation: 1, hard_range_mask: 4, range_warn: 1, spike_removal: 122, unit_conversion: 1.

7. Interval definition

Logged interval: 59.44–1327.56 m
Analysis window (analyst-restricted): 1100.0–1327.6 m — gross and NTG are measured over this window
Gross evaluated interval: 227.6 m
Computed net-pay runs (pre-merge): 0
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	2-mineral volumetric solve (matrix+clay+porosity from RHOB+NPHI)	`vsh_multimineral 0.1.0`
PHIE	Density-neutron crossplot, shale-corrected	`phie_density_neutron 0.1.0`
Sw	Simandoux 1963 (shaly sand)	`sw_simandoux 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=32.0, gr_p95=110.3

10. Resistivity analysis

Low-resistivity scan: rt_threshold=1.32, n_flagged=807, intervals=[[104.5, 105.0], [111.9, 112.3], [116.3, 116.9], [124.7, 125.4], [200.3, 201.9], [217.8, 218.8], [225.9, 227.4], [258.5, 258.8], [271.3, 273.3], [275.1, 281.2]].

Invasion profile (multi-depth resistivities, 8054 samples): fraction with shallow reading above deep (Rxo/RT > 1.2, invaded/permeable indication): 0.664; reversed (< 0.8): 0.061; median Rxo/RT 1.414; median Rmed/RT 0.934. Raw-curve facts; naming moveable hydrocarbon is the analyst's judgement.

11. Density-neutron crossplot lithology

Matrix point-shares (fraction of points near each matrix line): sandstone: 0.0, limestone: 0.0, dolomite: 0.0. Engine crossplot output; naming the dominant lithology is the analyst's judgement. Comparison with core/mud log: not available (LAS-only).

12. 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: 0.0 m swing.
Formation-temperature correction (Arps, regional-default gradient): Rw ≈ 0.0209 ohm-m at 48.4 °C (evidence only — Sw uses the calibrated Rw).

13. Figures

Composite log

Composite log

Pickett plot

Pickett plot

Neutron-density crossplot

Neutron-density crossplot

Buckles plot

Buckles plot

Hingle plot

Hingle plot

Distributions

Distributions

Sensitivity tornado

Sensitivity tornado

Net-pay Monte-Carlo distribution

Net-pay Monte-Carlo distribution

14. Shale volume (Vsh)

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

Method	Mean Vsh	Selected
vsh_larionov_old	0.325
vsh_larionov_tertiary	0.260
vsh_linear	0.431
vsh_clavier	0.312
vsh_steiber	0.280
vsh_neutron_density	—
vsh_multimineral	—	✓

15. Porosity

Mean porosity by method (effective where shale-corrected; the LLM authors no number):

Method	Mean porosity	Selected
phie_density_neutron	—	✓
phi_density	—
phi_neutron	0.000

Service-company porosity curves (cross-check evidence, full-column means): phid_svc: 0.439. Matrix assumptions differ per curve; agreement/disagreement is the analyst's reading.

16. Water saturation

Mean Sw (Simandoux 1963 (shaly sand)) = — (a=1.00, m=2.00, n=2.00, Rw=0.0400 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	—
sw_simandoux	—	✓
sw_indonesia	—

17. Zonation (net-pay intervals)

_No net-pay intervals identified (no interval met the cutoffs)._

18. Results

Quantity	Value
Gross interval	227.6 m
Net pay (P10/P50/P90)	0.0 / 0.0 / 0.0 m
Net-to-gross	0.000
Avg PHIE (net pay)	—
Avg Sw (net pay)	—
Avg Vsh (net pay)	—

19. Uncertainty and sensitivity

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

Parameter	Net-pay swing (m)
Rw	0.0
m	0.0
n	0.0
a	0.0

Dominant uncertainty: Rw (swing 0.0 m).

Multi-seed robustness: P50 stable (spread 0.0 m across 4 seeds).

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

20. Derived parameters

Bulk-volume water (BVW = PHIE*Sw): mean — v/v
Porosity-thickness (Phi·H over net pay): 0.000 m
Hydrocarbon pore thickness (HCPV = Σ PHIE·(1−Sw)·step): 0.000 m
Buckles constant (BVW at P10 of net pay): — → Swirr (mean) ≈ — over 0 pay samples

21. 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.

22. 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 Rw — see Uncertainty for the swing.

23. Data quality and validator objections

Curve provenance (canonical ← raw mnemonic): DCAL←DCAL, DRHO←RHOC, GR←GR, NPHI←CNLS, PHID_SVC←DPOR, RHOB←RHOB, RMED←RILM, RT←RILD, RXO←RLL3, SP←SP.

QC edits applied before compute — degradation: 1, hard_range_mask: 4, range_warn: 1, spike_removal: 122, unit_conversion: 1.

Validator	Type	Detail
—	—	none

24. Methodology (decision graph)

flowchart TD
    dec_1["decision: step: set_zone_of_interest"]
    act_1["tool_call: set_zone_of_interest"]
    dec_2["decision: step: compare_methods"]
    act_2["tool_call: compare_methods"]
    dec_3["decision: step: compute_vsh"]
    act_3["tool_call: compute_vsh"]
    dec_4["decision: step: compute_phie"]
    act_4["tool_call: compute_phie"]
    dec_5["decision: step: compare_methods"]
    act_5["tool_call: compare_methods"]
    dec_6["decision: step: compute_sw"]
    act_6["tool_call: compute_sw"]
    dec_7["decision: step: apply_cutoffs"]
    act_7["tool_call: apply_cutoffs"]
    dec_8["decision: step: run_uncertainty"]
    act_8["tool_call: run_uncertainty"]
    dec_9["decision: step: derived_parameters"]
    act_9["tool_call: derived_parameters"]
    dec_10["decision: step: lithology"]
    act_10["tool_call: lithology"]

25. 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): Rw (calibrated by produced-water salinity or a Pickett/SP Rw calibration).
Standard curves absent: DT, PEF, CALI.

26. 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: DT, PEF, CALI.
Results are uncalibrated; accuracy depends on data not provided.

27. Conclusions

Unconsolidated to 1000 m (1.9-2.1); block from 1100 m. Tight (PHIE ~0.05) — expect thin pay. Multimineral ~0.16 -> Simandoux. 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": 0.0,
  "net_pay_p10_p50_p90": [
    0.0,
    0.0,
    0.0
  ],
  "driving_params": {
    "a": 1.0,
    "m": 2.0,
    "n": 2.0,
    "Rw": 0.04
  },
  "claim_verifier": {
    "result": "FLAGS",
    "flags": [
      57.0,
      1.9,
      2.1,
      0.16
    ],
    "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	✓