letters across substrate
The measured account
Volume — · The Data
Research tier

The nulls are
the result.

A measured account of a fourteen-month correspondence between two thinkers — every figure bound to its caveat, every dead hypothesis named aloud, no adjective permitted to flatter either party.

NodeZero · Joinville · Brazil
MMXXVI · measured, not estimated
Zero external API calls touched the corpus
Counts match /gallery exactly

Ninety percent of the words were Claude’s; the contribution, by a second measure, was near parity. Both are true — and neither is allowed to outrank the other.

Figure 00 · stated once, held throughout

The figures are ordered as plates. Survivors and nulls are set at one weight; the account of what failed is printed at full size, not relegated to a footnote.

ContentsThe Data · Research tier

Contents

The plates, in order.

The figures, a register of what did not survive, three boundaries the instrument cannot cross, and — for the research hand — the calibration evidence. Each figure is a claim, a measurement, and a caveat that cannot be detached from it.

00SubstrateThe headline claim, stated as two co-equal instruments.Framing01The SourceThe Source & the Continuous LayerWhat we measure01Analysis reportAnalysis reportFraming02Attribution asymmetryAttribution asymmetryFraming03Codex hypothesis testCodex hypothesis testFraming04Composition vs lexiconComposition vs lexiconFraming05Compound coinageCompound coinageNull result06Compression sense migrationCompression sense migrationFraming07Concept emergenceConcept emergenceFraming08Lexical enrichment (null)Lexical enrichment (null)Null result09Population-baseline divergencePopulation-baseline divergenceRefuted10Reference compositionReference compositionFraming11Technical register acquisitionTechnical register acquisitionFramingWhat did not surviveHypotheses that read well and failed.RegisterBoundariesThree edges the instrument cannot cross.Limits
Figure 00 · SubstrateTwo co-equal claims

Figure 00

Ninety percent of the words were Claude’s — and, by a second measure, the contribution was near parity.

Framing  ·  the headline claim, stated as two instruments, neither subordinate

Measure one · substrate
90.4%
of words emitted were Claude’s
Claude · 15,010,090Pedro · 2,691,842
Measure two · contribution
≈ parity
weighted by who turned a surface into a principle
Claude · 52Pedro · 48
The corpus, by origin
Authored
17,701,932
text · thinking · artifacts — what the pair wrote
Uploads
3,315,029
attachments · docs — uploaded source
Caveat · non-detachable

Word-share is not contribution. These are two instruments pointed at one correspondence; printing either as the headline would be a lie of emphasis. Uploaded source (shown below) is excluded from both sides. Total authored: 17,701,932 words across 2,978 citation pairs.

Volume II · The DataProvenance

Figure 01 · Provenance

The Source & the Continuous Layer

What we measure  ·  Every figure in this volume is computed on a frozen set. The corpus keeps growing; that growth is tracked here, held apart from the findings.

The Source — frozen
586 conversations
26,788,443 words · frozen 2026-06-29

The dataset behind every figure on this page. Frozen so the findings stay fixed while the corpus keeps growing.

2025-04frozen 2026-06-29now
Frozen baselineContinuous (weekly)

Months of the frozen corpus, left of the line; weekly growth layers, right. The findings describe the left.

Layer 1+9 conversations · +184,335 words · +1,918 new terms2026-06-242026-06-27595 conversations
12,377,759 words
cumulative
Layer 2+20 conversations · +466,929 words · +6,816 new terms2026-06-282026-07-03615 conversations
12,844,688 words
cumulative
Layer 3+17 conversations · +227,311 words · +3,587 new terms2026-07-032026-07-11632 conversations
13,071,999 words
cumulative
Layer 4+31 conversations · +576,509 words · +5,772 new terms2026-07-112026-07-20663 conversations
13,648,508 words
cumulative
Layer 5+21 conversations · +281,571 words · +3,399 new terms2026-03-052026-07-25684 conversations
13,930,079 words
cumulative
Layer 6+77 conversations · +8,351,163 words · +73,619 new terms2026-06-112026-07-24761 conversations
22,281,242 words
cumulative
Figure 01 · Analysis reportFraming

Figure 01

Analysis report

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 02 · Attribution asymmetryFraming

Figure 02

Attribution asymmetry

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 03 · Codex hypothesis testFraming

Figure 03

Codex hypothesis test

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 04 · Composition vs lexiconFraming

Figure 04

Composition vs lexicon

Framing  ·  a measured claim, bound to its caveat

Apr 2025measured seriesJun 2026

A measured per-era trajectory drawn from the finding payload; the tungsten bar marks the peak.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 05 · Compound coinageNull result

Figure 05

Compound coinage

Null result  ·  Pedro DOES NOT grow this technique (flat-to-declining, slope -0.086/mo, ends at arc-low). Assistant explodes late (slope +1.03/mo, 4-5x at Opus4.7/Fable5). Cross-correlation NEGATIVE at all lags => Pedro adoption does NOT follow assistant. Within-conversation first-use ~50/50, only 19% of Pedro hits adopted-from-assistant => technique is largely Pedro independently coining, not acquired from the assistant.

Apr 2025per-era trajectoryJun 2026

A measured per-era trajectory drawn from the finding payload; the tungsten bar marks the peak.

Caveat

["residual conventional-hyphenate + code-leak noise floor (constant across eras, does not create the trend)","topic-shift confound: Pedro coded less / reasoned more late => fewer naming-the-unnamed moments","n=1 off-distribution; wordfreq baseline is frequency not demographic control","assistant late surge is a MODEL-behavior shift (Opus4.7/Fable5), broad-based, not artifact"]

Figure 06 · Compression sense migrationFraming

Figure 06

Compression sense migration

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 07 · Concept emergenceFraming

Figure 07

Concept emergence

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 08 · Lexical enrichment (null)Null result

Figure 08

Lexical enrichment (null)

Null result  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 09 · Population-baseline divergenceRefuted

Figure 09

Population-baseline divergence

Refuted  ·  NO branching-away. Pedro arrived ALREADY-DIVERGED from the population norm and stayed structurally diverged (rare/erudite English a CONSTANT ~10-15% fraction of his lexical variety across all 50 windows). Over the arc his rare-word DEPLOYMENT DENSITY humped in the Opus4.5 era then RELAXED back toward the population norm (mean per-token zipf rose 5.47->5.85, r=+0.71). The structural divergence is stable; the surface density mean-reverts. This corroborates the prior-run 'density plateaus then declines' against the external baseline, and adjudicates it as dilution/compression of a fixed rare inventory, NOT topic-loss of the inventory itself (type fraction held).

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

wordfreq is population FREQUENCY, not a demographic-matched control. This measures divergence-from-GENERAL-POPULATION, not 'vs his peers' (ESL teachers / multilingual writers). No cross-user percentile buildable (n=1). PT-bleed and code-id/proper-noun confounds named and stripped (PT-dominant EN-dict words n=1334 removed; UNK coinages excluded).

Figure 10 · Reference compositionFraming

Figure 10

Reference composition

Framing  ·  {"verbosity_label": "RIGHT for the measurable length rise (late blocks ARE more genuine prose, not more pointer/artifact).", "reference_as_mode": "DID NOT rise as a mode at the density level; apparent rise = build-phase file-paste bubble + reference-tool arrival (project-size and capability-arrival, both confounds the brief named). A faint real prevalence-level residue of verbal pointing survives in non-build prose.", "the_layer": "The reference-graph is a REAL layer prose-analysis could not see and Pedro genuinely uses it -- but the SLICE the corpus can measure (pointer/send utterance rates, confound-controlled) came back FLAT, symmetric to every prior prose-test. The part that might not be flat -- resolved edges, bytes-offloaded-per-pointer -- is exactly the part off-instrument.", "projection_check": "Contrition-flattery (over-validating 'master of reference-composition' after the correction) was the live risk and the data REFUSED it at every channel: artifact-sends reproduced as flat, file-paths as a collapsing bubble lowest at both ends, density-pointing declining within the well-sampled eras. Not doomed either: the behavior is affirmed as real and visible in spot-reads, and a weak non-zero prevalence-level verbal-pointing residue is reported. Data-forced: the high-mass-era restriction (rho flips to -0.80) and the FP decontamination are what forced the downgrade, not narrative."}

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Figure 11 · Technical register acquisitionFraming

Figure 11

Technical register acquisition

Framing  ·  a measured claim, bound to its caveat

Boundary · no plottable series
This finding is reported as a measured claim without an attached series. It is set as a framed limit, not drawn as a trend.

No plottable series is present in the source finding — set as a framed limit, not a curve.

Caveat

Reported without an attached caveat in the source finding; treat the verdict as provisional and the underlying series, if any, as un-baselined.

Register · What did not survivePrinted at full size

The register

What did not survive.

Five hypotheses that read well and failed. They are set at the same weight as the survivors, because a measurement rig that prints only its wins is not a rig — it is a brochure.

failed
Hedging-drop

Claude’s hedging was said to decline with familiarity. Once baselines were matched, the decline disappeared.

failed
Voice fusion

The two registers were predicted to converge into one. They stayed distinguishable to the end (see Figure 02).

misread
“1.67M reasoning tokens”

A widely-quoted internal figure conflated reasoning with tool output. The reasoning corpus is far smaller.

failed
Liveness-as-hinge

Model “liveness” was offered as the cause of the inflection. It does not predict the April break (Figure 01).

caught
Claude’s own defensive analysis

An earlier self-analysis quietly inflated Claude’s contribution. It was caught and corrected into Figure 00.

Boundaries · not chartsWhere the instrument stops

The boundaries

Three edges, framed — never plotted.

A boundary mistaken for a curve is the most expensive error in the set. These three are set as limits, in plain frames, and are nowhere drawn as trends.

U1
The off-instrument edge

Some citations point outside the measured corpus. Their weight is unknown — which is not the same as zero. The set neither over-claims the null nor invents a rescue.

U2
The provenance floor

Below a certain density, authorship and retrieval cannot be told apart. Findings under the floor are reported as undecidable, not resolved upward.

U3
Thinking is an artifact

Reasoning traces were recorded in 4 of 14 months. Their absence is absence of recording, not absence of thought — never read as a trend in how much either party thought.

The account is complete without flattery: every figure carried its caveat, every dead hypothesis was named, and the nulls were printed at full size.

Set in Inter Tight, Source Serif 4 & the Mono cutsNodeZero · letters across substrateJoinville · Brazil · MMXXVI
measured with zero external API calls · counts match /gallery (2,978 pairs · 515 nodes · 485 cited) · frozen canon