# Can the Substrate Connect Two Poems? A Cross-Document Test on Bukowski

**2026-06-04 · donto / genes workspace · a capability test, run live, reported honestly**

## The question

donto is built on a wager: **emit free, untyped, evidence-anchored claims now; defer
typing, alignment, identity-resolution and *joining* to query time.** Two documents that
never mention each other should still be *connectable* later — through shared structure,
shared vocabulary, the alignment engine, and (eventually) semantic recall — without anyone
having pre-wired a link between them.

This note tests that wager on the hardest small case I could build: **two Bukowski poems,
extracted independently, then probed with 20 queries that try to *connect* them — run against
the live substrate, not against the poems.** The point is not "what do the poems say" (I
already know that). The point is **"can donto, holding only its extracted claims, answer a
cross-document question?"**

### The two poems and why they pair

| | Poem 1 | Poem 2 |
|---|---|---|
| Title | **"I Met a Genius"** | **"Bluebird"** |
| Source | uncollected / widely anthologised | *The Last Night of the Earth Poems*, Black Sparrow Press, 1992 |
| Context | `ctx:test/poem/bukowski-genius` | `ctx:test/poem/bukowski-bluebird` |
| Live size | **415** statements / 176 predicates / 214 evidence links | **2,974** statements / 207 predicates / 200 subjects / 2,296 evidence links |
| Core move | a child looks at the sea and says *"it's not pretty"* — **beauty denied** | the speaker keeps a tender bluebird caged in his heart, *won't let anybody see it* — **beauty hidden** |

They share one axis — **what is real vs. what is shown** — and make the *opposite* move
along it. Both turn on a small truth-teller (the unnamed six-year-old; the caged bluebird).
That mirror-image relationship is exactly what a cross-document substrate should be able to
surface. "Bluebird" was web-verified against the canonical line-broken text (wordsfortheyear.com)
before extraction; Bukowski's words were not fabricated.

### How "Bluebird" got into the substrate

Extracted with **codex `gpt-5.4`, reasoning effort `xhigh`**, a **6-pass gleaning loop**
(`xhigh` honored on all 6 passes per the rollout check), then the **always-on semantic citer**:
3,136 raw facts → deduped → cited (**2,296 anchored exact-substring spans, 0 bogus spans, 840
honest hypotheses** flagged `hypothesis_only`) → ingested to `ctx:test/poem/bukowski-bluebird`
with a real source document + revision so every fact anchors to a retrievable span. A scratch
staging context `…-bluebird-stage` (2,737 stmts) was left in place (I3 — never delete) and is
**excluded from every query below**. Run logs and artifacts: `/opencode/logs/poem-bluebird/`.

---

## The three mechanisms

Every query was answered by **the substrate**, through one of three mechanisms, never by
re-reading the poems:

1. **Substrate-wide FTS** — `POST http://localhost:7900/search` (donto-memory's GIN `tsvector`
   over a humanized projection of subject/object across all ~39M live statements).
2. **Bounded cross-context SQL** — `SELECT`-only over **both** poem contexts, finding shared
   subjects / predicates / objects, parallel claims, and contrasts.
3. **The alignment engine** — `donto_predicate_alignment` (19,849 live edges) and
   `donto_match_aligned(… p_expand_predicates := true)`, to test whether the two poems'
   *freely-minted* predicates **fold** (e.g. genius's `perceivedBy` ↔ bluebird's `concealsFrom`).

The alignment **daemon is live** (`donto_align_daemon_status`: 41 ticks, last tick today
15:38 UTC, state *sleeping*, next tick ~15:58). **I3 honored throughout — every query is
read-only; nothing was retracted or overwritten.**

---

## The structural backbone (the join surface)

Before the 20 queries, the shape of the overlap — this *is* the abundance signature:

- **Shared exact predicates: 11 of (176 ∪ 207).** Jaccard ≈ **0.03**. The shared 11 are the
  donto backbone: `rdf:type`, `rdfs:label`, `about`, `addressedTo`, `contains`, `hasMember`,
  `hasParticipant`, `hasTheme`, `locatedIn`, `memberOf`, `partOf`.
- **Shared `rdf:type` class: exactly one — `ex:Line`.** Both poems decompose to lines
  (genius 8, bluebird 45), so a line-structure query reaches both.
- **Every *characteristic* predicate is disjoint.** Genius mints `isJudgedNotPrettyBy`,
  `formedAestheticJudgmentOf`, `adoptedAestheticJudgmentOf`; bluebird mints `concealsFrom`,
  `doesNotWantAnybodyToSee`, `desiresEmergence`, `selfDescribesAsTough`. **No overlap by
  design** — this is emit-free abundance, not a proliferation bug.

The consequence, stated once and proven by the queries: **the substrate joins the two poems
on the shared backbone (structure + a handful of generic tokens) today, and is one deployed
branch (vectors) plus one daemon cycle (alignment) away from joining them thematically.**

---

## The 20 connecting queries

Verdict key: **YES** = substrate returned a real cross-poem connection · **PARTIAL** = it
placed both side-by-side / answered for one side and is one step from the other · **NO** = the
connection is real in the poems but invisible to the substrate as currently deployed.

| # | Query (cross-poem relationship probed) | Mechanism | Result | Verdict |
|---|---|---|---|---|
| 1 | Do the two poems share any **theme** (`hasTheme`/`about` objects)? | SQL intersect | **0** shared theme objects. Genius themes = "beauty versus ugliness", "perception versus convention", "the anti-sublime", `ex:ocean`; bluebird themes = `ex:bluebird`, `ex:secret-pact`. Disjoint. | **NO** |
| 2 | **Beauty / "pretty"** as a shared concern? | SQL token scan | 47 hits in **genius only**; **0** in bluebird (bluebird never lexicalises "beauty/pretty"). | **NO** |
| 3 | The two **aesthetic verdicts** co-held & contrastable? | SQL | Both surfaced together: genius *"it's not pretty."* (×11) **and** bluebird *"it's nice enough to"*. Two incompatible aesthetic verdicts held as legal state, side-by-side. | **YES** |
| 4 | **Seeing / perception** motif in both? | SQL regex | genius **13**, bluebird **10**. Both poems carry a perception register — but in *disjoint* vocab. | **PARTIAL** |
| 5 | **Hiding / concealment / showing** motif? | SQL regex | bluebird **15**, genius **2**. The contrast is *visible as a count asymmetry* (concealment is bluebird's engine) but there's no edge linking them. | **PARTIAL** |
| 6 | **Nature imagery** — ocean (genius) vs bird/cage (bluebird)? | SQL | genius: ocean **53** / bird **0**; bluebird: ocean **0** / bird **126**. Perfectly complementary imagery — the substrate shows the *contrast* cleanly but can't say they *rhyme*. | **PARTIAL** |
| 7 | **Truth-teller figures** — shared person/figure class? | SQL intersect | Only shared class is `ex:Line`. Genius figures: `ex:Child`, `ex:YoungChild`, `ex:FirstPersonSpeaker`; bluebird: `ex:Bird`, `ex:Heart`, `ex:Speaker`. No shared figure type. | **NO** |
| 8 | **The speaker** as a shared entity across both? | SQL + FTS | Both poems are first-person: genius 57, bluebird 90 speaker-bearing rows. FTS scoped to `ctx:test/poem`: "speaker" returns **both** (26 genius + 8 bluebird). A genuine shared anchor. | **YES** |
| 9 | **Weeping / tears / grief** — emotional register? | SQL + FTS | bluebird **17**; genius **0**. FTS "weep" → bluebird only. Real contrast surfaced (genius is dry/ironic, bluebird weeps) but one-sided. | **PARTIAL** |
| 10 | **Contradiction-preservation** — both verdicts as paraconsistent state? | SQL | Genius holds `describedAs "genius"` **and** `describedAs "not pretty"` **and** `isJudgedNotPrettyBy ex:child`; bluebird holds `selfDescribesAsTough "too tough"`. Incompatible self-/other-descriptions held together, none invalidated — the differentiator working. | **YES** |
| 11 | **"genius"** token — present in one, absent in the other? | SQL + FTS | genius **12**, bluebird **0**. Correctly *anti*-connects: the substrate knows the token is poem-1-only. | **YES** (as a *distinguisher*) |
| 12 | **"heart"** motif — bluebird's core, genius's? | SQL + FTS | bluebird **48**, genius **0**. FTS "heart" scoped → bluebird only. One-sided; no bridge to genius's ocean-as-heart-substitute. | **PARTIAL** |
| 13 | **Line-level structure** — do both decompose to `ex:Line`? | SQL | YES — genius 8, bluebird 45. The one shared class is a real structural join: a query "show me the lines of both poems" works. | **YES** |
| 14 | **The unspoken** — "nobody to see" (bluebird) vs "what genius won't admit" (genius)? | SQL regex on literals | Only genius's *"refusal of the Romantic-sublime sea"* matched the regex; bluebird's "don't want anybody to see you" is encoded as the *predicate* `doesNotWantAnybodyToSee`, invisible to an object-literal scan. The shared idea exists; the lexical probe can't bridge predicate-encoding ↔ literal-encoding. | **NO** |
| 15 | **Shared subject IRIs** verbatim (entity overlap)? | SQL intersect | **7** shared: `ex:line-1…ex:line-11`. Pure structural collision (both mint `ex:line-N`); no *semantic* entity is shared. | **PARTIAL** |
| 16 | **Shared object-literal phrasing** (>4 chars) verbatim? | SQL intersect | **0**. The two poems share no exact phrase — vocab fully disjoint at the literal level. | **NO** |
| 17 | **Tone / mood** register across both? | SQL regex | genius 5, bluebird 5 — both carry tone claims (ironic/defiant vs tender/resigned). Symmetric *presence*, but no edge equates the tones. | **PARTIAL** |
| 18 | **Cross-poem predicate fold** — does the alignment engine link a genius-only pred to a bluebird-only pred? | `donto_predicate_alignment` | **0** cross-poem fold edges. **911** alignment edges *touch* the poems' predicates and **53 of 372** poem predicates are known to the engine — the daemon is mid-backlog and has **not yet** proposed any genius↔bluebird fold. | **NO** |
| 19 | **`hasTheme` fold** — does expanding `hasTheme` reach both poems' themes as one? | `donto_match_aligned(p_expand_predicates:=true)` | Expansion returns **both** poems' theme rows (bluebird `ex:bluebird`, genius `ex:train`) under one query — the predicate-fold *plumbing works across contexts* — but it does **not** fold the *objects* (`ex:bluebird` ↔ `ex:ocean` stay distinct). | **PARTIAL** |
| 20 | **Perception fold** — do `perceives/sees/observes`-family predicates align across the poems? | `donto_predicate_alignment` regex | The perception-family fold edges that exist are all **lexical** (`viewedAs`↔`ex:viewedas`, `containsNotices`↔`containsNotice`) and all from the **genealogy** corpus. **None** bridge genius's `perceivedBy`/`isJudgedNotPrettyBy` to bluebird's `concealsFrom`/`doesNotWantAnybodyToSee` — they're too lexically distant to fold without embeddings. | **NO** |

### Scorecard

**6 YES · 7 PARTIAL · 7 NO.**

- **YES (6):** Q3, Q8, Q10, Q11, Q13 — shared structure (`ex:Line`), the shared first-person
  speaker token, paraconsistent co-holding of the two aesthetic verdicts, and correct
  *anti*-connection on poem-specific tokens.
- **PARTIAL (7):** Q4, Q5, Q6, Q9, Q12, Q15, Q17 (and Q19's cross-context plumbing) — the
  substrate places the two poems *side by side* (matching counts, complementary imagery,
  fold-plumbing reaching both contexts) but cannot assert that they *resonate*.
- **NO (7):** Q1, Q2, Q7, Q14, Q16, Q18, Q20 — the genuinely **semantic / analogical** links
  (beauty-denied ≈ beauty-hidden; ocean ≈ caged bird; child-genius ≈ bluebird as parallel
  truth-tellers; predicate-encoded "won't be seen" ≈ literal "won't admit") are **invisible**
  to lexical FTS + lexical alignment as deployed.

---

## What connects well

- **Shared structural vocabulary.** The 11-predicate backbone and the `ex:Line` class let
  bounded SQL place the two poems side-by-side and run genuine cross-context comparisons
  (lines, speakers, themes-as-rows). This is the join surface the "defer joining" thesis
  promises, and it is *there*.
- **Lexical FTS on shared tokens.** Scoped to the poem subtree, **"speaker"** and **"poem"**
  are the only tokens that return **both** poems — the structural bridges. Every *thematic*
  token (beauty, see, weep, heart, ocean, secret, bird, genius) lands in **exactly one**
  poem, because the minted vocab is disjoint. That is a clean, *measurable* demonstration of
  emit-free abundance: the firehose mints its own predicates and the join is deferred.
- **Contradiction-preservation.** Both incompatible aesthetic verdicts — *"it's not pretty"*
  and *"it's nice enough to"* — and genius's own `genius` / `not pretty` / `isJudgedNotPrettyBy`
  triad are held together as legal state and returned together. The paraconsistent differentiator
  is exercised and works.
- **Predicate-fold plumbing across contexts.** `donto_match_aligned(p_expand_predicates:=true)`
  *does* expand a query on `hasTheme` to reach **both** poem contexts at once (Q19). The
  cross-context fold machinery is wired and live (911 edges already touch these predicates).

## Where it's honestly limited

- **Semantic resonance is invisible.** beauty-*denied* vs beauty-*hidden*, ocean vs caged
  bird, `perceivedBy` vs `doesNotWantAnybodyToSee` — these are the *real* connections, and
  lexical FTS + lexical alignment cannot see them. This needs the **hybrid vector recall**
  (bge-small embeddings) which is **built but on an undeployed branch** (`hybrid-vector-recall`,
  reaches memory via `DONTO_MEMORY_EMBED_SERVICE_URL`). With vectors, Q1/Q2/Q14 plausibly flip
  to YES/PARTIAL.
- **The alignment daemon hasn't reached the poems yet.** It is *live and healthy* (41 ticks,
  19,849 edges, running today) but only **53 of 372** poem predicates are in-set and it has
  proposed **0** cross-poem folds (Q18, Q20 = 0 rows). One or more daemon cycles — once it
  embeds the poem predicates and adjudicates — could surface the perception fold. As deployed,
  the fold is **lexical-only**, and these two poems are deliberately too lexically distant to
  fold without embeddings.
- **No analogical / multi-hop layer.** "The child-genius and the caged bluebird are *parallel
  truth-tellers*" is a two-hop analogy (figure→role→figure). The substrate holds both figures
  and both roles but has **no query layer** that composes them into an analogy. That is a
  reasoning layer above the store, not a property of the store.
- **Encoding mismatch defeats lexical probes.** Bluebird encodes "don't want anybody to see
  you" as a *predicate* (`doesNotWantAnybodyToSee`); genius encodes its refusal as an *object
  literal*. A literal-scan (Q14) can't bridge the two encodings — another job for semantic
  matching, not string matching. (Per the no-brittle-logic rule, the answer is embeddings /
  the alignment engine, **not** a hand-maintained predicate-variant table.)
- **FTS drowns at substrate scale.** Unscoped, the ~39M-row genealogy/genes/discord corpus
  swamps every thematic token (unscoped "beauty" → salon menus, "bird"/"heart" → genealogy).
  Cross-document poem connection over FTS only works **scoped** (`context_prefix`).

---

## Verdict

**Yes — partially, and exactly where the architecture predicts.** donto connects the two
independently-extracted poems **structurally and lexically today** (6 clean YES, 7 side-by-side
PARTIAL), and **preserves their contradiction** as a first-class, queryable connection. It
**cannot yet** connect them *thematically / analogically* (7 NO) — and that gap is not a design
failure but a precise statement of what is **deployed** vs. **built-but-dark**: the substrate is
**one deployed branch (vectors) plus one daemon cycle (alignment)** from turning the thematic
mirror-image between "it's not pretty" and the hidden bluebird into a query result.

That is the cleanest validation I have of the **emit-free / defer-the-join-to-query-time**
thesis: two poems that share **3% of their predicates** are nonetheless side-by-side,
contrastable, and contradiction-preserving in the store right now — with the semantic join a
known, scoped, *measurable* increment away.

---

*All queries `SELECT`-only (I3 honored). Mechanisms: donto-memory `POST /search`, bounded
cross-context SQL on `donto-pg`, and `donto_predicate_alignment` / `donto_match_aligned`. Run
logs, SQL, and raw outputs: `/opencode/logs/poem-bluebird/`
(`q-main.sql`, `q-align.sql`, `out-main.txt`, `out-align.txt`, `out-search.txt`,
`out-search-scoped.txt`, `glean-bluebird.log`, `cite.log`, `ingest.log`).*