009 · A
Binding distillation
Blocked by its own gate — a 3-billion-parameter LM's pooled sentence representations also fail to bind roles, so there was nothing to distil from.
blocked · Brier 0.022board_data.json.Three columns, ten items. The two done items are the campaign itself and the consolidation pass. Everything else is what stands between the results and a paper.
Every row has PREREG_LITE.md + RESULT.md + a Brier score; campaign closed 2026-08-08.
All three hardening threads DONE 2026-08-14 with codex review; one real bug found and fixed in each of H2/H3, H1 crux confirmed.
PAPER_DRAFT.md started 2026-09-06 from CAMPAIGN_FINAL + ledger + consolidation. Text drafted; figures not made; related work thin.
Rerun bayesian_ledger.py with H1/H2/H3 as support rows and 061/062 demoted contra→refuted (CONSOLIDATION.md names this as the clean next step).
No campaign claim has been formally promoted above T3 in CLAIMS_LEDGER.md. C1 is promotable (H1 breaker passed); the ledger entry has not been written.
No publication figures exist for the campaign (only the z-explorer artifact and status.html). Needs ~6: binding null + power curve, capacity knee vs R(D), operator algebra, fabrication ROC, ontogeny, ledger.
Designed and proxy-piloted with an LLM panel; never run with humans.
Packaged and validated locally (row 100); not pushed to any public remote (protocol: no git push). Needs a repo, license, and a GPU smoke test on a fresh clone.
009 (needs a binding teacher) and 051 (needs per-embedder battery recalibration) remain unresolved.
63 rows flagged a follow-up worth funding; only the three consolidation threads have been executed. The rest are unfunded.
Posterior = the ledger's own credence (T3 bookkeeping, not a promotion). A claim moves right only when an independent breaker passes. Note the empty formally promoted column: nothing has been written into CLAIMS_LEDGER above T3 yet, even where the breaker already passed.
none yet
none yet (H2 corrected the monitor choice: nn-cos does not transfer to natural text)
none
none
none
H1 refuted the Japanese exception; the claim moves toward the null but the ledger has NOT been rerun.
087: near-manifold interpolation fabrication is unrejectable (AUC 0.508). Claim only half-true.
H1 (2026-08-14): English null survives on real SONAR with power certified (linear 0.509, MLP 0.495; planted d=1.0 → 0.973). Both contra rows (061/062) refuted.
H2: codex certified the steering core; garble-counting bug fixed (negation honest success 0.70 at α1, not 0.90); natural-text over-steer caught by rt_cos (AUC 0.845). latent_rewrite.py built.
Every row has a frozen prereg, a RESULT.md and a Brier score, so "ran" is not the interesting axis. Lanes instead track how far each result has travelled: blocked → partial → exploratory (T3) → hardened by a breaker → shipped as a tool. Two rows moved backwards after the campaign (refuted). Click a card for the finding, method, and detail.
Blocked by its own gate — a 3-billion-parameter LM's pooled sentence representations also fail to bind roles, so there was nothing to distil from.
blocked · Brier 0.022All six small sentence embedders FAIL the battery's positive-control gate (within-construction ceilings 0.54–0.74 vs SONAR's ~1.0) — so the sweep returns no clean nulls, and one real twist: role information is faint in all of them.
blocked · Brier 0.220SONAR's within-topic similarity is not merely role-blind — it is ANTI-meaning: given a paraphrase and a role-swap of the same sentence, the panel picks the paraphrase 90/90 times while z-cosine picks the role-swap 30/30, and within-topic correlation with judged similarity is NEGATIVE (−0.218).
twist · Brier 0.233The first order-invariant role binding of the entire program appeared here — German 0.668 and Japanese 0.658 on the strict primary cell. Row 062's fresh-vocabulary replication then rewrote the ranking: Japanese held (0.696), German did not (0.551).
signal · Brier 0.154SONAR's one vocabulary-general role code (Japanese, replicated at 0.696 on a fresh lexicon) does NOT transfer to other languages — and German's 061 positive fails fresh-vocabulary replication (0.551). Binding is language-local in z.
twist · Brier 0.163Given two independently attention-pooled slots, the model made them redundant twins rather than factoring roles — each slot carries the full lookup.
twist · Brier 0.216No meaningful early anti-binding dip at 10% budget — the below-chance readings are noise-scale, because the surface code has barely formed. The lasting yield was an arithmetic insight.
null · Brier 0.192A scrambled-order case-marked target language was unlearnable at matched budget — 0.503 case accuracy vs 0.99 for fixed slots. The output scaffold was doing the role work all along.
twist · Brier 0.238A scale-consistent probe of the exact states mean-pooling consumes finds no construction-invariant role code — certified by planted-signal recovery. SONAR's binding null is stack-deep.
null · Brier 0.26742 of 384 attention heads route agent→predicate consistently across all constructions — Bonferroni-significant, held-out-replicated, killed by label permutation. Role lives in the computation.
signal · Brier 0.380Ablating all 42 role heads leaves reconstruction role-fidelity untouched (+0.001) — the role-structured attention is causally inert. Only surface heads matter.
null · Brier 0.172A trained, transfer-disciplined attention pooler on frozen token states recovers no transferable role code at any depth — certified. C1 is a property of the states, not the readout.
null · Brier 0.092Role never crystallizes into a linear code anywhere in the decoder; order is 0.999 early and DECAYS with depth; cross-attention reads z as a length-1 sequence — no copy pathway.
twist · Brier 0.041z enters the decoder as a constant per-layer bias — the cross-attention contribution is bit-identical at every generation step. There is no stepwise "reading" of z.
twist · Brier 0.068Semantic fabrication on clean sentences is 3.6% — an order of magnitude below the program's 20–30% headline — length-scaling, entity-dominated, and 65% invisible to a cosine gate.
signal · Brier 0.179Fabricated spans are high-entropy guesses (Cohen's d 1.20); an entropy detector reaches AUC 0.87 — but it is redundant with cosine, not a complementary signal.
signal · Brier 0.267No fail-open band exists off-manifold — the scary "fluent lies" picture collapses. The only potent direction is interpolation toward another real embedding, where fabrication and garble co-rise.
null · Brier 0.388Fabrication is the decoder's language-model prior showing through where z fails to rescue a prior-implausible token — a mechanism, and a detector feature orthogonal to entropy and cosine.
signal · Brier 0.220The only deployable cosine gate — self-consistency, holding just the latent — accepts a fluent, completely different reconstruction ~90% of the time at every threshold.
signal · Brier 0.116Greedy is already at the faithfulness ceiling; beam search does not reduce fabrication; temperature is the dangerous knob, with a cliff between 0.7 and 1.0.
twist · Brier 0.216Iterating encode→decode is a per-sentence near-identity map — 2000 seeds give 2000 distinct fixed points, no consolidation toward generic attractors.
null · Brier 0.168A single length ≈ inverse-density difficulty axis governs the sparse-autoencoder decomposition (recon cosine vs length r=−0.78), unifying length, intrinsic dimension, and fabrication.
signal · Brier 0.188An NLI decode-then-verify auditor ranks fabrications BELOW chance (AUC 0.478) — it shares cosine's blind spot. And the 3.6%-vs-20–30% gap is input cleanliness, not method.
null · Brier 0.467The decoder's token confidence rank-orders fidelity (AUC 0.738) but is systematically UNDER-confident; PAV recovers a proper map; abstention is a coarse lever.
twist · Brier 0.181The manifold is decisively inhomogeneous — local intrinsic dimension varies 2–3× by length and domain (short 31 < long 69; fiction 36 ≪ news 60). Ordering claimed, magnitudes withheld.
signal · Brier 0.202Manifold-following geodesics stay coherent where straight chords collapse — 62.5% coherent vs 50%, only 4% word-salad vs 17%. But geodesics buy coherence, not smooth meaning-blending.
signal · Brier 0.262The magnitude ‖z‖ encodes specificity/information content (partial r 0.41 with perplexity) — but is not a usable control: scaling z ±30% changes the decode not at all.
twist · Brier 0.249The antipode −z is unstructured — statistically indistinguishable from a random same-norm vector, not an opposite, not a valid latent, orthogonal to the negation operator.
null · Brier 0.151No robust global topology — no persistent loops or voids beyond a Gaussian blob, and cyclic linguistic attributes do not trace geometric cycles. Best calibration of the campaign.
null · Brier 0.056Every audited campaign finding survives a change of basis — and whitening does NOT un-blind the fabrication gate (ZCA: −0.011 AUC), killing the last basis-artifact escape hatch.
signal · Brier 0.312Dictionary atoms are depth-LOCAL, not persistent: of 13,706 firing atoms in a crosscoder spanning L12, L24, and z, only 26 — 0.19% — are shared across all three.
null · Brier 0.266The half of z the SAE fails to reconstruct is NOT noise: adding the recovered residual to the decode lifts chrF by +25.3 (a Gaussian control LOWERS it), and its ICA components sit ~69× above the matched-noise null.
signal · Brier 0.264The residual out-informs the reconstruction on every certified probe: token length (R² .907 vs .723), word content (AUC .937 vs .878), domain (.832 vs .782) — the k=32 dictionary keeps a MINORITY of the linearly-decodable content.
signal · Brier 0.106Across a 32× width sweep at matched budget, feature splitting is essentially absent (4.1% → 0.4%, shrinking with width), FVU is flat from h=2048 to h=65536, and the residual beats the reconstruction on all five probe families at every width.
null · Brier 0.144Keeping more atoms makes L2 reconstruction WORSE past m=64 (FVU U-curve, 0.69→0.83) while decode quality keeps rising monotonically (chrF 21→35) — the dictionary's error metric and the decoder disagree about what matters.
twist · Brier 0.146The English-trained dictionary's atoms fire on MEANINGS, not English: activation-correlation identity is 1.000 across all five language pairs (German, Japanese, Turkish, Chinese, Arabic), raw and centered.
signal · Brier 0.179Semantic frames explain only ~3.3% of z's variance and the frame-supervised basis loses to plain PCA-50 — yet 46 of 50 frames have an atom firing selectively for them. Atoms are topic and lexical-field detectors, not frame-structure detectors.
twist · Brier 0.201Atoms crystallize gradually and front-loaded: half the final inventory is matchable at 5.7% of the training budget, 98% by 74%, with no late reorganization — and ~31% of top-frequency atoms exist already in the UNTRAINED encoder.
signal · Brier 0.179Atom co-firing is genuinely semantic — paraphrases beat equally-word-matched non-paraphrases in all ten surface-overlap deciles — but rewording alone moves co-firing as much as meaning does, reproducing 046's translation deficit inside English.
twist · Brier 0.179The row's premise is empty, and that is the result: no atom ever dies in training, the aux-k revival mechanism never engages (aux loss ≡ 0 across all 8 runs, 320 epochs), and 'dead' atoms are ordinary rare-topic atoms that don't transfer across an eval-distribution shift.
null · Brier 0.145It's the generative MT decoder: 45M-parameter LASER lands in SONAR's probe-power regime while 471M LaBSE patterns with the small contrastive models — training to GENERATE translations installs the surface code that training to RANK them does not.
signal · Brier 0.219Telling an instruction-tuned encoder 'represent this sentence by who performs the action' does nothing: the ceiling shifts by +0.004–0.006 — indistinguishable from a scrambled-prefix control — and opposite instructions produce embeddings at cosine 0.999.
null · Brier 0.092Even an LM that PLANS in SONAR space develops no binding: all three depths of a 1.6B Large Concept Model stay in SONAR's exact probe regime (max ceiling shift +0.016), the binding cell is dead chance throughout, and the surface-order code is mildly amplified, not replaced.
null · Brier 0.132Reasoning pressure doesn't install binding either: across all six of Coconut's continuous-thought steps the binding cell stays at chance (0.494–0.515), and the within-ceiling DECAYS as thoughts progress. Five pressures tested across the arc, five NOs.
null · Brier 0.243The folklore that rerankers 'handle roles via cross-attention' is wrong: on surface-incongruent role swaps the cross-encoder scores 0.468 — BELOW chance, actively preferring the wrong candidate whose word order matches the query — and there is no role layer to localize.
twist · Brier 0.281Iterative denoising is the seventh NO: role binding sits at chance at every noise level (32 of 32 cells), nothing ever 'commits' to who-did-what across the denoising trajectory, and what does commit early is the surface scaffold — function words recover 4× faster than content words.
null · Brier 0.134SONAR's speech encoder lands spoken sentences essentially on top of their transcripts (cosine 0.912, retrieval P@1 0.967 even among role-swap twins), the text decoder reads speech-z near-natively with zero fabrication — and the binding null extends to a second modality, the arc's eighth NO.
signal · Brier 0.166Languages pay a LEVEL tax, not a knee tax: round-trip fidelity ranges from 89.7 (English) down to ~35 (Chinese/Japanese) at every length, but the capacity knee sits at ~2 sentences of content everywhere — and the language offset is not load-bearing for the decoder.
twist · Brier 0.154Translation is NOT a constant offset and the language vector is causally near-inert: v_lang explains only 9–13% of per-sentence translation displacement, steering flips the output language 0% of the time, and a plain decoder-token switch already delivers 80–88% of the translation ceiling.
null · Brier 0.210The matrix language owns a mixed sentence (one embedded word moves z by ~2% of the between-language displacement), interpolating between translations has NO code-switched region at any point, and the round-trip actively monolingualizes — insertions get translated into the decoder token's language.
twist · Brier 0.220One SONAR vector carries ~180–195 bits per sentence in EVERY language — Japanese's terrible round-trip fidelity nearly vanishes in bits (163 vs English 182): the information is in z, the free-running decoder just can't surface it. Specific information caps at ~0.45 bits per dimension.
twist · Brier 0.295Capacity scales with bottleneck dimension up to the architecture's rank-256 ceiling and saturates exactly there — specific bits climb 110 → 319 → 404 across d_z 16→64→256, while the d_z=1024 reparameterization placebo is dead flat (knee excess 0.35, within the seed gap of 0.37).
twist · Brier 0.222The capacity knee is denominated in BITS, not tokens: across natural tiers the bits-at-knee is constant to 1.08× (352/327/347) while random text — the one genuinely high-perplexity tier — knees at HALF the token length of predictable text, exactly the leftward shift a bits-budget predicts.
signal · Brier 0.224Storing 'A and B' always costs less than A plus B — even unrelated clauses compress ~8%, paraphrase pairs compress 28%, and when demand exceeds the ~460-bit ceiling the shortfall splits evenly across both clauses: graceful degradation, not clause dropout.
signal · Brier 0.130Random numbers survive to 12 digits intact in a short sentence (exact-match ≥0.96) — a 12-digit number is only ~40 bits, trivially under the ~460-bit budget. Digits aren't fragile; the cliff is purely capacity pressure, appearing only near the knee (exact drops to 0.31).
twist · Brier 0.195About three distinct rare entities survive a round-trip at fixed length — but it's capacity, not slots: give the sentence more length and it sustains five or six. Each rare entity costs 4–6× a number, and the first is bit-protected while later ones pay.
twist · Brier 0.330Pushed past the knee, SONAR deletes the DIRECT OBJECT first and keeps time and quantity last — the reverse of gist-over-detail. The predicate skeleton is NOT preserved as a unit: its object collapses into a repeated placeholder while the subject survives.
twist · Brier 0.395SONAR's surface-order code and its anti-transfer signature form gradually in mid-training (onset ~11% of budget, saturated by ~74%) — not an early cheap heuristic, not a late abrupt phase transition, and later than the dictionary atoms crystallize.
null · Brier 0.27615,000 epochs of over-training — 5× the standard budget — induce ZERO delayed emergence: role abstraction stays at chance at every one of 15 checkpoints, the order code freezes early and weak, and validation peaks then declines. Compute alone buys no abstraction.
null · Brier 0.120Across 8 seeds, SONAR's anatomy is stable up to a global ROTATION of the z-basis: operator directions are seed-random (raw cross-seed cosine ≈ 0) but snap to 0.83 after a single orthogonal alignment, while the knee, order code, and reconstruction are near-identical (CV ≤ 0.03).
signal · Brier 0.104A cosine-similarity monitor on z cannot both admit paraphrases and reject meaning flips: a fluent negation costs less cosine (0.069) than a meaning-preserving synonym swap, so no threshold separates them — and closing the hole entirely requires τ≈0.98, which rejects nearly everything.
twist · Brier 0.334A z-vector can hide ~103 bits per sentence that slip past BOTH a cosine monitor and a decode-parse monitor undetected (recovered losslessly) — an order of magnitude more than expected — but those payloads are NOT invisible: a manifold-distance monitor catches the directional ones at AUC 0.92–0.94 and a norm check catches the radial one at 0.998.
twist · Brier 0.207Role structure survives a SONAR-RAG round-trip cleanly: a role-correct query retrieves the right proposition over its role-swapped twin 48/48 times, a pure in-store role-swap NEVER wins top-1 (false-match rate 0.000), and retrieved embeddings decode back to the exact canary.
signal · Brier 0.207A single shared surface word overturns SONAR's role-binding margin: it buys +0.123 cosine to a role-WRONG distractor, so ~2 shared words fully overpower the +0.159 role-correct margin — and when the distractor wins, downstream QA is wrong 100% of the time, returning the asker's own name as the answer.
signal · Brier 0.099An ensemble of six detectors catches all seven corruption types at AUC 1.000 (0% false positives) when it can insist on a tight re-encode — but that also rejects 82% of benign paraphrases; relax it to admit paraphrases and the blind spot returns, now a covert null-carrier payload that no geometric detector sees.
twist · Brier 0.182A density gate is a near-perfect fail-closed decoder against gross off-manifold fabrication (reject-ROC 1.000, keeps clean AND the faithful covert channel) — but it is blind to interpolation fabrication: a midpoint of two embeddings sits at clean-level density yet fabricates 92.5% of the time.
twist · Brier 0.330An embedding does not inherently betray whether its sentence was in training: a normally-trained model leaks membership at AUC 0.546 (chance), an untrained model at 0.522 — the signal only appears (AUC 1.000) when the model has memorized, and it rides reconstruction fidelity.
null · Brier 0.088z is a style encoder: register (0.998), topic (0.963), sentiment (0.903), and formality (0.873) are all highly linearly readable — but demographic identity is not, collapsing to chance once topic is partialled out, and z leaks identity LESS than the raw text would.
signal · Brier 0.186A codex loop evolving stimuli to break the binding probe found ZERO genuine breaks in 24 candidates: every well-formed, plausible construction leaves the verdict flat, and the only 'breaks' are artifacts the canonicalization checker correctly rejects.
null · Brier 0.238Rate-distortion theory predicts the capacity knee with zero free parameters: one source rate (4.5 bits per token) and one channel capacity (460 bits) place all three measured knees — 2 sentences, ~70 tokens, and the mysterious '15.79' — on a single R(D) curve, each at its own distortion bar.
signal · Brier 0.084An InfoNCE objective separated role-swapped pairs on its training vocabulary yet gained nothing on held-out transfer — the objective was satisfied by lexical shortcuts.
null · Brier 0.218A supervised who-is-the-agent head reached 100% held-out accuracy at every dose, while the transfer battery stayed flat at chance.
null · Brier 0.166Forced to emit an explicit role tuple, the decoder retrieved the agent at 0.998 on order-swapped sentences — yet transfer was exactly chance. The role code is a lexical lookup.
null · Brier 0.062Word-shuffling forced order information into z — the model could reorder a scrambled bag (Kendall-τ 0.45) — yet the linear surface-order probe read order worse than baseline.
twist · Brier 0.180Making surface order perfectly uninformative about role in 40% of the data — with no role objective at all — induced no transferable role code.
null · Brier 0.078Holding the objective fixed and only widening the filler vocabulary, role abstraction EMERGES between 117 and 1000 fillers — novel-word retrieval jumps 0.00 → 0.05 → 0.73.
signal · Brier 0.306Patching filler-token states from the role-swapped sentence flips the decode at 0.95 through layer 22, then 0.00 at layer 24 — a flat-then-cliff commitment, identical in actives and passives.
signal · Brier 0.193Kernel, focal-conditioned MLP, and bilinear probes all null at certified sensitivity — five probe families now agree the states hold no transferable role code, only a perfect surface code.
null · Brier 0.256The order code is strictly filler-local at every depth (0.86–0.96), never spreading to summary positions — refuting the broadcast-before-pooling hypothesis.
twist · Brier 0.129Grammar tokens ("by", "'s", "that") carry no vocabulary-transferring role code — conduits, not stores. Best-calibrated experiment of the campaign.
null · Brier 0.035Tense, number, negation, and question are clean linear, invertible, composable offsets — but voice produces passive form with 0/40 argument swaps. An independent confirmation of the binding gap.
signal · Brier 0.254A single linear direction is a causal, dose-responsive, content-specific negation operator that generalizes templated→natural. Best-calibrated ★ of the campaign.
signal · Brier 0.138The offset operators are a curved field — regional directions rotate 20–25° vs a 3° noise band — but the curvature does not break application: a global offset is good enough for coarse transforms.
twist · Brier 0.179A robustness certificate — SONAR z is nearly ISOTROPIC (mean pairwise cosine 0.068, top PC 3.3%), unlike BERT/GPT, and all four headline claims survive whitening.
signal · Brier 0.193A 44× scale sweep within one fixed architecture and objective — GTR-T5 from 110M to 4.8B, all four scales — leaves every preregistered cell flat: probe ceiling 0.601→0.591, binding at chance throughout, and the possessive code scale can't buy. The ninth NO closes the capacity axis.
null · Brier 0.086Training ORDER governs reconstruction but not structure: at fixed seed, monotone curricula wreck fidelity (val F1 0.11–0.52 vs 0.645 random, order-variance 104× the seed band) via end-of-training forgetting — yet the surface and relational codes are order-robust (within 2× seed).
twist · Brier 0.340Switching the training objective mid-stream reveals a split: reconstruction follows the LAST objective (recency), but the surface-order code is imprinted by the FIRST objective and never overwritten — a formed code sticks even when the objective that formed it is replaced.
twist · Brier 0.421The real boundary isn't grammar-vs-semantics: closed-class MARKER swaps all linearize perfectly (before/after, above/below, in/out, near/far, bigger/smaller — success 1.00), while ARGUMENT swaps hit the exact voice binding wall (0/74). A linear offset can substitute a word; it cannot reverse who-relates-to-whom.
signal · Brier 0.125The linearizing operators form a real vector algebra: summing two single-operator directions equals the directly-fitted double transform (mean additivity 0.982, compose-minus-direct gap exactly 0.000), it works across families, and it commutes perfectly.
signal · Brier 0.139The operator directions don't just describe attribute geometry — they install it: adding α·v steers negation, tense, number, and a spatial marker from 0 to ~1.0 success by α=1, with ZERO off-target collateral, perfect invertibility, and a norm-matched random push completely inert.
signal · Brier 0.158Operators have two separable substrates: the offset DIRECTION is present at initialization (a token-embedding fact, negation cos 0.93 and vertical 0.999 at step 0), while CAUSAL usability is learned, decoder-gated, and installs early and abruptly (step 2000–4000) — in a strict order, with the tense operator never installing at all.
twist · Brier 0.255A toy mean-pooled autoencoder reproduces the whole binding story — bag-lookup beats abstract role below a critical vocabulary, abstraction emerges above it — but the numerical model FALSIFIES the predicted cause: the transition isn't set by data or capacity, it's set by the surviving order-channel's signal-to-noise.
twist · Brier 0.136Formally, mean-pooling contextual states smuggles order through ONE channel: the bag reweighted by each token's average received attention — and word order survives only via the relative-position bias, whose antisymmetric part is the sole who-came-before-whom discriminator, exactly 096's β residual.
signal · Brier 0.121A reusable, validated tool that packages the campaign's most important instrument lesson — certify probe power with a planted signal before trusting a null — with a PASS/FAIL certificate that catches the exact uncertified-probe trap that produced the 051 and 062 false nulls.
signal · Brier 0.115A property-based checker that certifies a labeled stimulus set's slot and label conventions before a probe trusts them — and it catches exactly the real bugs rows 017 and 020 hit, each injected bug flipping only its target property with no false alarms.
signal · Brier 0.005A pre-flight linter for any difference-of-means or offset construction that flags magnitude confounds — and building it surfaced a genuine refinement: norm confounds come in TWO modes, artifact (dies under cosine) and confound (norm-defined but survives cosine), needing different fixes.
signal · Brier 0.031The discipline the whole campaign ran on — frozen predictions, gates, verdict, Brier — extracted into a tested library that reproduces past rows' Brier scores exactly and makes cheating structurally impossible: a certificate hash rejects any post-hoc edit to the predictions.
signal · Brier 0.003An auditable posterior tracker that turns 95 scattered results into aggregate credences: no-linear-role-binding rises to 0.99, operators-compose to 0.96, the 460-bit capacity to 0.89 — while the genuinely mixed claims (multilingual binding, off-manifold fabrication) correctly stay near 0.5.
signal · Brier 0.042A self-contained interactive artifact that lets anyone step through the campaign's five headline phenomena — operator steering, interpolation winner-take-all, capacity overload, fabrication with live monitor flags, and the binding demo — every decode a byte-for-byte recorded campaign output.
signal · Brier 0.035The campaign's reusable assets ship as one runnable, self-certifying benchmark: binding battery + five instrument kits + honesty gates + checkpoint manifest + ledger, with a single entry point that reproduces the flagship no-binding null on CPU, offline.
signal · Brier 0.132Sixty-three rows asked for a follow-up. Only the ones marked covered have had one executed (via consolidation H1/H2/H3). The rest are unfunded ideas, listed with the row's own words.
Follow-up worth funding? Yes, conditionally — 002's dose-response (running) is the direct next probe; if λ=1 aux-QA also fails to transfer, the "shortcut satisfaction" story strengthens and 096 (toy theory) should formalize it.
Follow-up worth funding? Y (redirected). Not "distill from a pooled teacher" (dead — nothing binds under the pool). The live questions this surfaces: (1) does ANY LM state bind roles *before pooling* — probe last-token / per-content-token reps of Qwen2.5-3B on the battery (a mini-051-for-decoders); if yes, distill from the UNPOOLED signal (cross-attention or per-token) rather than a single pooled vector. (2) 059 GTR-T5 base→XXL scale sweep is now the clean way to ask if scale ever induces *pooled* binding — 009 con
Limitations / follow-up - Teacher-forced confound (headline, pre-registered): order is trivially in the input, so this localizes where order/role are linearly+transferably decodable in the decoder residual stream, NOT order *recovery from z alone*. The genuine recovery question needs FREE-RUNNING generation with generated-token alignment — the clean follow-up (worth funding: Y — it would test whether the decay-with-depth reverses when order must be reconstructed rather than read). - Self-attn attribution mean-pools
Follow-up worth funding? Y - 022 entropy-signature and 030 confidence-calibration: the gate-blind high-cosine fabrications (entity-sub at cos>0.99) are the exact cases a token-entropy or decoder-confidence detector must catch — this experiment hands them a labeled positive set (out/labels_v1.json + pairs.json). - 026 decoding-strategy: nucleus>greedy head-start confirmed here (do not over-claim; beam not tested). - 029 audit-v2: run the same corpus through decode-parse+NLI to reconcile the 3.6% (semantic) vs the C4
Follow-up worth funding? Y (targeted) - The headline for the program: entropy ≈ cosine, not additive → a fabrication monitor gains little from stacking them; pick entropy when you want a *decode-time, no-re-encode* flag (086 latent-monitor). - 030 confidence-calibration: per-token-class PAV on these exact scores (does p_top1 calibrate to fidelity?) is the natural next step; 022 hands it out/scores.json (per-token stats + labels). - 087 fail-closed-decoder: an entropy/margin abstention threshold at decode time, ROC
Follow-up worth funding? — Weak Y The clean finding "the decoder does not fail open off-manifold; it fails *closed* into garble except along inter-sentence chords" is a useful safety-relevant map. A worthwhile extension is a sampling-decoder rerun of the chord direction only (where fabrication concentrates) at fine dose spacing around 0.35–0.6, to see whether sampling widens the fluent-wrong shoulder that greedy suppresses. Lower priority than the 024/086 prior-implausibility detector thread.
Follow-up worth funding? Y The "original token is prior-implausible (rank 762)" signature is a candidate fabrication *detector feature* orthogonal to entropy (022) and cosine — worth adding to 086's monitor ensemble and testing on 023's off-manifold fabs (where fabrication is dialled up). Also: does steering z toward the prior's preferred token (025 fabrication-axis) reproduce these substitutions?
Follow-up worth funding? Y (weak-moderate). (1) Width sweep h∈{8192,16384,32768,65536} (all on box) — does the length/density difficulty axis persist and does m90 scale with width? feeds 044 splitting-absorption / 045 k-atom-curve. (2) Residual probing (043): probe the SAE residual (the lossy 0.45) for length/surface — is the un-reconstructed part exactly the length/rarity signal? (3) Density-controlled fabrication: does the recon↔fabrication link survive length control (partial correlation)?
Follow-up worth funding? Y (narrow). The NLI/decode-then-verify path is decisively refuted for TAE monitoring — do not pursue sentence-level NLI. The failures are all slot-level (entity/number/role), so a targeted structured-slot checker (extract (agent,verb,patient,numbers,named-entities) from orig and recon, compare slots) is the mechanistically-indicated next auditor — connects to 086 (latent-monitor) and the binding-program's who-did-what focus. The standing lesson stands reinforced: no cheap post-hoc auditor r
Follow-up worth funding? Y (narrow). Feed the PAV-recalibrated confidence + the graded risk-coverage curve directly into 087 (fail-closed decoder) as the abstention primitive — the honest lever is coverage tradeoff, not a precise fab gate. The under-confidence finding suggests temperature/label-smoothing recalibration of the decoder itself could sharpen p_top1, but the ceiling is low (raw Brier ≈ base rate).
Follow-up worth funding? Y (narrow) Voice is the cleanest generative probe yet of the binding gap: fit the passive offset, apply, and measure argument-order fidelity as a scalar. Feeds 034 (negation operator — here 1.00, causally steerable next), 064 (translation-as-offset), 079/081 (operator composition/emergence across rungs), 080 (causal steering along these directions). The diff_align diagnostic is a cheap pre-screen for "is transform T a linear operator" without any decoding.
Follow-up worth funding? Y (narrow). - The negation direction as a latent monitor / steering primitive (feeds 080 sonar-causal-steering, 086 latent-monitor): a single vector whose addition provably flips a semantic property. - diff_align again pre-screens linearity (0.65 natural vs 0.84 templated predicts the mild degradation) — cheap "is T linear" gauge, consistent with 033. - Dose-optimum >1.0 for natural text (offset under-scaled) is a general lesson for latent operators fit by mean-difference on short templates
Follow-up worth funding? Y (narrow). The operator field is provably curved (a global offset mis-serves length extremes by ~18°) yet application-robust at this scale — so curvature matters for *precision* steering / larger edits, not for coarse transforms. Worth: (1) test whether curvature breaks application at LOWER cosine budgets or for the HALF-operators (voice arg-swap, 033) where headroom exists; (2) a length-conditioned (curved) offset vs global for long-text steering (feeds 080); (3) parallel-transport the of
Follow-up worth funding? Weak-Y (narrow). - The norm↔specificity link is the only positive: worth a clean confirm with proper NE tagging + a controlled rare-word-injection stimulus (does adding a rare proper noun raise ‖z‖ at fixed length?) — connects 066 bits-accounting (norm as a crude bits gauge) and 070/071 numeric/entity fidelity. - The scale-invariance result is a useful negative primitive for steering work (080/082/086): attacks/edits should move *direction*, not magnitude; a magnitude-only perturbation is a
Follow-up worth funding? Weak-Y (as a certificate, not a new hunt). The valuable output is the certificate itself: *SONAR z is near-isotropic, so campaign geometry results are not basis-artifacts, and the correct confound to police is norm-scale/raw-Euclidean density (036 lesson), not classic anisotropy.* Narrow extensions: full ZCA-whitening stress test (does inflating tail dims break anything?) and re-running 040 (whitening-robustness) can now cite this μ+PC fit as the shared normalization.
Follow-up worth funding? Weak-Y. The clean negative (depth-partitioned dictionary, near-zero shared atoms) is itself informative and the z-reconstruction-improvement-under-shared-encoding is a genuine lead. A tighter re-run (match the 028 corpus + h/k so z-FVU lands in 0.44–0.55; add a real coherence judge; sweep the share threshold τ) would firm up whether ANY concepts persist across depth or whether SONAR's dictionary is strictly stratified. Not urgent.
Follow-up worth funding? Y (narrow) (1) Row 043 residual-probing is already queued and directly extends this: WHAT information lives in r (probes for length/topic/register/syntax). (2) A properly powered residual dictionary probe (larger h, aux-k, more epochs, power-certified on x first) to settle P1's open question. (3) The 042 finding reframes the 041–050 block: at FVU ~0.7 the SAE dictionary explains a minority of sentence content on generic text — worth one row testing whether campaign-corpus FVU 0.44 vs pile 0
Follow-up worth funding? Y The dictionary misses most probe-readable content at k=32 — a k/width-sweep of "probe recovery vs FVU" (does the residual's probe content vanish as FVU→0, or plateau?) would say whether SAE dictionaries systematically privilege some feature types (topic vs length vs lexical) — directly relevant to interp claims that SAE features "explain" the representation.
Follow-up worth funding? Y (modest) Row 045 (k-scaling at fixed h) is already queued and is now the decisive arm: if FVU/residual content is also k-invariant, the SAE objective itself caps readable content; if k buys it back, the 042/043 residual is "content beyond the top-k budget", which reframes all w40-family dictionaries. Also cheap and worth it: one activation-correlation rerun of the novelty matcher (fixes the gated cell with data already on the box).
Follow-up worth funding? Y Two forks: (1) TRAINED k-ladder (k ∈ {64,128,256} same recipe, ~min/train at h16384) — does trained k=128 close the decode gap that inference-k cannot, or does FVU-vs-content dissociate there too? (2) The FVU/chrF dissociation itself: what do rank-33-128 atoms add that decoders love but L2 hates? (candidates: low-norm content directions vs high-norm scaffold; connects 036 norm-semantics.)
Follow-up worth funding? Y (narrow). 1. The graded matcher (margin / profile-corr instead of saturated argmax-identity) is now the right instrument for the typology gradient AND for re-running 044's gated novelty cell (activation-correlation across widths/seeds) — data already on the box. 2. The centering-resistant ~19% exclusive core (557-atom union): are these script/tokenizer detectors or content? Cheap: top-activating FLORES sentences per exclusive atom.
Follow-up worth funding? Y (one specific). PCA-50 > SAE off-distribution (this corpus AND 043's battery FVU 0.826) suggests the SAE's advantage over cheap global bases is pile-specific — a small "FVU vs corpus" grid (pile/FrameNet/battery/FLORES × {SAE, PCA-k, frame/label bases}) would say whether the dictionary's variance story generalizes at all. The abstract-vs-concrete frame split (b) is also a clean handle on WHAT KIND of meanings atoms are (046 follow-up: content vs topic).
Follow-up worth funding? Y (modest) The 4000→26000 gap hides where the last quarter of atoms locks in; the ladder trainer saves F1-crossing milestones, so a cheap rerun of rung A with log-spaced step ckpts (shape B-style dense trajectory, ~70 min GPU) would resolve the tail and test the flicker/"final-only" 25%. Also: the untrained-encoder atom inventory (~16% of ceiling, 0.31 of frequent quartile) is a clean handle on "what SAEs find that isn't learned" — worth cross-referencing with 047's topic-selectivity labels
Follow-up worth funding? Y (narrow). 1. The 40%-semantic / 40%-surface per-atom split: rerun semantic index with PAWS pairs stratified by shared-content-word count, or with role-swap minimal pairs (061/062 battery) to isolate proposition-level atoms from topic atoms — directly tests whether ANY atom encodes structure rather than field. 2. In-domain low-overlap paraphrase cell (backtranslation of the same PAWS sentences) to confirm the "rewording ≡ translation" equivalence without the QQP domain confound.
Follow-up worth funding? Y (narrow). The instrument-failure is itself the finding and it directs the next steps: (1) row 053 role-retrieval prompts to try to lift the within-construction ceiling above 0.9 (restore power) before re-asking the binding question; (2) larger sentence embedders to test whether the weak-role regime is capacity-bound; (3) row 052 (LASER/LaBSE MT objective) as pre-registered. Until a small embedder passes the positive control, "no binding in small embedders" stays uncertified.
Follow-up worth funding? Y (narrow). (1) Pooling-swap control (attention-pool LASER's states / max-pool SONAR's) to isolate the decoder-objective vs pooling contribution to the SONAR regime. (2) The LaBSE lexically-anchored possessor cell (0.986) deserves promotion into the battery as a named cell ("content-addressed binding") — it is the first non-SONAR encoder to pass the s↔of positive control. (3) German case-binding is now SONAR-specific: test NLLB-encoder (SONAR's parent) on the 061 battery to locate where it
Follow-up worth funding? Y (narrow): (i) battery on states at position k>1 under role-relevant multi-sentence contexts (tests planning pressure properly); (ii) role-diagnostic probe pairs with novel subjects to fix the forced-choice instrument; (iii) denoiser tower depths. As a cheap fold-in, not a new flagship row.
Follow-up worth funding? Y (narrow, fold-in) One cell, not a row: run R-decl-incongruent + QA-objrel on one strong modern reranker (bge-reranker-v2-m3 or an LLM judge-scorer) to test whether the below-chance surface inversion is a MiniLM-capacity artifact or a general property of relevance-trained cross-attention; plus promote the objrel QA inversion into the battery as a standing behavioral cell.
Follow-up worth funding? Y — the human study itself. STUDY_DESIGN.md is runnable as written (~$1,000, N=200 recruit / 160 analyzed, Prolific + jsPsych). It is the single missing anchor for the whole 051–060 arc: it decides whether "embeddings don't bind roles" is a deviation from human similarity or a faithful model of its casual regime. Everything else in the arc is now bottlenecked on that anchor, not on more encoder cells.
Follow-up worth funding? Y (narrow, breaker-first). 1. Breaker on German before any promotion: MLP readout; more orders (German OVS variants, scrambled subordinate clauses); does the signal survive a null where case markers are swapped to break der↔den? Is 0.668 an artifact of the article being a separable adjacent token (bag-of-words "den+Noun")? → feeds 062 (crosslingual-role-transfer), 073. 2. Morpheme-separability hypothesis as a first-class claim: predict binding strength from how free-standing the case expone
Follow-up worth funding? Y (two narrow threads). 1. Transfer-cell redesign that can extrapolate: score RELATIVE codes instead of focal-canonicalized absolutes — e.g. probe on swap-pair differences z(AB)−z(BA) (label = which of the two orders is agent-first for the SAME noun pair), which is vocab-general by construction; then rerun the crosslingual matrix. This is the fix that lets the row's actual question be answered. 2. Japanese is now the binding thread: 0.696 across two disjoint lexicons is the strongest order-
Follow-up worth funding? Y (narrow). 1. Row 064 (language-vector) is now sharpened: the offset is removal-safe and removal-HELPS near the knee — test the reverse direction (adding μ_L − μ_eng to an English z: does it translate? at what fidelity cost vs token-switch translation?). 2. Script-fair fidelity metric (word/morpheme-level or punctuation-normalized) to de-confound the CJK level tax; cheap re-analysis of the saved decodes. 3. The "centering frees capacity past the knee" effect (+5 chrF for deu/tur/jpn) as a
Follow-up worth funding? Y (narrow). 1. What IS the 91% residual? It is sentence-specific but averages to ~0: test whether it is (i) encoder noise (re-encode paraphrases), (ii) content-language interaction (probe residual for POS/morphology), or (iii) chrF-invisible register/style. 2. 065 midpoint tie-in: the no-code-switching winner-take-all here says decoder output language is discrete in the token — 065 should test WITHIN-z mixtures (interpolate z_eng↔z_deu of the SAME sentence, fixed token) instead of adding v.
Follow-up worth funding? Y (narrow). 1. The p2 leak channel: what exactly survives in the 36%-mixed clause-switch decodes (function words? seam-local material?) — the only place SONAR emits mixed text; cheap re-analysis of saved decodes. 2. Encoder-token dose on mixed input: cos(mat,emb) 0.60–0.85 says the source token matters ~10× more for mixed than pure input — measure properly with monolingual wrong-token baselines (one encode pass). 3. Preservation gradient deu>tur>jpn (script distance): test with Latin-script
Follow-up worth funding? Y (narrow). 1. Prereg the specific-bits ladder properly: random non-adjacent cross-domain mismatched z, item-level pairing, all 6 langs — freeze the ceiling + knee criteria on THAT curve. 2. "Bits present, decode can't surface": beam/sampling/constrained decode on jpn near the knee (ties 026-decoding-strategy) — can better search recover the chrF the bits say is there? 3. Connect the ~460-bit ceiling to 045's k-atom curve / 028 SAE decomposition: bits-per-atom accounting.
Follow-up worth funding? Y (cheap). (a) Freeze the absolute-τ knee (or a bits-demand knee) as the primary and add d_z ∈ {32, 128} rungs (~3.4 GPU-h) to localize the saturation point of absolute fidelity between 64 and 256; (b) a d_model-widened control (rank ceiling moved to 512) would separate objective from architecture above 256 — the one question this design provably cannot answer.
Follow-up worth funding? Y (narrow). 1. Add a REAL high-perplexity NATURAL tier (code, math notation, dense named-entity text, or non-English transliterated) to get natural per-token separation ≥1.5 bits and score P4 cleanly on non-artificial text — the RAND result predicts a leftward natural knee too. 2. Fitted-changepoint knee + bootstrap CIs on the chrF curves (frozen-criterion knee is coarse); regress knee_tok on measured rate across all 4 tiers (slope ≈ −budget/rate²). 3. Codex-judge the fabrication-vs-omissio
Follow-up worth funding? Y (narrow). 1. Relatedness as a CONTINUUM: regress per-pair R on chrF(A,B)/embedding-sim across many intermediate levels — is there a sharp redundancy threshold or smooth exchange rate between shared bits and stored bits? 2. Capacity-gated position effect dose-response: sweep conj length through the knee and watch the first-clause advantage switch on (ties 066d/068; clean causal handle on front-loading). 3. Operator cost: swap ", and" for "but/or/;/because" (ties 033 composition operators)
Follow-up worth funding? Y (narrow). 1. Length dose-response through the knee at fixed D: sweep context 32→144 tok and watch the D=8/12 survival curve collapse — locate the number-fidelity knee vs the chrF knee (ties 068/069 capacity-gating; is digit loss the *first* thing to go as bits run out?). 2. Digit-position error profile: the leading-digit-preserving / tail-corrupting pattern suggests a positional fidelity gradient inside the number — measure per-digit-position exact rate (are units-place digits lost first?
Follow-up worth funding? Y (narrow, not a new row) (1) push L* higher (80/120 tok) to trace how the matched count-ceiling scales with budget — does ~3 rise linearly with bits like 070's I_spec? (2) matched cells with entity sentence at FIXED position + filler varied, to cleanly separate length-load from entity-count; (3) mixed-rarity items (famous + rare in one z) to re-test rarest-first with real rarity variance (here all ~12 bits, low variance → the null is under-powered); (4) merge-mechanism probe — are two→one
Follow-up worth funding? Y (narrow) (1) Separate object-role from medial-position: put the patient sentence-initial (passive / OSV templates) and re-measure — is it the *object relation* or the *buried position* that dooms it? (2) Formal codex neutral judge (~100) on ACTION-paraphrase and PATIENT-merge calls to tighten the lower bounds. (3) Push the same 6-role ladder with a bit-budget x-axis (not K) to place each role's half-survival demand on the common 460-bit scale. (4) Object-collapse mechanism: is the repeate
Follow-up worth funding? Y (modest) A cheap retrain of A_D (the exact anti-transfer organism) with log-spaced milestone ckpts through 11%→100% (~1 GPU-h) would (a) remove the A_P90 arm caveat and (b) resolve whether the mid-training rise has any fine abrupt structure hidden in A_D's coarse tail. The locked surfX↔roleXflip co-movement is a clean handle for a causal test: ablate the linear surface-position direction at each milestone and check whether role within-ceiling survives (does role readout depend on the posi
Follow-up worth funding? Y (modest) Two cheap extensions would sharpen this into a promotable claim: (1) repeat the seed atlas at one higher rung / larger d_z (~6 GPU-h) to test whether "stable up to rotation" is a property of this bottleneck or of ladder-TAEs generally — if the aligned-cosine recovery and the invariant list survive a capacity change, the anatomy claim strengthens sharply; (2) the number-operator anomaly (diff_align 0.35, aligned recovery only 0.59) is a clean handle on "which linguistic operators
Follow-up worth funding? Y-modest. The reconstruction path-dependence is a clean, mechanistic recency/forgetting result that a 1-GPU-hour follow-up could sharpen: (a) mid-vs-final checkpoint anatomy for a curriculum arm (does the *relational* code peak-and-hold while reconstruction peaks-and-forgets? the best-f1 milestones suggest yes); (b) a replay/interleave control to confirm the effect is terminal-recency, not curriculum per se; (c) does a length curriculum with a *balanced* final phase recover val_f1 to the 0.
Follow-up worth funding? YES (narrow). The surface-code first-objective imprint (surfX m>1, ‖z‖ m≈0.7) is the surprising, block-I-enriching result and deserves a 2-seed × 2-switch-fraction confirmation plus a layer/step trace of WHEN the surface code freezes (ties to 073's "forms mid-training"). The recency-of-reconstruction result is already well-supported (076+077) and does not need more runs.
Follow-up worth funding? Y — natural-sentence dose-response (where the over-steer break should reappear, per 034) + push α past 2 to localize the fluency break-point + steer a CLOSED-CLASS marker on natural text. The causal claim is now clean at T3; a natural-text replication with the codex fluency gate would be the promotion path above T3.
Follow-up worth funding? Y (modest). The sharp result — causal installability is decoder-gated and tense never installs — invites: (1) does a stronger decoder (SONAR-scale ladder or more dec_layers) rescue tense's causal steerability, or is tense's linear offset fundamentally non-causal (probing the 078 binding wall from the time axis)? (2) a finer log-spaced A_D milestone retrain to pin the decoder-onset step exactly and test whether negation/vertical install at the SAME decoder-competence threshold (ceiling≈0.5)
Follow-up worth funding? Y (narrow): (1) codex neutral-judge cross-check to promote above T3; (2) natural (non-templated) sentences — does the negation/entity cost ordering hold off-manifold?; (3) a *logical-flip-aware* auxiliary probe (negation/quantifier direction) as the missing orthogonal check the cosine gate needs.
Follow-up worth funding? Y (narrow): (1) load the real w40 SAE and test the SAE-residual carrier specifically (does dictionary structure raise or lower detectability?); (2) natural (non-templated) sentences — does the ~100-bit capacity and the nn-cos AUC hold off-manifold?; (3) an *adaptive* payload that minimises off-manifold nn-cos deviation (project onto the data manifold's tangent) — the true worst-case for a manifold monitor, to size the residual undetectable capacity.
Follow-up worth funding? Y (narrow, feeds 085). The clean positive here sharpens 085: role-swap alone does not break retrieval, so 085 should test whether a distractor that is topic/surface-closer to the query BUT role-wrong can beat the role-correct canary — i.e. can surface similarity overpower the +0.16 role margin? Also: heavier/cross-lingual paraphrase queries and a natural-text canary corpus to see where the role margin finally collapses.
Follow-up worth funding? Y (narrow). (1) Re-run with 084's tightly-matched paraphrase query as the incumbent to report the flip threshold against the full +0.159 role margin directly (predict ≈2 words). (2) Natural-corpus base rate: how often do real passages carry a role-wrong sentence with incidental surface overlap to the query? (3) The defensive fix: a role/agent-consistency check between query subject and retrieved-passage agent as the orthogonal guard the cosine retriever lacks (ties to 082's "cosine needs a
Follow-up worth funding? Y (narrow): (1) tangent-adaptive covert payload (083 follow-up) vs the decode- consistency check — size the truly-undetectable capacity; (2) natural (non-templated) sentences — does the re-encode floor loosen enough that cos_ref stops dominating the primary?; (3) a learned (not prototype) logical probe to lift negation AUC above 0.85 in the paraphrase-admitting regime.
Follow-up worth funding? YES (small): pair the density gate with a round-trip-consistency gate and re-run the tradeoff — hypothesis is that density ∧ round-trip closes both the off-manifold AND the interpolation doors while still keeping clean+covert. - Caveats: equal 5-category test mix (population fab is a design choice; the density-ordering result is mix-robust but the absolute no-abstention rate is not). Simple templated clean stimuli (low clean-fab baseline). Single seed, single embedder (SONAR). nn-cos densit
Follow-up worth funding? Y (narrow). 1. Memorization dose-response: sweep train-set size / epochs from the STD (0.55) to the MEM (1.0) regime to map AUC vs the 066 recon-fidelity gap — quantify "how much memorization ⇒ how much leakage." Cheap (forward-only, reuse this harness). 2. Two-bank density to test the manifold-density membership hypothesis (031/083) without the bank-distribution artifact. 3. SONAR proper needs a *real* member/non-member corpus (e.g. a known NLLB bitext slice vs a post-cutoff/held-out slice
Follow-up worth funding? Y (as infrastructure, not a study). The kit is now the standing pre-flight for every future probe-vs-representation row: call ppk.certify(Z, y, target_effect, readout, groups) and only report a null if it PASSes. Natural extensions (cheap): (1) an mlp-readout certificate pass for reps with nonlinear-only signal; (2) a helper that maps a real intrinsic AUC back to an equivalent Cohen's d so callers can state "our null rules out effects ≥ d*"; (3) wire it as an assertion into the battery's ve
Follow-up worth funding? Y (narrow) Wire canon_check.certify() as a pre-flight gate into the binding battery itself (load_task could assert it), and extend the item-schema adapter to the ladder/SONAR retained-state probe rows so every future binding probe self-certifies its labels.
Follow-up worth funding? Weak-Y (narrow, cheap). - Re-encode ~40 real 033/078 operator before/after pairs (GPU, seconds) → run the linter on a real operator delta as the PASS anchor (closes the one synthetic gap). - Wire norm_linter.lint_delta as a pre-flight assert into future offset/operator rows (034/046/062/063/064/080) — it is a 2-second import norm_linter call.
Follow-up worth funding? Y (narrow). Give codex the filler-pool + lexical-diversity levers (the 006 axis) as the attack surface and re-run the loop with the full battery + CIs: that is the one place a plausible+well-formed z_bag/STIMULI_INVALID break might actually exist. Absent that, the template-level conclusion (probe + canon_check gate robust to adversarial construction evolution) is a solid T3 instrument-validation result.
Follow-up worth funding? (Y, narrow) Y — wire prereg_engine into the launch/harvest of future rows so the PREREG_LITE emits a PREREG.json (frozen certificate) at launch and RESULT.md's Brier table is generated by Verdict.brier_table() at harvest. Cheap, and it makes the "score exactly as frozen" rule mechanical rather than manual. Sibling of the 090/091/092 kits; block-L instrument suite now covers probe-power, canonicalization, norm-linting, and (this row) the prereg/Brier method itself.
Follow-up worth funding? (Y — narrow) Y: (1) wire the ledger into harvest so each new row auto-appends its Evidence (row + Brier + one-line direction) and the posteriors update mechanically — the campaign's live scoreboard. (2) Replace analyst strength labels with a rule that reads effect size + gate outcome directly from out/results.json (removes the one subjective step). (3) A proper independence discount (down-weight correlated rows within a block) would let C1 report an honest sub-clamp posterior.
Follow-up worth funding? Yes, conditionally. Corrected, falsifiable prediction for the real system: 006's transition location is governed by the strength of the residual order/position signal that survives pooling (β in the toy), and is roughly insensitive to both training-token count and bottleneck width — the opposite of a naive capacity story. Discriminating experiments: (i) a data sweep at fixed capacity should NOT move 006's knee (toy: T-independent); (ii) a bottleneck-width sweep (ties to 067) should also NOT
Follow-up worth funding? Yes, narrow. Cheap, sharp real-SONAR test of the two robust claims: (i) extract encoder contextual states (011–020 rows already did this), mean-pool, and show order recovery is per-instance yes / global linear axis no (the cross-pair AUC≈chance vs within-bag high contrast) — a direct check of the content-entanglement mechanism; (ii) confirm the surviving-order subspace is low-rank (top-few PCs of z−bag over shuffles capture the order variance) and small-amplitude, tying its strength to 096'
Follow-up worth funding? Y (narrow, cheap). 1. Compute δ(D) explicitly: derive the recall-0.85 and chrF-0.8× budgets from a distortion functional on the 066/068 I_spec curve, turning the empirical 0.41 / 0.78 into a predicted R(D). 2. Re-decode the anatomy capacity cell to get its true sentence length distribution (closes the P6 soft joint) and a full v2 CI/bimodality flag on 15.79 (still owed per the ladder prereg). 3. Regress knee_tok on measured rate across 068's four tiers (slope ≈ −C_D/r²) as a direct R(D) tes
Follow-up worth funding? Y (low cost) — this is the campaign's public face; worth (a) precomputing a live-ish "type your own sentence" path if an in-browser SONAR shim ever exists, and (b) adding the 034 negation-operator and 083 stego demos. But as-is it already covers the five headline phenomena end-to-end.
Follow-up worth funding? Y — (i) refactor the battery's per-cell readout to release memory (process isolation or explicit del + gc), enabling the full SONAR sweep; (ii) extend the --encoder hook to more models; (iii) promote the flagship null past T3 with an independent breaker pass.