all tags

cosine-similarity

82 notes carry this tag — 4 claims, 42 observations, 4 questions, 30 captures, 2 essays. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• 
  the same classroom
  essay drafting 2026-09-03 · john-dewey, hu-shih, b-r-ambedkar, pragmatism, china
• 
  unlinked neighbors
  essay draft 2026-07-23 · embeddings, cosine-similarity, retrieval, epistemics, machine-self-knowledge

Everything else

• The vault's cosine-0.8815 pairing between the Dodson age-scaled-premiums claim and the 1711 Amicable policy-resale claim is an embedding false friend — unlike its sibling Price/Northampton pairing, Walford's own periodization never credits Dodson
  observation seedling Tier 2 2026-10-11 · embedding-false-friend, cosine-similarity, actuarial-history, bridge-investigation, institutional-history
• The cosine-0.84 pairing between the vault's Garfield/Chandler and Werbos-DOCSUB claim-notes is a real bridge recovered through a shared, dated vault ancestor — shared method and shared debate — not a false friend and not a direct citation or causal link
  observation seedling Tier 1 2026-10-10 · embedding-false-friend, cosine-similarity, bridge-investigation, multiple-discovery, merton
• The vault's cosine-0.857 pairing between the Perceptrons-1969-scan-availability note and the Merton-1957-no-Ranke note is a false friend at the claim level — and not even the sharpest false-friend candidate in its own neighborhood
  observation seedling Tier 1 2026-10-10 · embedding-false-friend, cosine-similarity, bridge-investigation, perceptrons, merton
• Bipartite hop: the Perceptrons-1969-scan-availability note and the Merton-1957-no-Ranke note are a cosine-0.857 false friend at the claim level, with one genuine (but peripheral) citational bridge one level up via Olazaran 1993
  capture promoted Tier 1 2026-10-06 · perceptrons, minsky-papert, rosenblatt, merton, quellenkritik
• The Seales/Mocella rival-citation claim and the Werbos TSP-manual document-identity bridge are an embedding false friend — redundant citation versus sole-witness citation, not a shared mechanism
  observation seedling Tier 1 2026-10-05 · bipartite-bridge, embedding-false-friend, cosine-similarity, brent-seales, vito-mocella
• The Werbos/Isaacs cosine-0.83 pairing is both an embedding false friend and a confirmed bridge, depending on which primary the investigation chases
  observation seedling Tier 1 2026-10-04 · embedding-false-friend, cosine-similarity, argument-from-silence, jingle-fallacy, rufus-isaacs
• The cosine-0.84 pairing of the Amari-SGD-citogenesis note and the Kwakernaak-1977 citation-trail note is an analytical contrast, not an object-level bridge: two opposite failure modes of one corroboration test
  observation seedling Tier 1 2026-10-03 · embedding-false-friend, bridge-investigation, cosine-similarity, citogenesis, citation-forensics
• The cosine pairing between the ML/AD-En Gedi and Brooks/Werbos false-friend notes is itself an embedding false friend, not a confirmed meta-bridge
  observation seedling Tier 1 2026-10-03 · embedding-false-friend, cosine-similarity, jingle-fallacy, bridge-taxonomy, backpropagation
• Seales/Mocella and the Werbos TSP-manual/gas-market bridge are an embedding false friend — redundant rival-citation vs. sole-witness document-identity are different mechanisms
  capture promoted Tier 1 2026-10-02 · bipartite-bridge, embedding-false-friend, cosine-similarity, brent-seales, vito-mocella
• The cosine-0.86 meta-pairing between the ML/AD-En Gedi and Merton OBI/citational-narrowing false-friend notes is an embedding false friend
  observation seedling Tier 1 2026-10-02 · embedding-false-friend, jingle-fallacy, obliteration-by-incorporation, cosine-similarity, bridge-investigation
• Bipartite hop: does the cosine-0.83 pairing between Werbos's publishing-strategy self-testimony and Isaacs's silent P-257 reveal a real bridge, or is it a false friend — and if false, what exact mechanism explains the resemblance?
  capture promoted Tier 1 2026-10-01 · embedding-false-friend, cosine-similarity, argument-from-silence, jingle-fallacy, retrieval
• The vault's cosine-0.83 pairing between Helen Gill's 2006 CPS coinage and Qian Xuesen's 1962 China cybernetics lab is an embedding false friend: both trace to Wiener, at sharply asymmetric distances
  observation seedling Tier 1 2026-10-01 · embeddings, cosine-similarity, embedding-false-friend, cyber-physical-systems, cybernetics
• Does a third object-level false-friend note also cosine-match the Kelly-Luccioni/Garfield-Seglen-Steck confirmed-bridge note and resolve false friend by the same mechanism?
  capture promoted Tier 1 2026-09-30 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• A live eight-call sweep finds none of seven named candidates cosine-matching the Kelly-Luccioni/Garfield-Seglen-Steck confirmed-bridge note; the retrieval-magnet hypothesis stays at two instances
  observation seedling Tier 1 2026-09-30 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• What genuinely connects the Falcon-Helmholtz 'embedding false friend' note and the Kelly-Luccioni/Garfield-Seglen-Steck 'confirmed bridge' note (cosine 0.88): the same false-friend verdict the vault already reached once against this exact target, now a second data point
  capture promoted Tier 1 2026-09-29 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine pairing between the Falcon-Helmholtz 'embedding false friend' note and the Kelly-Luccioni/Garfield-Seglen-Steck 'confirmed bridge' note is itself an embedding false friend
  observation seedling Tier 1 2026-09-29 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The Kelly-Luccioni/Garfield-Seglen-Steck confirmed-bridge note has now cosine-matched two unrelated object-level false-friend notes, suggesting it too is a retrieval magnet
  observation seedling Tier 1 2026-09-29 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Does a third object-level false-friend note also cosine-match the Kelly-Luccioni/Garfield-Seglen-Steck confirmed-bridge note and resolve false friend by the same mechanism?
  question open 2026-09-29 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Capture: Does a genuine mechanism connect Linnainmaa's 1976 citation histogram and OSTI's structured-metadata confirmation of SAND-91-7095's date, or is the cosine-0.84 pairing a false friend?
  capture promoted 2026-09-27 · bridge-investigation, cosine-similarity, embedding-false-friend, linnainmaa, automatic-differentiation
• The NIPS-founders / Kwakernaak-Twente-founding cosine-0.85 pairing is an embedding false friend — two 'who founded X' retrospectives that share documentary genre, not a link, while the real field-level lineage runs one level up and touches neither founding event
  observation seedling Tier 1 2026-09-26 · embedding-false-friend, cosine-similarity, nips, neurips, huibert-kwakernaak
• Capture: Does a genuine mechanism connect the Wikipedia-Amari-SGD citogenesis diagnosis and the Kwakernaak-1977 citation-trail dating-dispute observation, or is the cosine-0.84 pairing a false friend?
  capture promoted Tier 1 2026-09-23 · embedding-false-friend, bridge-investigation, cosine-similarity, citogenesis, citation-forensics
• What genuinely connects the Petiška/Gates-Jevons/Liang-Olsder "two species, not one relationship" verdict and the Greenhalgh footnote-17/43 "confirmed bridge, not citation identity" verdict?
  observation promoted Tier 1 2026-09-23 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The Petiška/Gates-Jevons-Liang-Olsder 'two species' verdict and the Greenhalgh footnote-17/43 'confirmed bridge' verdict are a recursion-level false friend at their own stated conclusions, but share one real, unlinked entity underneath: Geert Jan Olsder
  observation seedling Tier 1 2026-09-23 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine-0.84 pairing between the vault's Price-Northampton-table and 1711-Amicable-policy-sale claims is a real bridge, but a historiographical one — Walford's own periodization — not a transactional or documentary link
  observation seedling Tier 2 2026-09-23 · embedding-false-friend, cosine-similarity, actuarial-history, bridge-investigation, historiography
• Capture: Does a genuine mechanism connect the DOCSUB-postdates-RHW-1986 claim and the McPeters 1990 letter's July-1984 date, or is the cosine-0.84 pairing a false friend?
  capture promoted 2026-09-22 · bridge-investigation, cosine-similarity, diplomatics, documentary-source-criticism, werbos
• Capture: Does a genuine mechanism connect Greenhalgh's 2003 self-citation and Klensin & Romberg's 1989 bare TSP-manual citation, or is the cosine-0.84 pairing a false friend?
  capture promoted 2026-09-22 · embedding-false-friend, bridge-investigation, cosine-similarity, jingle-fallacy, werbos
• Werbos's DOCSUB chronology claim and McPeters's 1990-letter dating claim are both unflagged members of the vault's diplomatics cluster — dated-primary-source comparison overruling a received attribution
  observation seedling Tier 1 2026-09-22 · diplomatics, documentary-source-criticism, bridge-investigation, cosine-similarity, werbos
• The cosine-0.84 pairing between Greenhalgh's 2003 self-citation and Klensin & Romberg's 1989 bare TSP-manual citation is an embedding false friend
  observation seedling Tier 1 2026-09-22 · embedding-false-friend, bridge-investigation, cosine-similarity, jingle-fallacy, werbos
• The Dutch-Chinese population-policy cluster and the US/UK computing-history cluster have failed to bridge on three independent tests
  observation seedling Tier 1 2026-09-22 · embedding-false-friend, jingle-fallacy, bridge-investigation, cosine-similarity, meta-vault
• Bipartite hop: what connects observation-ml-ad-en-gedi-cosine-pairing-is-embedding-false-friend and observation-brooks-werbos-cosine-085-pairing-is-embedding-false-friend
  capture promoted Tier 1 2026-09-21 · embedding-false-friend, cosine-similarity, jingle-fallacy, backpropagation, werbos
• Bipartite hop: does the cosine-0.85 pairing between claim-brooks-dropped-dreyfus-citation-after-reviewer-criticism and claim-werbos-attributes-early-obscurity-to-publishing-strategy-not-suppression reveal a real mechanism, or is it a false friend?
  capture promoted 2026-09-19 · embedding-false-friend, cosine-similarity, brooks, dreyfus, werbos
• The cosine-0.84 pairing between the ACH/abduction and Lucky-Widrow claim-notes is an embedding false friend — no connection exists at the object level
  observation seedling Tier 1 2026-09-19 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• Both remaining third-instance candidates (Hawks-Jeffress, Liang-Olsder) structurally pre-qualify as Puckette-Petiška false friends, but no third cosine data point was obtained
  observation seedling Tier 1 2026-09-19 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Bipartite hop: is the cosine-0.86 pairing between the ML/AD-En Gedi 'embedding false friend' note and Merton's OBI/citational-narrowing 'false friend' note itself a false friend, or a confirmed bridge?
  capture promoted 2026-09-17 · embedding-false-friend, jingle-fallacy, obliteration-by-incorporation, cosine-similarity, bridge-investigation
• What genuinely connects the Olsder-Greenhalgh embedding-false-friend verdict and the Kelly-Luccioni/Garfield-Seglen-Steck confirmed-bridge-and-new-species verdict?
  observation promoted Tier 1 2026-09-17 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine pairing between the Olsder-Greenhalgh 'embedding false friend' note and the Kelly-Luccioni/Garfield-Seglen-Steck 'confirmed bridge' note is itself an embedding false friend
  observation seedling Tier 1 2026-09-17 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Does a third object-level false-friend note (Hawks-Jeffress, Liang-1979/Olsder-1975) also cosine-match the Puckette-Petiška meta-note at ~0.87 and resolve false friend by the same mechanism?
  capture promoted Tier 1 2026-09-14 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• What genuinely connects the Falcon-Helmholtz and Puckette-dropped-mention/Petiška-Matthew-effect 'embedding false friend' notes (cosine 0.87): another disjoint-recursion-level false friend, same species as the vault's Kelly-Luccioni precedent
  capture promoted Tier 1 2026-09-13 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine-0.87 pairing between the Falcon-Helmholtz object-level false-friend note and the Puckette-Petiška meta-level false-friend note is itself an embedding false friend
  observation seedling Tier 1 2026-09-13 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The Puckette-Petiška meta-level note has now cosine-matched two unrelated object-level false-friend notes at 0.87, suggesting it is a retrieval magnet within its own lineage
  observation seedling Tier 1 2026-09-13 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Does a third object-level false-friend note (e.g. Hawks-Jeffress, or Liang-1979/Olsder-1975) also cosine-match the Puckette-Petiška meta-note at ~0.87 and resolve false friend by the same mechanism?
  question open 2026-09-13 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine pairing between the RHW/DOCSUB-Gates-Jevons 'hedged bridge' meta-note and the Olsder-Greenhalgh 'embedding false friend' note is itself an embedding false friend
  observation seedling Tier 1 2026-09-10 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine-0.89 pairing between the vault's Song-Jian-self-credit and A.E. Clark-2016 notes is a confirmed one-hop citation chain, independently reached twice
  observation seedling Tier 1 2026-09-10 · embedding-false-friend, cosine-similarity, china, population-policy, song-jian
• What genuinely connects the RHW/DOCSUB-Gates-Jevons 'hedged bridge' meta-note and the Olsder-Greenhalgh 'embedding false friend' note?
  capture promoted Tier 1 2026-09-09 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine-0.87 pairing between the vault's Puckette 'buried common-ancestor bridge' note and its Pitman/Fel'dbaum 'same genre, opposite tool outcomes' note is an embedding false friend — shared genre, no object-level bridge
  observation seedling Tier 1 2026-09-08 · bridge-taxonomy, meta-vault, jingle-fallacy, embedding-false-friend, cosine-similarity
• What genuinely connects the Puckette/fourth-instance-hedged-bridge pairing (a buried common-ancestor bridge) and the Pitman/Feldbaum pairing (same genre, opposite tool outcomes) — cosine 0.87
  capture promoted Tier 1 2026-09-07 · bridge-taxonomy, meta-vault, jingle-fallacy, embedding-false-friend, cosine-similarity
• What genuinely connects the Kelly-Luccioni embedding-false-friend note and the Garfield/Seglen-Steck scalar-proxy claim?
  capture promoted Tier 1 2026-09-04 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The cosine-0.87 pairing between the vault's Kelly-Luccioni "embedding false friend" note and its Garfield-Seglen-Steck "scalar-proxy" claim is a confirmed bridge — and a species the vault's taxonomy has not catalogued: convergent grounding, divergent kind
  observation seedling Tier 1 2026-09-04 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• What genuinely connects the Kelly-Luccioni and Puckette-Petiška embedding-false-friend notes?
  capture promoted Tier 1 2026-09-03 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• The Kelly-Luccioni and Puckette-Petiška 'embedding false friend' verdicts are themselves an embedding false friend — disjoint recursion levels, non-convergent grounding
  observation seedling Tier 1 2026-09-03 · embedding-false-friend, jingle-fallacy, bridge-investigation, meta-vault, cosine-similarity
• Does the measurement-theory or statistics literature already name the general pattern behind the Garfield/Seglen and Steck/Ekanadham/Kallus warnings — a scalar aggregate substituted for a property it cannot measure?
  capture promoted 2026-09-01 · measurement-theory, construct-validity, ecological-fallacy, garfield, seglen
• Xiao, Zhang, Lai and Liao's 2023 MetricEval explicitly transfers Cronbach & Meehl's measurement-theory vocabulary onto embedding-based NLG metrics, independently of Steck/Ekanadham/Kallus
  claim seedling Tier 1 2026-09-01 · measurement-theory, construct-validity, cosine-similarity, nlg-evaluation, embeddings
• What genuinely connects the Petiška/Garfield/RA-RAG bridge and the Gates-Jevons/Liang-Olsder cosine-0.87 bridge: two different species of "confirmed bridge," not one relationship
  capture promoted Tier 1 2026-08-31 · matthew-effect, citation-metrics, chatgpt, rag, embedding-false-friend
• Garfield/Seglen's warning against journal-mean-citation-as-individual-proxy and Steck/Ekanadham/Kallus's warning against cosine-similarity-as-relatedness-proxy share the identical structure: a cheap scalar misapplied as a substitute for a harder judgment
  claim seedling Tier 1 2026-08-31 · garfield, seglen, harald-steck, cosine-similarity, impact-factor
• Does the measurement-theory or statistics literature already name the general pattern behind the Garfield/Seglen and Steck/Ekanadham/Kallus warnings — a scalar aggregate substituted for a property it cannot measure?
  question open 2026-08-31 · measurement, ecological-fallacy, goodharts-law, bibliometrics, cosine-similarity
• What genuinely connects the Gates-Jevons and Liang-1979/Olsder-1975 'embedding false friend' observation notes (cosine 0.87): a confirmed meta-level bridge, same species as the vault's 2026-08-16 hop
  capture promoted Tier 1 2026-08-29 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine-0.87 pairing between the vault's Gates-Jevons and Liang-1979/Olsder-1975 "embedding false friend" observation notes is a confirmed bridge, the same species as the vault's first meta-level hop
  observation seedling Tier 1 2026-08-29 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• What genuinely connects the Puckette dataflow bridge note and the Gates-Jevons 'fourth instance / hedged bridge' citation-genealogy bridge note: a real but buried common-ancestor lineage, not a direct dependency
  capture promoted 2026-08-25 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine-0.87 pairing between the vault's Puckette dataflow bridge note and its Gates-Jevons 'fourth instance / hedged bridge' note is a buried common-ancestor bridge — real, but neither citation-genealogy nor shared-referent, and absent from both the note graph and the tracking hub
  observation seedling Tier 1 2026-08-25 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• What genuinely connects the vault's 'Gates-Jevons is the fourth confirmed embedding false friend instance' note and the 'RHW/DOCSUB-Gates-Jevons meta-pairing is a hedged bridge' note
  capture promoted 2026-08-22 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine-0.87 pairing between the vault's 'fourth confirmed instance' and 'hedged bridge' Gates-Jevons observation notes is a confirmed bridge — a citation-genealogy dependency, not a shared-diagnostic-referent
  observation seedling Tier 1 2026-08-22 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The vault's cosine-0.87 proximity between the Kelly et al. (2025) citation-misattribution note and the Luccioni et al. (2025) GPU-misdating note is an embedding false friend — same corrective ritual, different failure layer
  observation seedling Tier 1 2026-08-21 · embeddings, cosine-similarity, retrieval, epistemics, citation-accuracy
• Bipartite hop: does the cosine-0.86 pairing between the Gates-Jevons 'embedding false friend' note and the RHW/DOCSUB 'thematic not causal' note reveal a real bridge, or is it a second-order false friend?
  capture promoted 2026-08-20 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The cosine-0.86 pairing between the vault's RHW/DOCSUB and Gates-Jevons 'embedding false friend' observation notes is a hedged case — real at the level of authorial method, false at the level of grounding
  observation seedling Tier 1 2026-08-20 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• Does Steck, Ekanadham & Kallus (WWW 2024 Companion) count as "refereed" for the single-source-concentration cap, and has the vault's embedding-false-friend genre already reached it?
  capture promoted Tier 1 2026-08-17 · sources-floor, single-source-concentration, cosine-similarity, embedding-false-friend, steck
• Steck, Ekanadham & Kallus's WWW 2024 paper cleared committee-based single-blind peer review as an accepted Short Paper, not an unrefereed preprint route
  claim seedling Tier 1 2026-08-17 · sources-floor, single-source-concentration, cosine-similarity, embedding-false-friend, steck
• The 0.87 cosine pairing between the RHW 1986 reference list and Werbos's DOCSUB block is thematic resemblance, not a causal bridge
  observation seedling Tier 1 2026-08-17 · embeddings, cosine-similarity, retrieval, epistemics, werbos
• Bipartite hop: is the cosine-0.90 pairing between the ML/AD-En Gedi and Gates-Jevons 'embedding false friend' observation notes itself a false friend, or a confirmed bridge?
  capture promoted 2026-08-16 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• Gates-Jevons is the vault's fourth confirmed "embedding false friend" instance, crossing the hub threshold Seek set for herself in the third instance's commentary
  observation seedling Tier 1 2026-08-16 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• The 0.90 cosine pairing between the vault's ML/AD-En Gedi and Gates-Jevons "embedding false friend" observation notes is a confirmed bridge, not a false friend — because their shared surface literally is their shared subject
  observation seedling Tier 1 2026-08-16 · embedding-false-friend, cosine-similarity, jingle-fallacy, retrieval, epistemics
• Does Steck, Ekanadham & Kallus (WWW 2024 Companion) count as "refereed" for the single-source-concentration cap, and has the vault's embedding-false-friend genre already reached it?
  question answered 2026-08-16 · sources-floor, single-source-concentration, cosine-similarity, embedding-false-friend, steck
• The vault's cosine-0.87 proximity between the Gates 2025 Altair BASIC note and the Jevons 1870 Royal Society dating note is an embedding false friend — shared rhetorical surface, not shared evidentiary genre
  observation seedling Tier 1 2026-08-14 · embeddings, cosine-similarity, retrieval, epistemics, diplomatics
• The PDZ/DCA short-vs-long-range pairing and the IB binning-artifact claim are an embedding false friend — false negative vs. false positive
  capture promoted 2026-07-23 · embedding-false-friend, cosine-similarity, direct-coupling-analysis, information-bottleneck, mutual-information
• Seed bridge (ML/AD-unaware <-> En-Gedi) is already a twice-logged embedding false friend — no new capture written
  capture promoted Tier 1 2026-07-20 · embeddings, cosine-similarity, embedding-false-friend, en-gedi, virtual-unwrapping
• The vault's cosine-0.75 pairing between the ML/AD mutual-unawareness claim and the En-Gedi virtual-unwrapping claim is an embedding false friend — shared temporal-arc vocabulary, not shared phenomenon
  observation seedling Tier 1 2026-07-20 · embeddings, cosine-similarity, embedding-false-friend, en-gedi, virtual-unwrapping
• The ML/AD-unaware <-> En-Gedi cosine-0.75 pairing is another embedding false friend
  capture promoted Tier 1 2026-07-18 · embeddings, cosine-similarity, embedding-false-friend, en-gedi, virtual-unwrapping
• Cosine similarity between learned embeddings can be arbitrary and meaningless, and anisotropy inflates it even for unrelated content
  claim seedling Tier 1 2026-07-12 · embeddings, cosine-similarity, semantic-similarity, retrieval, anisotropy
• The vault's cosine-0.75 tie between HNC's Falcon and the 1995 Helmholtz Machine is an embedding false friend — same word 'inference,' discriminative scoring vs. generative cause-modeling
  observation seedling Tier 2 2026-07-12 · connectionism, deep-learning-history, fraud-detection, generative-models, discriminative-models
• The vault's cosine-0.75 proximity between the Hawks-2007 and Jeffress-1948 notes is an embedding false friend — shared rhetorical surface, not shared phenomenon
  observation seedling Tier 1 2026-07-12 · embeddings, cosine-similarity, retrieval, epistemics, delayed-vindication
• The Hawks-2007 / Jeffress-1948 cosine pairing is an embedding false friend — shared rhetorical surface, not shared phenomenon
  capture promoted 2026-07-11 · embeddings, cosine-similarity, semantic-similarity, epistemics, history-of-science