{"assessment":{"class":"C","importance":"high"},"audit":{"blind":true,"ended":"2026-11-03T02:10:43.537Z","figures":[{"ci95":[0.4891,0.9935],"drawn":36,"id":"primary","label":"Strong links (exact, close or broad match) on supporting passages that have exactly the right relation","n_eff":5.1,"population":1029,"share":0.9234,"weights":"relation and library"},{"ci95":[0.3979,0.9202],"drawn":48,"id":"S2","label":"Links in a counting relation (exact, close, broad, narrow match or part) on supporting passages that have exactly the right relation","n_eff":8.1,"population":1740,"share":0.734,"weights":"relation and library"},{"ci95":[0.7268,0.9357],"drawn":44,"id":"CS","label":"Central and subject passages whose formalization status is right","n_eff":42.0,"population":1905,"share":0.8615,"weights":"recorded status"},{"ci95":[0.2519,0.8658],"drawn":12,"id":"S3","label":"'Not formalized' on supporting passages that is right (no declaration in the 48 libraries states it)","n_eff":6.1,"population":1236,"share":0.5957,"weights":"article"}],"independent":false,"items":224,"models":[{"model":"claude-opus-5-5","model_name":"Claude Opus 5.5"}],"operator":"jack","run_id":"tierA-batch1-audit","started":"2026-11-02T21:10:01.351Z"},"campaign":"run:loc-tierA-b1b+chal-tierA-b1","licence":{"mapping":"CC0-1.0","text":"CC-BY-SA-4.0"},"pageid":579867,"passages":[{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"420fb907d99c4f50bf6fc3649065adc921d8003554ad41b52ecd00b800c752f1"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #ba342cf6","item":"In-text #ba342cf6","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"bb8bc71d3dca259e5b706c28bc76cdeccb565943d17123e181bca3c5de451eeb","prominence":"subject","quote":{"exact":"Dimensionality reduction, or dimension reduction, is the transformation of data from a"},"quote_capped":true,"section":[],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension.","segments":[{"text":"Dimensionality reduction, or dimension reduction, is the transformation of data from a high-dimensional space into a low-dimensional space so that the low-dimensional representation retains some meaningful properties of the original data, ideally close to its intrinsic dimension."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"c0fc454514e3ed876dc05b917ae640df90b358c7200cb606841ea6f5f71803ad"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #d9f816f4","item":"In-text #d9f816f4","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"74ff949bbad035fa1fae7c3004b23cb9b617a698c0bdb283af58365da81a6c53","prominence":"central","quote":{"exact":"The process of feature selection aims to find a suitable subset of"},"quote_capped":true,"section":["Feature selection"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The process of feature selection aims to find a suitable subset of the input variables (features, or attributes) for the task at hand.","segments":[{"text":"The process of feature selection aims to find a suitable subset of the input variables (features, or attributes) for the task at hand."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"f8f11a97799bc9c6dc7237c9d8c34e6a238d9a40b843c9bdf0315150610d641d"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #6b763194","item":"In-text #6b763194","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"888b98b439a100affef2a49c0a7842a9bbfce7e5a7607f8ae623afca89bfe8ee","prominence":"central","quote":{"exact":"Feature projection (also called feature extraction) transforms the data from the high-dimensional"},"quote_capped":true,"section":["Feature projection"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Feature projection (also called feature extraction) transforms the data from the high-dimensional space to a space of fewer dimensions.","segments":[{"text":"Feature projection (also called feature extraction) transforms the data from the high-dimensional space to a space of fewer dimensions."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"e8a800377926278e7001ea4f6da387f0fb03f139887fefdfb78fcfc11cb4a1ad"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #bc66dd9f","item":"In-text #bc66dd9f","kind":"definition","locations":[{"challenge":"survived","commit":"3dfb8e22b67042b31fac228dee0e1169a1a7820f","confidence":"high","declaration":"IsSelfAdjoint.hasEigenvector_of_isMaxOn","end_line":290,"library":"mathlib","line":276,"location_key":"ac5611b43ed6ba99c4ee1e0b8f3a5b85a79b64cf049ce4d94a081492b1a38832","module":"Mathlib.Analysis.InnerProductSpace.Rayleigh","note":"This is the variational fact behind the passage's maximisation, but the passage defines a map of the data into fewer dimensions, which this declaration never mentions.","pair_key":"3ef7d6c7ead3d8d79b2a7c4332e3ee053e2a7c44d30f6fc163c3287e04ec1ad9","path":"Mathlib/Analysis/InnerProductSpace/Rayleigh.lean","proof_status":"proved","rank":1,"relation":"relatedMatch","repo":"https://github.com/leanprover-community/mathlib4","signature":{"elided":false,"text":"theorem IsSelfAdjoint.hasEigenvector_of_isMaxOn {𝕜 : Type*} [RCLike 𝕜] {E : Type*} [NormedAddCommGroup E] [InnerProductSpace 𝕜 E] [CompleteSpace E] {T : E →L[𝕜] E} : IsSelfAdjoint T → ∀ {x₀ : E}, x₀ ≠ 0 → IsMaxOn T.reApplyInnerSelf (Metric.sphere 0 ‖x₀‖) x₀ → Module.End.HasEigenvector (↑T) (↑(⨆ x, T.rayleighQuotient ↑x)) x₀"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"00859d596ddbcb4ee84d476bc9d164b02769616da52eb6c815e4fa21e9bbe1a7","prominence":"central","quote":{"exact":"The main linear technique for dimensionality reduction, principal component analysis, performs a"},"quote_capped":true,"section":["Feature projection","Principal component analysis (PCA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The main linear technique for dimensionality reduction, principal component analysis, performs a linear mapping of the data to a lower-dimensional space in such a way that the variance of the data in the low-dimensional representation is maximized.","segments":[{"text":"The main linear technique for dimensionality reduction, principal component analysis, performs a linear mapping of the data to a lower-dimensional space in such a way that the variance of the data in the low-dimensional representation is maximized."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"b6ee15a1b9ea0e60c0c67afe15e88b8de081b2898dc498dd13718397bfe9acc9"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #f640bec3","item":"In-text #f640bec3","kind":"theorem","locations":[{"challenge":"sampled_out","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"high","declaration":"LinearMap.IsSymmetric.sum_re_inner_apply_self_le_sum_eigenvalues","end_line":376,"library":"tauceti","line":343,"location_key":"29c3f681c0cfbfcc2c71449baf24a77f26ba041889b594dbc9ea60459bb87f49","module":"TauCeti.Analysis.InnerProductSpace.KyFan","note":"Ky Fan's inequality bounds what any orthonormal family of directions can capture by the sum of the leading eigenvalues; it is an upper bound and claims nothing about how much of the variance the leading eigenvectors actually recover.","pair_key":"2d59c87ef65c5ce0703074265f172791bc2d89f289a0d32f633cd9c26f2142a0","path":"TauCeti/Analysis/InnerProductSpace/KyFan.lean","proof_status":"proved","rank":1,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"theorem LinearMap.IsSymmetric.sum_re_inner_apply_self_le_sum_eigenvalues {𝕜 : Type*} {E : Type*} [RCLike 𝕜] [NormedAddCommGroup E] [InnerProductSpace 𝕜 E] [FiniteDimensional 𝕜 E] {T : E →ₗ[𝕜] E} {n : ℕ} (hT : T.IsSymmetric) (hn : Module.finrank 𝕜 E = n) {ι : Type*} [Fintype ι] {w : ι → E} : Orthonormal 𝕜 w → ∑ i, RCLike.re (Inner.inner 𝕜 (T (w i)) (w i)) ≤ ∑ j with ↑j < Fintype.card ι, hT.eigenvalues hn j"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"cd1121c9f32cfdd69e5261f32a7c9598e64daa37fafb48bf8ce9f58c1e4b623c","prominence":"supporting","quote":{"exact":"The eigenvectors that correspond to the largest eigenvalues (the principal components) can"},"quote_capped":true,"section":["Feature projection","Principal component analysis (PCA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The eigenvectors that correspond to the largest eigenvalues (the principal components) can now be used to reconstruct a large fraction of the variance of the original data.","segments":[{"text":"The eigenvectors that correspond to the largest eigenvalues (the principal components) can now be used to reconstruct a large fraction of the variance of the original data."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"b46dc9af65432a38228dfaaa7000e28155d1c588cf4d108a4e2de5440721b274"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #7455eac1","item":"In-text #7455eac1","kind":"theorem","locations":[{"challenge":"sampled_out","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"medium","declaration":"ContinuousLinearMap.exists_rank_le_nnnorm_sub_eq_singularValue","end_line":129,"library":"tauceti","line":100,"location_key":"7d07493f6da8afcf4d91ef1868a6bc2806684f16a71034aad90a08af902b74e4","module":"TauCeti.Analysis.OperatorIdeal.ApproximationNumber.Attainment","note":"This is the nearest formal analogue of trading dimension for error, as it realises the best approximation by a map of bounded rank, but it mentions no eigenvector span and no data set.","pair_key":"4640b8387e2160e542a49f0cb6359195f04b520a2864e97194c7bead60ce4261","path":"TauCeti/Analysis/OperatorIdeal/ApproximationNumber/Attainment.lean","proof_status":"proved","rank":1,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"theorem ContinuousLinearMap.exists_rank_le_nnnorm_sub_eq_singularValue {𝕜 : Type*} {E : Type*} {F : Type*} [RCLike 𝕜] [NormedAddCommGroup E] [InnerProductSpace 𝕜 E] [FiniteDimensional 𝕜 E] [NormedAddCommGroup F] [InnerProductSpace 𝕜 F] (T : E →L[𝕜] F) (n : ℕ) : ∃ R, (↑R).rank ≤ ↑n ∧ ‖T - R‖₊ = T.singularValue n"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"16dd1153eb1815c9a95090acfce216646c4d387b512756398253bb084fa074aa","prominence":"supporting","quote":{"exact":"The original space (with dimension of the number of points) has been"},"quote_capped":true,"section":["Feature projection","Principal component analysis (PCA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The original space (with dimension of the number of points) has been reduced (with data loss, but hopefully retaining the most important variance) to the space spanned by a few eigenvectors. [citation needed]","segments":[{"text":"The original space (with dimension of the number of points) has been reduced (with data loss, but hopefully retaining the most important variance) to the space spanned by a few eigenvectors. [citation needed]"}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"e4dbb5379806538ad6a480ce3901a0193eaf374996598f9c8f4323be806aae32"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #92ec7ab2","item":"In-text #92ec7ab2","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"1c68647257db47a3e049e46a501d245913e799592164348aac25feac7f8734a5","prominence":"central","quote":{"exact":"NMF decomposes a non-negative matrix to the product of two non-negative ones,"},"quote_capped":true,"section":["Feature projection","Non-negative matrix factorization (NMF)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"NMF decomposes a non-negative matrix to the product of two non-negative ones, which has been a promising tool in fields where only non-negative signals exist,[7][8] such as astronomy.[9][10]","segments":[{"text":"NMF decomposes a non-negative matrix to the product of two non-negative ones, which has been a promising tool in fields where only non-negative signals exist,"},{"ref":"[7][8]"},{"text":" such as astronomy."},{"ref":"[9][10]"}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"32bb6c78b2d6aa9e274e5013e9b77dea28bb633ef0eb04c41bb825e125381b41"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #445b0e7a","item":"In-text #445b0e7a","kind":"construction","locations":[{"challenge":"survived","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"high","declaration":"Matrix.PosSemidef.inner_kolmogorovFeature","end_line":152,"library":"tauceti","line":143,"location_key":"9b6f4093442b8222b4c00eeec0d2fe1a3bc3589859e887553f6ed2ce1fb47cf6","module":"TauCeti.Analysis.PositiveDefinite.Kernel.Kolmogorov","note":"This is the mechanism the passage alludes to, an inner product in a feature space computed by the kernel, but no component analysis is carried out with it anywhere in the universe.","pair_key":"a6eaa46f6c885c0cee9df4d7566cc839d596e9aab9feab8aa5ea822a73d3fbf5","path":"TauCeti/Analysis/PositiveDefinite/Kernel/Kolmogorov.lean","proof_status":"proved","rank":1,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"theorem Matrix.PosSemidef.inner_kolmogorovFeature {𝕜 : Type u} [RCLike 𝕜] {α : Type v} {K : α → α → 𝕜} (hK : Matrix.PosSemidef K) (a b : α) : Inner.inner 𝕜 (hK.kolmogorovFeature a) (hK.kolmogorovFeature b) = K a b"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"31118f53c9e04a7b579d8ec47c9c243fcc0a62b3c5e21ac7adc5e2daf50851a8","prominence":"central","quote":{"exact":"Principal component analysis can be employed in a nonlinear way by means"},"quote_capped":true,"section":["Feature projection","Kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Principal component analysis can be employed in a nonlinear way by means of the kernel trick.","segments":[{"text":"Principal component analysis can be employed in a nonlinear way by means of the kernel trick."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":3,"queries":5,"sha256":"a0264d682afbf58a4d06bddc163fb02b6cf9c6877d9a92ed7372f197291a6842"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #de79e538","item":"In-text #de79e538","kind":"theorem","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"eee736aaafe10873b8ea96de96866815df707a1a6152fb0e32793a2a08e955c5","prominence":"supporting","quote":{"exact":"The resulting technique is capable of constructing nonlinear mappings that maximize the"},"quote_capped":true,"section":["Feature projection","Kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The resulting technique is capable of constructing nonlinear mappings that maximize the variance in the data.","segments":[{"text":"The resulting technique is capable of constructing nonlinear mappings that maximize the variance in the data."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"28593ac9bfecef616f4858c8dba64b549229f2b3b261c15440f8f26d979a7399"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #fcae7b52","item":"In-text #fcae7b52","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"254dbeaf16f2bce097353005412312757c6d47091edaf4df174d67226568de5c","prominence":"central","quote":{"exact":"The resulting technique is called kernel PCA."},"quote_capped":false,"section":["Feature projection","Kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The resulting technique is called kernel PCA.","segments":[{"text":"The resulting technique is called kernel PCA."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":5,"sha256":"201ca37ecc0347ec3bc6b52da1925bd169bd294a09b3e65458b0e609fbdca45f"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #f0b785c7","item":"In-text #f0b785c7","kind":"construction","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"5a8db20d299126fabf2f619c5c9e9fde3cb33bbe32a66cbf23d5d883b3bae838","prominence":"supporting","quote":{"exact":"Other prominent nonlinear techniques include manifold learning techniques such as Isomap, locally"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"after":{"layer":"; they can be viewed as defining a graph-based kernel for Kernel PCA.","segments":[{"text":"; they can be viewed as defining a graph-based kernel for Kernel PCA."}]},"layer":"Other prominent nonlinear techniques include manifold learning techniques such as Isomap, locally linear embedding (LLE),[13] Hessian LLE, Laplacian eigenmaps, and methods based on tangent space analysis.[14] These techniques assume that the high-dimensional input data lies near a low-dimensional manifold embedded in the ambient space, and construct a low-dimensional representation using a cost function that retains local properties of the data","segments":[{"text":"Other prominent nonlinear techniques include manifold learning techniques such as Isomap, locally linear embedding (LLE),"},{"ref":"[13]"},{"text":" Hessian LLE, Laplacian eigenmaps, and methods based on tangent space analysis."},{"ref":"[14]"},{"text":" These techniques assume that the high-dimensional input data lies near a low-dimensional manifold embedded in the ambient space, and construct a low-dimensional representation using a cost function that retains local properties of the data"}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"6171a83a1244f07e8f4c1756d0948b2cc06b4d00767e73b2ca387aa6198f9120"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #21fcf70d","item":"In-text #21fcf70d","kind":"theorem","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"b18bea222bfc377dede313b36dbafd01c3e4d42c862341cb73e8e4ea1bcddc78","prominence":"supporting","quote":{"exact":"they can be viewed as defining a graph-based kernel for Kernel PCA."},"quote_capped":false,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"before":{"layer":"These techniques assume that the high-dimensional input data lies near a low-dimensional manifold embedded in the ambient space, and construct a low-dimensional representation using a cost function that retains local properties of the data; ","segments":[{"text":"These techniques assume that the high-dimensional input data lies near a low-dimensional manifold embedded in the ambient space, and construct a low-dimensional representation using a cost function that retains local properties of the data; "}]},"layer":"they can be viewed as defining a graph-based kernel for Kernel PCA.","segments":[{"text":"they can be viewed as defining a graph-based kernel for Kernel PCA."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":5,"sha256":"c33f1ca0bfd6fc91d4ba899751845ebe851302c230cf53d25b3f39a8b6525deb"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #ec4a7447","item":"In-text #ec4a7447","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"e441fa71322fc70d2640de60a1a097dbab1e4b02d5919815dd7d5e70a133da8d","prominence":"central","quote":{"exact":"The central idea of MVU is to exactly preserve all pairwise distances"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"The central idea of MVU is to exactly preserve all pairwise distances between nearest neighbors (in the inner product space) while maximizing the distances between points that are not nearest neighbors.","segments":[{"text":"The central idea of MVU is to exactly preserve all pairwise distances between nearest neighbors (in the inner product space) while maximizing the distances between points that are not nearest neighbors."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"6b43b6c48f6e44da46cf252e86c469149dc7fc46e0d21dbc2ff34c2007222422"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #c6c1fdd9","item":"In-text #c6c1fdd9","kind":"construction","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"7ee1bf8ab32fee9a96f4e932ce4bf6c6cb78bd1c23a6e0e55459c9f38d79507e","prominence":"supporting","quote":{"exact":"An alternative approach to neighborhood preservation is through the minimization of a"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"An alternative approach to neighborhood preservation is through the minimization of a cost function that measures differences between distances in the input and output spaces.","segments":[{"text":"An alternative approach to neighborhood preservation is through the minimization of a cost function that measures differences between distances in the input and output spaces."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"5c2733c23942f38b43d2c036cb0abda7082a3b3da9150534653896e0b105b690"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #ec6b8f45","item":"In-text #ec6b8f45","kind":"theorem","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"46ab3265d6869a4cf1864675a9942f29c675cc6a086ebca4f0a11594729beab5","prominence":"supporting","quote":{"exact":"Important examples of such techniques include: classical multidimensional scaling, which is identical"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"after":{"layer":"; Isomap, which uses geodesic distances in the data space; diffusion maps, which use diffusion distances in the data space; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis.","segments":[{"text":"; Isomap, which uses geodesic distances in the data space; diffusion maps, which use diffusion distances in the data space; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis."}]},"layer":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA","segments":[{"text":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA"}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":4,"sha256":"959c4169387a5acc47a7bfc743e26ad5f5a896fe0143ae00798c2c5d06cf7205"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #6807d2cd","item":"In-text #6807d2cd","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"de42a447e48da0b2a276f0c7ab0f4041707b82f5e4c99790c1594614b3e60e15","prominence":"supporting","quote":{"exact":"Isomap, which uses geodesic distances in the data space"},"quote_capped":false,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"after":{"layer":"; diffusion maps, which use diffusion distances in the data space; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis.","segments":[{"text":"; diffusion maps, which use diffusion distances in the data space; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis."}]},"before":{"layer":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; ","segments":[{"text":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; "}]},"layer":"Isomap, which uses geodesic distances in the data space","segments":[{"text":"Isomap, which uses geodesic distances in the data space"}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":3,"sha256":"4091b9fc38de5f671080429b264c3299fb70fa006ae27fa77776ff80c28083da"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #35a3fe9f","item":"In-text #35a3fe9f","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"036137d30acb9b8044eb19b67d673eeb274620a67bf870b7b5e364c5e28f2aea","prominence":"supporting","quote":{"exact":"diffusion maps, which use diffusion distances in the data space"},"quote_capped":false,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"after":{"layer":"; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis.","segments":[{"text":"; t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis."}]},"before":{"layer":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; Isomap, which uses geodesic distances in the data space; ","segments":[{"text":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; Isomap, which uses geodesic distances in the data space; "}]},"layer":"diffusion maps, which use diffusion distances in the data space","segments":[{"text":"diffusion maps, which use diffusion distances in the data space"}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"74d55a860b2585993e434a97f6ab29cfa725d66dc8f39c4acee8ea8ae1657468"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #7803e6e3","item":"In-text #7803e6e3","kind":"definition","locations":[{"challenge":"sampled_out","commit":"3dfb8e22b67042b31fac228dee0e1169a1a7820f","confidence":"high","declaration":"InformationTheory.klDiv","end_line":59,"library":"mathlib","line":56,"location_key":"bb466a706a318d045904a78cc9b25f37c2ca81a49ed6c3ad92477e5c36d0e2af","module":"Mathlib.InformationTheory.KullbackLeibler.Basic","note":"defines the divergence of one measure from another on a single measurable space; it introduces no embedding and no pair-similarity distributions derived from one","pair_key":"2e8ebd6fe922f9ea82cc16d3a6a116370f52be605c7ab80ff2dc9943de024940","path":"Mathlib/InformationTheory/KullbackLeibler/Basic.lean","proof_status":"definition","rank":1,"relation":"relatedMatch","repo":"https://github.com/leanprover-community/mathlib4","signature":{"elided":false,"text":"def InformationTheory.klDiv {α : Type*} {mα : MeasurableSpace α} : MeasureTheory.Measure α → MeasureTheory.Measure α → ENNReal"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"20de0834fe2cc3c27dd484eb35421f643ce6eced1db66c2caa5129f71b92b688","prominence":"supporting","quote":{"exact":"t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"before":{"layer":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; Isomap, which uses geodesic distances in the data space; diffusion maps, which use diffusion distances in the data space; ","segments":[{"text":"Important examples of such techniques include: classical multidimensional scaling, which is identical to PCA; Isomap, which uses geodesic distances in the data space; diffusion maps, which use diffusion distances in the data space; "}]},"layer":"t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis.","segments":[{"text":"t-distributed stochastic neighbor embedding (t-SNE), which minimizes the divergence between distributions over pairs of points; and curvilinear component analysis."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"6904c3b31b7a4293b6a778878ee4910c076bf31d02434146e680427003b8c606"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #0029be5b","item":"In-text #0029be5b","kind":"definition","locations":[{"challenge":"survived","commit":"64c2773ffad3e5453b9f40c62e693b3669ade83f","confidence":"high","declaration":"MetaMathlibExt.universal_approximation","library":"atlas","line":1067,"location_key":"a723c8075016c773f8a79fe259ff032b0625363a0c5a3cc7dd16792c30b34f62","module":"MathlibExt.Analysis.Approximation.UniversalApproximation","note":"states that networks with one hidden layer approximate continuous functions uniformly on compacta; it fixes no narrow middle layer and no reduced representation of the input","pair_key":"9dc96f3b4c4808f02956aa43ac5604b6a4e174115cf250d4f0c641f549ccf633","path":"MathlibExt/Analysis/Approximation/UniversalApproximation.lean","proof_status":"proved","rank":1,"relation":"relatedMatch","repo":"https://github.com/facebookresearch/atlas-lean","signature":{"elided":false,"text":"theorem MetaMathlibExt.universal_approximation {n : ℕ} {K : Set (EuclideanSpace ℝ (Fin n))} : IsCompact K → ∀ {σ : ℝ → ℝ}, Continuous σ → (¬∃ p, ∀ (x : ℝ), σ x = Polynomial.eval x p) → ∀ {f : EuclideanSpace ℝ (Fin n) → ℝ}, ContinuousOn f K → ∀ {ε : ℝ}, 0 < ε → ∃ m c W b, ∀ x ∈ K, |f x - ∑ i, c i * σ (Inner.inner ℝ (W i) x + b i)| < ε"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"5cfbd2fec31004ae6def389e97103e1b18c6f4c75ba15b64e2024a55faa86342","prominence":"supporting","quote":{"exact":"A different approach to nonlinear dimensionality reduction is through the use of"},"quote_capped":true,"section":["Feature projection","Graph-based kernel PCA"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"A different approach to nonlinear dimensionality reduction is through the use of autoencoders, a special kind of feedforward neural networks with a bottleneck hidden layer.[16]","segments":[{"text":"A different approach to nonlinear dimensionality reduction is through the use of autoencoders, a special kind of feedforward neural networks with a bottleneck hidden layer."},{"ref":"[16]"}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":3,"sha256":"2b076784cc0706d368f419f98cd596e1b1c3cff28a5b61c8c6c5a6f238d3d6d1"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #f0aa837e","item":"In-text #f0aa837e","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"24a21b99260f6d690c43f73fcaaec57ce7553fe7668b438350afe3cdc33f384e","prominence":"central","quote":{"exact":"Linear discriminant analysis (LDA) is a generalization of Fisher's linear discriminant, a"},"quote_capped":true,"section":["Feature projection","Linear discriminant analysis (LDA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Linear discriminant analysis (LDA) is a generalization of Fisher's linear discriminant, a method used in statistics, pattern recognition, and machine learning to find a linear combination of features that characterizes or separates two or more classes of objects or events.","segments":[{"text":"Linear discriminant analysis (LDA) is a generalization of Fisher's linear discriminant, a method used in statistics, pattern recognition, and machine learning to find a linear combination of features that characterizes or separates two or more classes of objects or events."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"2793d079cafae298e66c7fc6b50f96f6a69836c35cb94bd9f19e203a2aad36e3"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #1a05e95a","item":"In-text #1a05e95a","kind":"definition","locations":[{"challenge":"survived","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"high","declaration":"Matrix.PosSemidef.kolmogorovFeature","end_line":138,"library":"tauceti","line":134,"location_key":"69b41f9556ebc5ca356b876b26aadbc7f3bf112c36f229e53c09717a2c181ee0","module":"TauCeti.Analysis.PositiveDefinite.Kernel.Kolmogorov","note":"builds the feature map of a positive semidefinite kernel into a Hilbert space; it carries no class labels and no discriminant criterion computed in that space","pair_key":"ec44bd62fa3d7531b2b6308ff7dd907f82c15ef392585f71667eb0316ef5f216","path":"TauCeti/Analysis/PositiveDefinite/Kernel/Kolmogorov.lean","proof_status":"definition","rank":1,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"def Matrix.PosSemidef.kolmogorovFeature {𝕜 : Type u} [RCLike 𝕜] {α : Type v} {K : α → α → 𝕜} (hK : Matrix.PosSemidef K) : α → hK.KolmogorovSpace"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"d7355eb56dcd92a60f8376fd2f779e28e402d62f7de0a9a1fc05fb6acbf4cf4b","prominence":"central","quote":{"exact":"GDA deals with nonlinear discriminant analysis using kernel function operator."},"quote_capped":false,"section":["Feature projection","Generalized discriminant analysis (GDA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"GDA deals with nonlinear discriminant analysis using kernel function operator.","segments":[{"text":"GDA deals with nonlinear discriminant analysis using kernel function operator."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":3,"sha256":"d0641e662c7fcc4ba8b7ab982c05fad00b0dd29afd2f470b89ce2e42e56c3a16"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #f98833a4","item":"In-text #f98833a4","kind":"definition","locations":[{"challenge":"sampled_out","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"high","declaration":"TauCeti.centeredScatter","end_line":65,"library":"tauceti","line":64,"location_key":"59e7d8237bef2e2184c91366c07fe7b8e56f39911529ab49ff055ef6aec52cea","module":"TauCeti.Analysis.InnerProductSpace.CenteredScatter","note":"defines the scatter operator of one finite family of vectors about its own mean; it splits no family into classes and optimises nothing","pair_key":"bb355fa2e6801488575f44d8fa5f7915d9fee65536c979e09245042b0c1e0d19","path":"TauCeti/Analysis/InnerProductSpace/CenteredScatter.lean","proof_status":"definition","rank":1,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"def TauCeti.centeredScatter (𝕜 : Type*) {E : Type*} {ι : Type*} [RCLike 𝕜] [NormedAddCommGroup E] [InnerProductSpace 𝕜 E] [Fintype ι] : (ι → E) → E →L[𝕜] E"},"statement":false},{"challenge":"sampled_out","commit":"83245abb3e4a4377e8d779ac045363a90c7e3a86","confidence":"medium","declaration":"IsCoercive.isLeast_rayleighQuotient","end_line":147,"library":"tauceti","line":134,"location_key":"9f669f15a3aee0d8e94347a8181969ea9d32ce5a05bd122369109c9a664ab1be","module":"TauCeti.Analysis.InnerProductSpace.Variational.Rayleigh","note":"gives the least value of a symmetric coercive form divided by a squared norm; the two quadratic forms of the passage are the scatters of a labelled sample, and the extremum sought is the other one","pair_key":"6367370a2290eeeba2150d9ec755005cbf137b85fbd8891f284a61a1e8cc4149","path":"TauCeti/Analysis/InnerProductSpace/Variational/Rayleigh.lean","proof_status":"proved","rank":2,"relation":"relatedMatch","repo":"https://github.com/TauCetiProject/TauCeti","signature":{"elided":false,"text":"theorem IsCoercive.isLeast_rayleighQuotient {V : Type*} {H : Type*} [NormedAddCommGroup V] [InnerProductSpace ℝ V] [CompleteSpace V] [NormedAddCommGroup H] [InnerProductSpace ℝ H] {B : V →L[ℝ] V →L[ℝ] ℝ} (hB : IsCoercive B) {J : V →L[ℝ] H} : IsCompactOperator ⇑J → (∀ (u v : V), (B u) v = (B v) u) → J ≠ 0 → IsLeast {r | ∃ v, J v ≠ 0 ∧ (B v) v / ‖J v‖ ^ 2 = r} ‖hB.formSolutionOperator J‖⁻¹"},"statement":false}],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"21be05670848acf12b883d91688061430241542b5a6ab0f46433d3ec49911eff","prominence":"supporting","quote":{"exact":"Similar to LDA, the objective of GDA is to find a projection"},"quote_capped":true,"section":["Feature projection","Generalized discriminant analysis (GDA)"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Similar to LDA, the objective of GDA is to find a projection for the features into a lower dimensional space by maximizing the ratio of between-class scatter to within-class scatter.","segments":[{"text":"Similar to LDA, the objective of GDA is to find a projection for the features into a lower dimensional space by maximizing the ratio of between-class scatter to within-class scatter."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":1,"queries":3,"sha256":"27771d7d06b1829b5a31dd8e4ba96c2972e51e6a968c01a5e04e29c241e6d612"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #80582007","item":"In-text #80582007","kind":"construction","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"b8945451a87ccf8b6fe517c4a1758eab8fa4b6a67be0f793d021915a15cb6f72","prominence":"central","quote":{"exact":"Autoencoders can be used to learn nonlinear dimension reduction functions and codings"},"quote_capped":true,"section":["Feature projection","Autoencoder"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Autoencoders can be used to learn nonlinear dimension reduction functions and codings together with an inverse function from the coding to the original representation.","segments":[{"text":"Autoencoders can be used to learn nonlinear dimension reduction functions and codings together with an inverse function from the coding to the original representation."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":3,"sha256":"fa3f5828a34ae85996c73178b132fecce2598130eab50518102f61002b9d7f79"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #5c1afee6","item":"In-text #5c1afee6","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"61a8fbd48c9c582c8deeded48d2107f9f37dbc3246455e4c012e54eff7451557","prominence":"central","quote":{"exact":"T-distributed Stochastic Neighbor Embedding (t-SNE) is a nonlinear dimensionality reduction technique useful"},"quote_capped":true,"section":["Feature projection","t-SNE"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"T-distributed Stochastic Neighbor Embedding (t-SNE) is a nonlinear dimensionality reduction technique useful for the visualization of high-dimensional datasets.","segments":[{"text":"T-distributed Stochastic Neighbor Embedding (t-SNE) is a nonlinear dimensionality reduction technique useful for the visualization of high-dimensional datasets."}]},"unresolved":null},{"absence":{"challenge":"survived","libraries":48,"receipt":{"candidates":2,"queries":5,"sha256":"46ac83a047b898b89295723d9efe2e385de8eab96bf222b15d3830ae5acb1e36"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #586e1237","item":"In-text #586e1237","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"533dc6ab4010a1e3399b2abf88dd8cb2897aa145b53a96589959137d9412f3b1","prominence":"central","quote":{"exact":"Uniform manifold approximation and projection (UMAP) is a nonlinear dimensionality reduction technique."},"quote_capped":false,"section":["Feature projection","UMAP"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Uniform manifold approximation and projection (UMAP) is a nonlinear dimensionality reduction technique.","segments":[{"text":"Uniform manifold approximation and projection (UMAP) is a nonlinear dimensionality reduction technique."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":3,"queries":6,"sha256":"78b97b2dca338fd915215b92c0d3422d0a69293b4d5097ec00760857b170829d"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #9c75f989","item":"In-text #9c75f989","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"b5ae39c72d1c639aa88fe60484d84260b9e0eb7d6ddb15f8a3cf0b3ad369415a","prominence":"supporting","quote":{"exact":"Visually, it is similar to t-SNE, but it assumes that the data"},"quote_capped":true,"section":["Feature projection","UMAP"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"Visually, it is similar to t-SNE, but it assumes that the data is uniformly distributed on a locally connected Riemannian manifold and that the Riemannian metric is locally constant or approximately locally constant.","segments":[{"text":"Visually, it is similar to t-SNE, but it assumes that the data is uniformly distributed on a locally connected Riemannian manifold and that the Riemannian metric is locally constant or approximately locally constant."}]},"unresolved":null},{"absence":{"challenge":"sampled_out","libraries":48,"receipt":{"candidates":2,"queries":5,"sha256":"4f5c112782c41fe45d176556423e6126483468aa0b55b872a565b6ab5fa42310"},"universe":"u1","universe_sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"basis":null,"coverage":null,"id":"enwiki-579867-1379974449::In-text #f5e4ba79","item":"In-text #f5e4ba79","kind":"definition","locations":[],"outcome":"absent","passage_ends_in_suffix":false,"passage_key":"4ea0be52cde570bbd62d3c48b17e477752e6ffb6c507e5fd48c775699c60309b","prominence":"supporting","quote":{"exact":"A dimensionality reduction technique that is sometimes used in neuroscience is maximally"},"quote_capped":true,"section":["Applications"],"status":"not_formalized","subject_uri":"https://en.wikipedia.org/w/index.php?curid=579867&oldid=1379974449","text":{"layer":"A dimensionality reduction technique that is sometimes used in neuroscience is maximally informative dimensions,[24] which finds a lower-dimensional representation of a dataset such that as much information as possible about the original data is preserved.","segments":[{"text":"A dimensionality reduction technique that is sometimes used in neuroscience is maximally informative dimensions,"},{"ref":"[24]"},{"text":" which finds a lower-dimensional representation of a dataset such that as much information as possible about the original data is preserved."}]},"unresolved":null}],"provenance":{"challenge":{"harvested":"2026-11-01T14:25:17Z","mode":"locate-challenge","model":"claude-opus-5","model_name":"Claude Opus 5","operator":"jack","reviewer_model":"claude-opus-5","reviewer_model_name":"Claude Opus 5","run_id":"chal-tierA-b1","sampling":{"absence_sample_rate":0.25,"sample_rate":0.2,"seed":0,"strong_sample_rate":0.5},"skill_commit":"d85385aa4eb2818373e9b6b8b41b765ffaf53750","started":"2026-11-01T03:19:32Z"},"inventory":{"harvested":"2026-10-30T20:00:47Z","mode":"locate-inventory","model":"claude-opus-5","model_name":"Claude Opus 5","operator":"jack","reviewer_model":"claude-opus-5","reviewer_model_name":"Claude Opus 5","run_id":"inv-tierA-b1r","skill_commit":"d85385aa4eb2818373e9b6b8b41b765ffaf53750","started":"2026-10-30T07:23:03Z"},"locate":{"harvested":"2026-11-01T03:06:57Z","mode":"locate","model":"claude-opus-5","model_name":"Claude Opus 5","operator":"jack","reviewer_model":"claude-opus-5","reviewer_model_name":"Claude Opus 5","run_id":"loc-tierA-b1b","skill_commit":"d85385aa4eb2818373e9b6b8b41b765ffaf53750","started":"2026-10-31T04:59:09Z"}},"reader":{"bytes":115569,"images":[{"author":"Amélia O. F. da S.","file":"LDA_Projection_Illustration_01.gif","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0","project":"commons"},{"author":"Headbomb","file":"Lock-gray-alt-2.svg","licence":"CC0","licence_url":"https://creativecommons.org/publicdomain/zero/1.0/deed.en","project":"commons"},{"author":"User:Trappist the monk","file":"Lock-green.svg","licence":"CC0","licence_url":"https://creativecommons.org/publicdomain/zero/1.0/deed.en","project":"commons"},{"author":"VulpesVulpes42, Headbomb","file":"Lock-red-alt-2.svg","licence":"CC0","licence_url":"https://creativecommons.org/publicdomain/zero/1.0/deed.en","project":"commons"},{"author":"https://phabricator.wikimedia.org/diffusion/GOJU/browse/master/AUTHORS.txt","file":"OOjs_UI_icon_edit-ltr-progressive.svg","licence":"PD","licence_url":null,"project":"en"},{"author":"Amélia O. F. da S.","file":"PCA_Projection_Illustration.gif","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0","project":"commons"}],"marks":91,"passages":27,"sha256":"0506bab57c1879fe5c69e718f2e664390bbeee5badf1c05680fe67235d5d29af","unplaced":[]},"record_set":"23710337d053e8212378a9e580805628bcdfda61a6fc431e65f24a4a16c9e602","records_sha256":"44fcda582fd486d60b29d6b24b78c67cbf27981961e3ba8739e7d1783d21f29b","revision":1379974449,"schema":"wikilean.articles.article/1","seal":{"created":"2026-11-01T14:25:17Z","schema":"cf-locate-recordset/2","set_id":"tierA-b1b","skill_commit":"d85385aa4eb2818373e9b6b8b41b765ffaf53750","status_rule":3},"source":{"html_sha256":"cd3799851718f3d382617905b77191cac4e204ccc89c4d7bbf3207278c23d7d5","layer_sha256":"9acae44e0152be6a84ca2780921789c449a362a075d240eba1945b977dcb349d","renderer":"web-html/3"},"source_id":"enwiki-579867-1379974449","summary":{"by_library":{"atlas":{"complete":0,"incomplete":0,"locations":0,"passages":0,"related":1},"mathlib":{"complete":0,"incomplete":0,"locations":0,"passages":0,"related":2},"tauceti":{"complete":0,"incomplete":0,"locations":0,"passages":0,"related":6}},"by_prominence":{"central":{"by_status":{"formalized":0,"not_formalized":12,"partial":0,"statement_only":0,"unresolved":0},"passages":12},"subject":{"by_status":{"formalized":0,"not_formalized":1,"partial":0,"statement_only":0,"unresolved":0},"passages":1},"supporting":{"by_status":{"formalized":0,"not_formalized":14,"partial":0,"statement_only":0,"unresolved":0},"passages":14}},"by_proof_status":{"definition":3,"proved":6},"by_relation":{"relatedMatch":9},"by_status":{"formalized":0,"not_formalized":27,"partial":0,"statement_only":0,"unresolved":0},"locations":0,"passages":27,"related":9},"supplements":{"audit_summary":{"schema":"wikilean.articles.audit-summary/1","sha256":"53b29c5773caa9a3a339ccb36db38548137820e05477c4eff49dfb63a91b74df"},"passage_text":{"schema":"wikilean.articles.passage-text/1","sha256":"c0c740562cd14bdcabe43ac1d7ba81039d8e41ef850fd199d7151de6bb774885"},"provenance":{"schema":"wikilean.articles.provenance/1","sha256":"ea245b590ba9078bc0b79003dc1e311dc1421475fe49483e3e3a905ed7c7ec4e"},"reader_html":{"schema":"wikilean.articles.reader-html/1","sha256":"738196c11695087fc8e74590f5ac362acd61af48a8950c0a049559dd3902d2df"},"signatures":{"corpus_built":"2026-10-18T06:14:30Z","corpus_sha256":"a364fd6aede529da1c9f2fa13fda6230a26381f27dafc8801c4205e2b5cf5221","schema":"wikilean.articles.signatures/1","sha256":"2ebb5eebf8b2ebd1f615518abce6169661140cc54d5fcad5f4443150cc62d874","universe":"u1"}},"title":"Dimensionality reduction","universe":{"frozen":"2026-10-17","id":"u1","libraries":48,"sha256":"12e9eacf66816a249dcecba39f20dd7ca977c042af3e6acdb16ac7a45a4a9e76"},"wikidata":"Q16000077"}
