{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SGDXCHP6XLXRSPCX647N6ESIDE","short_pith_number":"pith:SGDXCHP6","canonical_record":{"source":{"id":"2602.03797","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T18:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"9692d2ecba17d9875eb9e8a04198c891b37d268b9eeee253a5a77484b27bc1d6","abstract_canon_sha256":"b3eec12df0e7e08d9c8b97e3ee8f6618cd905b90189be33909372d43b6c0d2c4"},"schema_version":"1.0"},"canonical_sha256":"9187711dfebaef193c57f73edf12481939f37fe3bdfaa415043c9c2f08683466","source":{"kind":"arxiv","id":"2602.03797","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03797","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03797v3","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03797","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"SGDXCHP6XLXR","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"SGDXCHP6XLXRSPCX","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"SGDXCHP6","created_at":"2026-05-20T00:05:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SGDXCHP6XLXRSPCX647N6ESIDE","target":"record","payload":{"canonical_record":{"source":{"id":"2602.03797","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T18:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"9692d2ecba17d9875eb9e8a04198c891b37d268b9eeee253a5a77484b27bc1d6","abstract_canon_sha256":"b3eec12df0e7e08d9c8b97e3ee8f6618cd905b90189be33909372d43b6c0d2c4"},"schema_version":"1.0"},"canonical_sha256":"9187711dfebaef193c57f73edf12481939f37fe3bdfaa415043c9c2f08683466","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:41.578413Z","signature_b64":"I0jJYOeCjWZ192OKUTS/b32IAxXDtEf0DunLay+wIsqX62Z6DVie9c/kcVsR8OqagIfJZ2mgo9H6yMqWeLumDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9187711dfebaef193c57f73edf12481939f37fe3bdfaa415043c9c2f08683466","last_reissued_at":"2026-05-20T00:05:41.577911Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:41.577911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.03797","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPu3Fzdh9g1GtFjuQ1r3qJ93yUVJViR/dW2+baTQYxWUXp6oGLCKb2+sUB0MUt/i+9iCEo0OE2AUwEly664NDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:47:10.356366Z"},"content_sha256":"f9c31bb8ee67cc0e3746cde1107097580424bf02b329f66b3a90cd3833a8ef0f","schema_version":"1.0","event_id":"sha256:f9c31bb8ee67cc0e3746cde1107097580424bf02b329f66b3a90cd3833a8ef0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SGDXCHP6XLXRSPCX647N6ESIDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manifold Random Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ananya Parashar, Derek Long, Dwaipayan Saha, Krzysztof Choromanski","submitted_at":"2026-02-03T18:00:01Z","abstract_excerpt":"We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. This new mechanism of Manifold Random Features (MRFs) leverages discretization of the manifold and the recently introduced technique of Graph Random Features (GRFs) to learn continuous fields on manifolds. Those fields are used to find continuous approximation mechanisms that otherwise, in general scenarios, cannot be derived analytically. MRFs provide positive and bounded features, a key property for accurate, low-variance approximation. We show dee"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MRFs provide positive and bounded features, a key property for accurate, low-variance approximation, and show deep asymptotic connection between GRFs on discrete graphs and continuous random features for regular kernels.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That discretizing an arbitrary manifold into a graph preserves the geometric properties needed for the random features to converge to the desired continuous approximation on the original manifold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Manifold Random Features approximate kernels on general manifolds via discretization and graph random features to yield positive bounded features with asymptotic connections to continuous random features.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"37cf5df03f52a349483baa28f992e538d3ac7d816e0fa384d5daaa8524fe306c"},"source":{"id":"2602.03797","kind":"arxiv","version":3},"verdict":{"id":"c27e3299-e579-4bf9-a239-3c7626319126","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:46:57.217273Z","strongest_claim":"MRFs provide positive and bounded features, a key property for accurate, low-variance approximation, and show deep asymptotic connection between GRFs on discrete graphs and continuous random features for regular kernels.","one_line_summary":"Manifold Random Features approximate kernels on general manifolds via discretization and graph random features to yield positive bounded features with asymptotic connections to continuous random features.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That discretizing an arbitrary manifold into a graph preserves the geometric properties needed for the random features to converge to the desired continuous approximation on the original manifold.","pith_extraction_headline":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.03797/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b6299bdc3b08046fc7fb7a05f52ee1759ead7be5cd52d36b5b2aa7a2ecb65235"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c27e3299-e579-4bf9-a239-3c7626319126"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p/EXqxfNYCY2z3zVuc534fW5NpG4c593Drb2y1sFf69yL102RRbrmeat3ffBXbAWdeACSqiO40KygZLGWa01Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:47:10.356827Z"},"content_sha256":"92ddca48106826f3cca78164f388a124dcf7721f644ef84603a443b1dcba5832","schema_version":"1.0","event_id":"sha256:92ddca48106826f3cca78164f388a124dcf7721f644ef84603a443b1dcba5832"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGDXCHP6XLXRSPCX647N6ESIDE/bundle.json","state_url":"https://pith.science/pith/SGDXCHP6XLXRSPCX647N6ESIDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGDXCHP6XLXRSPCX647N6ESIDE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-12T09:47:10Z","links":{"resolver":"https://pith.science/pith/SGDXCHP6XLXRSPCX647N6ESIDE","bundle":"https://pith.science/pith/SGDXCHP6XLXRSPCX647N6ESIDE/bundle.json","state":"https://pith.science/pith/SGDXCHP6XLXRSPCX647N6ESIDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGDXCHP6XLXRSPCX647N6ESIDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SGDXCHP6XLXRSPCX647N6ESIDE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b3eec12df0e7e08d9c8b97e3ee8f6618cd905b90189be33909372d43b6c0d2c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T18:00:01Z","title_canon_sha256":"9692d2ecba17d9875eb9e8a04198c891b37d268b9eeee253a5a77484b27bc1d6"},"schema_version":"1.0","source":{"id":"2602.03797","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03797","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03797v3","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03797","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"SGDXCHP6XLXR","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"SGDXCHP6XLXRSPCX","created_at":"2026-05-20T00:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"SGDXCHP6","created_at":"2026-05-20T00:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:92ddca48106826f3cca78164f388a124dcf7721f644ef84603a443b1dcba5832","target":"graph","created_at":"2026-05-20T00:05:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MRFs provide positive and bounded features, a key property for accurate, low-variance approximation, and show deep asymptotic connection between GRFs on discrete graphs and continuous random features for regular kernels."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That discretizing an arbitrary manifold into a graph preserves the geometric properties needed for the random features to converge to the desired continuous approximation on the original manifold."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Manifold Random Features approximate kernels on general manifolds via discretization and graph random features to yield positive bounded features with asymptotic connections to continuous random features."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features."}],"snapshot_sha256":"37cf5df03f52a349483baa28f992e538d3ac7d816e0fa384d5daaa8524fe306c"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b6299bdc3b08046fc7fb7a05f52ee1759ead7be5cd52d36b5b2aa7a2ecb65235"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.03797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. This new mechanism of Manifold Random Features (MRFs) leverages discretization of the manifold and the recently introduced technique of Graph Random Features (GRFs) to learn continuous fields on manifolds. Those fields are used to find continuous approximation mechanisms that otherwise, in general scenarios, cannot be derived analytically. MRFs provide positive and bounded features, a key property for accurate, low-variance approximation. We show dee","authors_text":"Ananya Parashar, Derek Long, Dwaipayan Saha, Krzysztof Choromanski","cross_cats":[],"headline":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T18:00:01Z","title":"Manifold Random Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03797","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T07:46:57.217273Z","id":"c27e3299-e579-4bf9-a239-3c7626319126","model_set":{"reader":"grok-4.3"},"one_line_summary":"Manifold Random Features approximate kernels on general manifolds via discretization and graph random features to yield positive bounded features with asymptotic connections to continuous random features.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Manifold Random Features approximate kernels on general manifolds by discretizing them into graphs to generate positive bounded features.","strongest_claim":"MRFs provide positive and bounded features, a key property for accurate, low-variance approximation, and show deep asymptotic connection between GRFs on discrete graphs and continuous random features for regular kernels.","weakest_assumption":"That discretizing an arbitrary manifold into a graph preserves the geometric properties needed for the random features to converge to the desired continuous approximation on the original manifold."}},"verdict_id":"c27e3299-e579-4bf9-a239-3c7626319126"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f9c31bb8ee67cc0e3746cde1107097580424bf02b329f66b3a90cd3833a8ef0f","target":"record","created_at":"2026-05-20T00:05:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b3eec12df0e7e08d9c8b97e3ee8f6618cd905b90189be33909372d43b6c0d2c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T18:00:01Z","title_canon_sha256":"9692d2ecba17d9875eb9e8a04198c891b37d268b9eeee253a5a77484b27bc1d6"},"schema_version":"1.0","source":{"id":"2602.03797","kind":"arxiv","version":3}},"canonical_sha256":"9187711dfebaef193c57f73edf12481939f37fe3bdfaa415043c9c2f08683466","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9187711dfebaef193c57f73edf12481939f37fe3bdfaa415043c9c2f08683466","first_computed_at":"2026-05-20T00:05:41.577911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:41.577911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0jJYOeCjWZ192OKUTS/b32IAxXDtEf0DunLay+wIsqX62Z6DVie9c/kcVsR8OqagIfJZ2mgo9H6yMqWeLumDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:41.578413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03797","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9c31bb8ee67cc0e3746cde1107097580424bf02b329f66b3a90cd3833a8ef0f","sha256:92ddca48106826f3cca78164f388a124dcf7721f644ef84603a443b1dcba5832"],"state_sha256":"6d090cabf6925f1647001aecc032808f28799b1fab5bbf920ebedd39ba5b8967"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tVth1p9Ae6u+rO81L23ifm8Oso5En2ClnNt17GeF2pFDtlV0CvDyXgDRfJawGAYx/EQIgYouwEd+00yFYeQ4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T09:47:10.359058Z","bundle_sha256":"d181c01c533e31b7d4c4e2c5b57c1081b4e2d2e324eeceff872678a557db7ccc"}}