{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I35OTAYY4IIHNAB4J2GIYCDKW2","short_pith_number":"pith:I35OTAYY","canonical_record":{"source":{"id":"1808.10776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-31T14:32:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12922a1ab36d329daace652101234a800c8cac8693f16926cecbcd59f8db7822","abstract_canon_sha256":"87280114a66eeeb972abd01535cea7180f0fc5de3096675117e5accd94729284"},"schema_version":"1.0"},"canonical_sha256":"46fae98318e21076803c4e8c8c086ab68da6ca1c0324c88651baf13a437bf2c7","source":{"kind":"arxiv","id":"1808.10776","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10776","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10776v1","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10776","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"I35OTAYY4IIH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I35OTAYY4IIHNAB4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I35OTAYY","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I35OTAYY4IIHNAB4J2GIYCDKW2","target":"record","payload":{"canonical_record":{"source":{"id":"1808.10776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-31T14:32:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12922a1ab36d329daace652101234a800c8cac8693f16926cecbcd59f8db7822","abstract_canon_sha256":"87280114a66eeeb972abd01535cea7180f0fc5de3096675117e5accd94729284"},"schema_version":"1.0"},"canonical_sha256":"46fae98318e21076803c4e8c8c086ab68da6ca1c0324c88651baf13a437bf2c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:44.595440Z","signature_b64":"v/p+45YuL+eFYbXlbVXbbWUEH8M8aQfVaOc1A6N5sD7a7KcPSTTskHzhYWTnEdw38ggQWo6aZ0PZQwABoT0JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46fae98318e21076803c4e8c8c086ab68da6ca1c0324c88651baf13a437bf2c7","last_reissued_at":"2026-05-18T00:06:44.594936Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:44.594936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.10776","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2EwqwY/zzgKeZH4meWzEH8fcYfFr2/ke0ClKaeQDAaX7Tt0ldaadpVrP16ygebNR/6CboQvVN+yA5XfARbTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:27:02.511477Z"},"content_sha256":"5fe5ba0f052b7c4a47fbc8b498b3ea79e88d67421bb53a1633feb1bbd204e53c","schema_version":"1.0","event_id":"sha256:5fe5ba0f052b7c4a47fbc8b498b3ea79e88d67421bb53a1633feb1bbd204e53c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I35OTAYY4IIHNAB4J2GIYCDKW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Manifold Learning for Big Data with Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Frank Schoeneman, Jaroslaw Zola","submitted_at":"2018-08-31T14:32:10Z","abstract_excerpt":"Non-linear spectral dimensionality reduction methods, such as Isomap, remain important technique for learning manifolds. However, due to computational complexity, exact manifold learning using Isomap is currently impossible from large-scale data. In this paper, we propose a distributed memory framework implementing end-to-end exact Isomap under Apache Spark model. We show how each critical step of the Isomap algorithm can be efficiently realized using basic Spark model, without the need to provision data in the secondary storage. We show how the entire method can be implemented using PySpark, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10776","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bT+skElrmyS/UY2xV1JZkTDYW9V05bYG7ZiY444EETbnmhx+ALw9HWiSORjKCXgaOHzdT5coz9K2nT5RZbUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:27:02.511827Z"},"content_sha256":"a027696af2554af0650e7215c24cf51228648e8bd023dc5ba6e0cde0efcb75f9","schema_version":"1.0","event_id":"sha256:a027696af2554af0650e7215c24cf51228648e8bd023dc5ba6e0cde0efcb75f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/bundle.json","state_url":"https://pith.science/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/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":"2026-06-12T10:27:02Z","links":{"resolver":"https://pith.science/pith/I35OTAYY4IIHNAB4J2GIYCDKW2","bundle":"https://pith.science/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/bundle.json","state":"https://pith.science/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I35OTAYY4IIHNAB4J2GIYCDKW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I35OTAYY4IIHNAB4J2GIYCDKW2","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":"87280114a66eeeb972abd01535cea7180f0fc5de3096675117e5accd94729284","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-31T14:32:10Z","title_canon_sha256":"12922a1ab36d329daace652101234a800c8cac8693f16926cecbcd59f8db7822"},"schema_version":"1.0","source":{"id":"1808.10776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.10776","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"arxiv_version","alias_value":"1808.10776v1","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.10776","created_at":"2026-05-18T00:06:44Z"},{"alias_kind":"pith_short_12","alias_value":"I35OTAYY4IIH","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I35OTAYY4IIHNAB4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I35OTAYY","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:a027696af2554af0650e7215c24cf51228648e8bd023dc5ba6e0cde0efcb75f9","target":"graph","created_at":"2026-05-18T00:06:44Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Non-linear spectral dimensionality reduction methods, such as Isomap, remain important technique for learning manifolds. However, due to computational complexity, exact manifold learning using Isomap is currently impossible from large-scale data. In this paper, we propose a distributed memory framework implementing end-to-end exact Isomap under Apache Spark model. We show how each critical step of the Isomap algorithm can be efficiently realized using basic Spark model, without the need to provision data in the secondary storage. We show how the entire method can be implemented using PySpark, ","authors_text":"Frank Schoeneman, Jaroslaw Zola","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-31T14:32:10Z","title":"Scalable Manifold Learning for Big Data with Apache Spark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.10776","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5fe5ba0f052b7c4a47fbc8b498b3ea79e88d67421bb53a1633feb1bbd204e53c","target":"record","created_at":"2026-05-18T00:06:44Z","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":"87280114a66eeeb972abd01535cea7180f0fc5de3096675117e5accd94729284","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-31T14:32:10Z","title_canon_sha256":"12922a1ab36d329daace652101234a800c8cac8693f16926cecbcd59f8db7822"},"schema_version":"1.0","source":{"id":"1808.10776","kind":"arxiv","version":1}},"canonical_sha256":"46fae98318e21076803c4e8c8c086ab68da6ca1c0324c88651baf13a437bf2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46fae98318e21076803c4e8c8c086ab68da6ca1c0324c88651baf13a437bf2c7","first_computed_at":"2026-05-18T00:06:44.594936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:44.594936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/p+45YuL+eFYbXlbVXbbWUEH8M8aQfVaOc1A6N5sD7a7KcPSTTskHzhYWTnEdw38ggQWo6aZ0PZQwABoT0JAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:44.595440Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.10776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fe5ba0f052b7c4a47fbc8b498b3ea79e88d67421bb53a1633feb1bbd204e53c","sha256:a027696af2554af0650e7215c24cf51228648e8bd023dc5ba6e0cde0efcb75f9"],"state_sha256":"24455cf73fb2890505f6b0f87628aa7415c839df9e61b03eaafde8d613427fea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o5FgIbcMGPAIQB4WxvvdZlSyAdbq3Xng1ZgagBBg+lcGulOn5jb90AzGjzf0Vcv2C7cdkhSqn/XRhT5IN7D6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T10:27:02.513754Z","bundle_sha256":"abb973705f7a1b4e822c18dd2611b36088e147ad3e4d94a170685163f5304102"}}