{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WG4TYIMB7OWLPFDPNI542R2SMO","short_pith_number":"pith:WG4TYIMB","canonical_record":{"source":{"id":"1609.09619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2016-09-30T07:35:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f6f1d1457456693f6ffb1a4f346ae0dfa24cbadeb295af548a82312300434da","abstract_canon_sha256":"62eef63d54287aa5b6192edafd7539c916abfedd19145730b0ab90042f170595"},"schema_version":"1.0"},"canonical_sha256":"b1b93c2181fbacb7946f6a3bcd475263bb1778c79866254cc621b5dcfadafe6c","source":{"kind":"arxiv","id":"1609.09619","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.09619","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"1609.09619v1","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09619","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"WG4TYIMB7OWL","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WG4TYIMB7OWLPFDP","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WG4TYIMB","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WG4TYIMB7OWLPFDPNI542R2SMO","target":"record","payload":{"canonical_record":{"source":{"id":"1609.09619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2016-09-30T07:35:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4f6f1d1457456693f6ffb1a4f346ae0dfa24cbadeb295af548a82312300434da","abstract_canon_sha256":"62eef63d54287aa5b6192edafd7539c916abfedd19145730b0ab90042f170595"},"schema_version":"1.0"},"canonical_sha256":"b1b93c2181fbacb7946f6a3bcd475263bb1778c79866254cc621b5dcfadafe6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:35.521832Z","signature_b64":"0iBjfyM+vK2CAIyzf7CC8CV1QKr73Rpa9VW+IZ4kO555NN/reKBA+poNd15Z1HIkg0prHbIXWUgUExS+VN6QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b93c2181fbacb7946f6a3bcd475263bb1778c79866254cc621b5dcfadafe6c","last_reissued_at":"2026-05-18T01:03:35.521162Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:35.521162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.09619","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":"2026-05-18T01:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMqvMMBObSQ/FM2rnQvizmxadjfKd5QeW8quf+MtLZSpdLUQ+feQy9VDxDC73DtKlr1Vmqlb5VNiO1AQ7xTLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:45:57.232701Z"},"content_sha256":"5270a0a64a79469f7c568f5ab75a9f0217e3c6ae90b1c9325e1c44dbcb447fb8","schema_version":"1.0","event_id":"sha256:5270a0a64a79469f7c568f5ab75a9f0217e3c6ae90b1c9325e1c44dbcb447fb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WG4TYIMB7OWLPFDPNI542R2SMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Big Data analytics. Three use cases with R, Python and Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.AP","authors_text":"Brendan Guillouet (IMT), Jean-Michel Loubes (IMT), Philippe Besse (IMT)","submitted_at":"2016-09-30T07:35:49Z","abstract_excerpt":"Management and analysis of big data are systematically associated with a data distributed architecture in the Hadoop  and now Spark frameworks. This article offers an introduction for statisticians to these technologies by comparing the performance obtained by the direct use of three reference environments: R, Python Scikit-learn, Spark MLlib on three public use cases: character recognition, recommending films, categorizing products. As main result, it appears that, if Spark is very efficient for data munging and recommendation by collaborative filtering (non-negative factorization), current i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.09619","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":"2026-05-18T01:03:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wqm/kgl8EGm+B6N+ZB3RlN8QzJTxcuT3hWaPZa5Llt85WkhZQ6sEWuZyNbXg17HRDGEseOv87sI9vOufZOWVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:45:57.233050Z"},"content_sha256":"e8f597aa3729bd7517dbbae0cf644b9de175dd5ac156aaa8deea1357a4d8c957","schema_version":"1.0","event_id":"sha256:e8f597aa3729bd7517dbbae0cf644b9de175dd5ac156aaa8deea1357a4d8c957"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WG4TYIMB7OWLPFDPNI542R2SMO/bundle.json","state_url":"https://pith.science/pith/WG4TYIMB7OWLPFDPNI542R2SMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WG4TYIMB7OWLPFDPNI542R2SMO/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":"2026-06-04T06:45:57Z","links":{"resolver":"https://pith.science/pith/WG4TYIMB7OWLPFDPNI542R2SMO","bundle":"https://pith.science/pith/WG4TYIMB7OWLPFDPNI542R2SMO/bundle.json","state":"https://pith.science/pith/WG4TYIMB7OWLPFDPNI542R2SMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WG4TYIMB7OWLPFDPNI542R2SMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WG4TYIMB7OWLPFDPNI542R2SMO","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":"62eef63d54287aa5b6192edafd7539c916abfedd19145730b0ab90042f170595","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2016-09-30T07:35:49Z","title_canon_sha256":"4f6f1d1457456693f6ffb1a4f346ae0dfa24cbadeb295af548a82312300434da"},"schema_version":"1.0","source":{"id":"1609.09619","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.09619","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"1609.09619v1","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09619","created_at":"2026-05-18T01:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"WG4TYIMB7OWL","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WG4TYIMB7OWLPFDP","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WG4TYIMB","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:e8f597aa3729bd7517dbbae0cf644b9de175dd5ac156aaa8deea1357a4d8c957","target":"graph","created_at":"2026-05-18T01:03:35Z","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":"Management and analysis of big data are systematically associated with a data distributed architecture in the Hadoop  and now Spark frameworks. This article offers an introduction for statisticians to these technologies by comparing the performance obtained by the direct use of three reference environments: R, Python Scikit-learn, Spark MLlib on three public use cases: character recognition, recommending films, categorizing products. As main result, it appears that, if Spark is very efficient for data munging and recommendation by collaborative filtering (non-negative factorization), current i","authors_text":"Brendan Guillouet (IMT), Jean-Michel Loubes (IMT), Philippe Besse (IMT)","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2016-09-30T07:35:49Z","title":"Big Data analytics. Three use cases with R, Python and Spark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.09619","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":"sha256:5270a0a64a79469f7c568f5ab75a9f0217e3c6ae90b1c9325e1c44dbcb447fb8","target":"record","created_at":"2026-05-18T01:03:35Z","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":"62eef63d54287aa5b6192edafd7539c916abfedd19145730b0ab90042f170595","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2016-09-30T07:35:49Z","title_canon_sha256":"4f6f1d1457456693f6ffb1a4f346ae0dfa24cbadeb295af548a82312300434da"},"schema_version":"1.0","source":{"id":"1609.09619","kind":"arxiv","version":1}},"canonical_sha256":"b1b93c2181fbacb7946f6a3bcd475263bb1778c79866254cc621b5dcfadafe6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1b93c2181fbacb7946f6a3bcd475263bb1778c79866254cc621b5dcfadafe6c","first_computed_at":"2026-05-18T01:03:35.521162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:35.521162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0iBjfyM+vK2CAIyzf7CC8CV1QKr73Rpa9VW+IZ4kO555NN/reKBA+poNd15Z1HIkg0prHbIXWUgUExS+VN6QAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:35.521832Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.09619","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5270a0a64a79469f7c568f5ab75a9f0217e3c6ae90b1c9325e1c44dbcb447fb8","sha256:e8f597aa3729bd7517dbbae0cf644b9de175dd5ac156aaa8deea1357a4d8c957"],"state_sha256":"05dfe1be38c4d6c7470963255e1103a4516846c1896724a2b7d02139b4c854b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bu7eC41l1GlTY8KNArrNBZ7WOQkmK6CgW6iLIqIEp3Po9nYBSepony1/sxckALgUUhAcsXuaUGX8NH8oY/ZfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:45:57.235905Z","bundle_sha256":"ddf4a1783c01eebad58d4ce6a0a90d7afab10961431d5727150a3532519fe811"}}