{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EMDOBJSPWQWNVSNO7Z3W56L3QQ","short_pith_number":"pith:EMDOBJSP","schema_version":"1.0","canonical_sha256":"2306e0a64fb42cdac9aefe776ef97b840eadce020e972be44c853b15acb89588","source":{"kind":"arxiv","id":"1604.03034","version":1},"attestation_state":"computed","paper":{"title":"M3: Scaling Up Machine Learning via Memory Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dezhi Fang, Duen Horng Chau","submitted_at":"2016-04-11T17:12:14Z","abstract_excerpt":"To process data that do not fit in RAM, conventional wisdom would suggest using distributed approaches. However, recent research has demonstrated virtual memory's strong potential in scaling up graph mining algorithms on a single machine. We propose to use a similar approach for general machine learning. We contribute: (1) our latest finding that memory mapping is also a feasible technique for scaling up general machine learning algorithms like logistic regression and k-means, when data fits in or exceeds RAM (we tested datasets up to 190GB); (2) an approach, called M3, that enables existing m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1604.03034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-04-11T17:12:14Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"df126f93b92afbc245f5eba4e505ba4654e5d98eb906a2240e9d86e31603d493","abstract_canon_sha256":"2cb728acb15ac247ccaeb4b17ee5d88dd2daec85b95e78bc911d639b7a4cfeb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:21.603749Z","signature_b64":"nq1R+8Ij5oIBDqJ5UKTi9jAHs6MTqXOxGDLQlwsj21MyJdrfzEXrFR3LTtzCogQK93sSOi6qwDpTIcOnGrYLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2306e0a64fb42cdac9aefe776ef97b840eadce020e972be44c853b15acb89588","last_reissued_at":"2026-05-18T01:17:21.603257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:21.603257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3: Scaling Up Machine Learning via Memory Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dezhi Fang, Duen Horng Chau","submitted_at":"2016-04-11T17:12:14Z","abstract_excerpt":"To process data that do not fit in RAM, conventional wisdom would suggest using distributed approaches. However, recent research has demonstrated virtual memory's strong potential in scaling up graph mining algorithms on a single machine. We propose to use a similar approach for general machine learning. We contribute: (1) our latest finding that memory mapping is also a feasible technique for scaling up general machine learning algorithms like logistic regression and k-means, when data fits in or exceeds RAM (we tested datasets up to 190GB); (2) an approach, called M3, that enables existing m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03034","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1604.03034","created_at":"2026-05-18T01:17:21.603346+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.03034v1","created_at":"2026-05-18T01:17:21.603346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03034","created_at":"2026-05-18T01:17:21.603346+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMDOBJSPWQWN","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMDOBJSPWQWNVSNO","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMDOBJSP","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ","json":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ.json","graph_json":"https://pith.science/api/pith-number/EMDOBJSPWQWNVSNO7Z3W56L3QQ/graph.json","events_json":"https://pith.science/api/pith-number/EMDOBJSPWQWNVSNO7Z3W56L3QQ/events.json","paper":"https://pith.science/paper/EMDOBJSP"},"agent_actions":{"view_html":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ","download_json":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ.json","view_paper":"https://pith.science/paper/EMDOBJSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.03034&json=true","fetch_graph":"https://pith.science/api/pith-number/EMDOBJSPWQWNVSNO7Z3W56L3QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EMDOBJSPWQWNVSNO7Z3W56L3QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ/action/storage_attestation","attest_author":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ/action/author_attestation","sign_citation":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ/action/citation_signature","submit_replication":"https://pith.science/pith/EMDOBJSPWQWNVSNO7Z3W56L3QQ/action/replication_record"}},"created_at":"2026-05-18T01:17:21.603346+00:00","updated_at":"2026-05-18T01:17:21.603346+00:00"}