{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:F7HCHFXV4TMM5BEUA5LPI6NH4H","short_pith_number":"pith:F7HCHFXV","schema_version":"1.0","canonical_sha256":"2fce2396f5e4d8ce84940756f479a7e1d4abdca6500e15de68aad5e271a3a494","source":{"kind":"arxiv","id":"1202.6078","version":1},"attestation_state":"computed","paper":{"title":"Protocols for Learning Classifiers on Distributed Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Avishek Saha, Hal Daume III, Jeff M. Phillips, Suresh Venkatasubramanian","submitted_at":"2012-02-27T21:33:32Z","abstract_excerpt":"We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the processing of massive distributed datasets. We present several very general sampling-based solutions as well as some two-way protocols which have a provable exponential speed-up over any one-way protocol. We focus on core problems for noiseless data distributed across two or more"},"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":"1202.6078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-02-27T21:33:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89c2e071d31f5ff41dcc579b930ab31b194152fcce7a3b28a159b1513f2a1c6a","abstract_canon_sha256":"781a0ad73b49a9b89e226b6c61b062c1cb7dfa870045845a216d918a87ebbee5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:00:51.319004Z","signature_b64":"fdTxGCPyRes1YJY1SFev2Cu9r8JfQX8r/LFHc5IVPGr89g5W6EIo+MTehzuqsPmy55KUhNked8LAxgDlxEHlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fce2396f5e4d8ce84940756f479a7e1d4abdca6500e15de68aad5e271a3a494","last_reissued_at":"2026-05-18T04:00:51.318599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:00:51.318599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protocols for Learning Classifiers on Distributed Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Avishek Saha, Hal Daume III, Jeff M. Phillips, Suresh Venkatasubramanian","submitted_at":"2012-02-27T21:33:32Z","abstract_excerpt":"We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the processing of massive distributed datasets. We present several very general sampling-based solutions as well as some two-way protocols which have a provable exponential speed-up over any one-way protocol. We focus on core problems for noiseless data distributed across two or more"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.6078","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":"1202.6078","created_at":"2026-05-18T04:00:51.318655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.6078v1","created_at":"2026-05-18T04:00:51.318655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.6078","created_at":"2026-05-18T04:00:51.318655+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7HCHFXV4TMM","created_at":"2026-05-18T12:27:04.183437+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7HCHFXV4TMM5BEU","created_at":"2026-05-18T12:27:04.183437+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7HCHFXV","created_at":"2026-05-18T12:27:04.183437+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/F7HCHFXV4TMM5BEUA5LPI6NH4H","json":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H.json","graph_json":"https://pith.science/api/pith-number/F7HCHFXV4TMM5BEUA5LPI6NH4H/graph.json","events_json":"https://pith.science/api/pith-number/F7HCHFXV4TMM5BEUA5LPI6NH4H/events.json","paper":"https://pith.science/paper/F7HCHFXV"},"agent_actions":{"view_html":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H","download_json":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H.json","view_paper":"https://pith.science/paper/F7HCHFXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.6078&json=true","fetch_graph":"https://pith.science/api/pith-number/F7HCHFXV4TMM5BEUA5LPI6NH4H/graph.json","fetch_events":"https://pith.science/api/pith-number/F7HCHFXV4TMM5BEUA5LPI6NH4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H/action/storage_attestation","attest_author":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H/action/author_attestation","sign_citation":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H/action/citation_signature","submit_replication":"https://pith.science/pith/F7HCHFXV4TMM5BEUA5LPI6NH4H/action/replication_record"}},"created_at":"2026-05-18T04:00:51.318655+00:00","updated_at":"2026-05-18T04:00:51.318655+00:00"}