{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6MU4RSCMOU5UUHIAA7FTWQJEK6","short_pith_number":"pith:6MU4RSCM","canonical_record":{"source":{"id":"1710.04062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-11T13:49:28Z","cross_cats_sorted":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2ff2be342e8e5290e4d8da0b9b348f5c13bd22bd63b41e182973822e7e7e7bf3","abstract_canon_sha256":"ef1cbab8cf1be5d0e5f5a95cdf1f4436d04495e634e59363e43c188acdc26a20"},"schema_version":"1.0"},"canonical_sha256":"f329c8c84c753b4a1d0007cb3b4124578a487b403432198273d918f60e24d13d","source":{"kind":"arxiv","id":"1710.04062","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04062","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04062v1","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04062","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"6MU4RSCMOU5U","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6MU4RSCMOU5UUHIA","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6MU4RSCM","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6MU4RSCMOU5UUHIAA7FTWQJEK6","target":"record","payload":{"canonical_record":{"source":{"id":"1710.04062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-11T13:49:28Z","cross_cats_sorted":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2ff2be342e8e5290e4d8da0b9b348f5c13bd22bd63b41e182973822e7e7e7bf3","abstract_canon_sha256":"ef1cbab8cf1be5d0e5f5a95cdf1f4436d04495e634e59363e43c188acdc26a20"},"schema_version":"1.0"},"canonical_sha256":"f329c8c84c753b4a1d0007cb3b4124578a487b403432198273d918f60e24d13d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:40.557656Z","signature_b64":"jHVFO6K9ckKKNHpLbDAlEl8gRJdEOmvRNGUBf3tQztb/d2a/ttm4H2zQ0SK/HVfekvM2ZUmElG3GEBCqqjOwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f329c8c84c753b4a1d0007cb3b4124578a487b403432198273d918f60e24d13d","last_reissued_at":"2026-05-18T00:11:40.556897Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:40.556897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.04062","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":"2026-05-18T00:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGHsd3PfA3kF8sZnD5EC5qRB6vBL3W58H1eZcFN0DqBSiuFFt8J5crNgWWYY3PVv1Ci801wlepvLoB/6cgJcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:17:21.506957Z"},"content_sha256":"ec40aaf5ed103966d57ce5b6fe6d12fe4edf32f3d183f24d7e4969cc228c4419","schema_version":"1.0","event_id":"sha256:ec40aaf5ed103966d57ce5b6fe6d12fe4edf32f3d183f24d7e4969cc228c4419"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6MU4RSCMOU5UUHIAA7FTWQJEK6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decentralized Online Learning with Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"primary_cat":"math.OC","authors_text":"Alec Koppel, Alejandro Ribeiro, Cedric Richard, Santiago Paternain","submitted_at":"2017-10-11T13:49:28Z","abstract_excerpt":"We consider multi-agent stochastic optimization problems over reproducing kernel Hilbert spaces (RKHS). In this setting, a network of interconnected agents aims to learn decision functions, i.e., nonlinear statistical models, that are optimal in terms of a global convex functional that aggregates data across the network, with only access to locally and sequentially observed samples. We propose solving this problem by allowing each agent to learn a local regression function while enforcing consensus constraints. We use a penalized variant of functional stochastic gradient descent operating simu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04062","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":"2026-05-18T00:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pRjcpPvA+5W6PTJUoD8EMEik4UysiLjpeOBefOm2YTzhVnrOHLujoPq516IwmxI0YHeCSeVEgnUcAr5qutHYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T16:17:21.507312Z"},"content_sha256":"fc4b7c5dd72c456e64b1d01b5013dd9c6de6db6610a08d14b195f3e5741d91b3","schema_version":"1.0","event_id":"sha256:fc4b7c5dd72c456e64b1d01b5013dd9c6de6db6610a08d14b195f3e5741d91b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/bundle.json","state_url":"https://pith.science/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/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":"2026-06-05T16:17:21Z","links":{"resolver":"https://pith.science/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6","bundle":"https://pith.science/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/bundle.json","state":"https://pith.science/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MU4RSCMOU5UUHIAA7FTWQJEK6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6MU4RSCMOU5UUHIAA7FTWQJEK6","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":"ef1cbab8cf1be5d0e5f5a95cdf1f4436d04495e634e59363e43c188acdc26a20","cross_cats_sorted":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-11T13:49:28Z","title_canon_sha256":"2ff2be342e8e5290e4d8da0b9b348f5c13bd22bd63b41e182973822e7e7e7bf3"},"schema_version":"1.0","source":{"id":"1710.04062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04062","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04062v1","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04062","created_at":"2026-05-18T00:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"6MU4RSCMOU5U","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6MU4RSCMOU5UUHIA","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6MU4RSCM","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:fc4b7c5dd72c456e64b1d01b5013dd9c6de6db6610a08d14b195f3e5741d91b3","target":"graph","created_at":"2026-05-18T00:11:40Z","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":"We consider multi-agent stochastic optimization problems over reproducing kernel Hilbert spaces (RKHS). In this setting, a network of interconnected agents aims to learn decision functions, i.e., nonlinear statistical models, that are optimal in terms of a global convex functional that aggregates data across the network, with only access to locally and sequentially observed samples. We propose solving this problem by allowing each agent to learn a local regression function while enforcing consensus constraints. We use a penalized variant of functional stochastic gradient descent operating simu","authors_text":"Alec Koppel, Alejandro Ribeiro, Cedric Richard, Santiago Paternain","cross_cats":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-11T13:49:28Z","title":"Decentralized Online Learning with Kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04062","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:ec40aaf5ed103966d57ce5b6fe6d12fe4edf32f3d183f24d7e4969cc228c4419","target":"record","created_at":"2026-05-18T00:11:40Z","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":"ef1cbab8cf1be5d0e5f5a95cdf1f4436d04495e634e59363e43c188acdc26a20","cross_cats_sorted":["cs.DC","cs.LG","cs.MA","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-11T13:49:28Z","title_canon_sha256":"2ff2be342e8e5290e4d8da0b9b348f5c13bd22bd63b41e182973822e7e7e7bf3"},"schema_version":"1.0","source":{"id":"1710.04062","kind":"arxiv","version":1}},"canonical_sha256":"f329c8c84c753b4a1d0007cb3b4124578a487b403432198273d918f60e24d13d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f329c8c84c753b4a1d0007cb3b4124578a487b403432198273d918f60e24d13d","first_computed_at":"2026-05-18T00:11:40.556897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:40.556897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jHVFO6K9ckKKNHpLbDAlEl8gRJdEOmvRNGUBf3tQztb/d2a/ttm4H2zQ0SK/HVfekvM2ZUmElG3GEBCqqjOwCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:40.557656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.04062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec40aaf5ed103966d57ce5b6fe6d12fe4edf32f3d183f24d7e4969cc228c4419","sha256:fc4b7c5dd72c456e64b1d01b5013dd9c6de6db6610a08d14b195f3e5741d91b3"],"state_sha256":"6fcc58cb308bdd155e6a0fc9fec677ae0bf1253be8a391a23c5bfbec6ecb8b37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfTSunEKhHrnf9ZS0pQMKHTKcTS8WMIEEZPsakD15RxqYOTZl0nE+p84kI2AkmiK/Z+P0TZyP6Ey8WSVYEmfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T16:17:21.509309Z","bundle_sha256":"076755e14b96ec84cddabbf698b2bdb15fe65e8ef99c5079cd5b7cc2271a73a8"}}