{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:H6IC3EJIJDRHYKGUHSLG56JYYY","short_pith_number":"pith:H6IC3EJI","schema_version":"1.0","canonical_sha256":"3f902d912848e27c28d43c966ef938c6360d77fb89064a03230e8e5e8914beef","source":{"kind":"arxiv","id":"1910.13886","version":1},"attestation_state":"computed","paper":{"title":"Risk bounds for reservoir computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Juan-Pablo Ortega, Lukas Gonon, Lyudmila Grigoryeva","submitted_at":"2019-10-30T14:28:46Z","abstract_excerpt":"We analyze the practices of reservoir computing in the framework of statistical learning theory. In particular, we derive finite sample upper bounds for the generalization error committed by specific families of reservoir computing systems when processing discrete-time inputs under various hypotheses on their dependence structure. Non-asymptotic bounds are explicitly written down in terms of the multivariate Rademacher complexities of the reservoir systems and the weak dependence structure of the signals that are being handled. This allows, in particular, to determine the minimal number of obs"},"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":"1910.13886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-30T14:28:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b073c25e5fcd95e4f6c609ae8e73b3de2d239945a37ada33cdec307a2697d97d","abstract_canon_sha256":"93965d8f33581701d8e44f60d614f4dce5692e7348d340dc74b15b5c4b29a54e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:57.257581Z","signature_b64":"XNFnykIXL1HfVIgz2Vol+Dr+8qNHOS2DjwCtQXLNqOIHW1IeWJgXAMJGs3gjODyiw4YDlWnFs4/X8rDeTbNVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f902d912848e27c28d43c966ef938c6360d77fb89064a03230e8e5e8914beef","last_reissued_at":"2026-07-05T00:15:57.257034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:57.257034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk bounds for reservoir computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Juan-Pablo Ortega, Lukas Gonon, Lyudmila Grigoryeva","submitted_at":"2019-10-30T14:28:46Z","abstract_excerpt":"We analyze the practices of reservoir computing in the framework of statistical learning theory. In particular, we derive finite sample upper bounds for the generalization error committed by specific families of reservoir computing systems when processing discrete-time inputs under various hypotheses on their dependence structure. Non-asymptotic bounds are explicitly written down in terms of the multivariate Rademacher complexities of the reservoir systems and the weak dependence structure of the signals that are being handled. This allows, in particular, to determine the minimal number of obs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13886","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.13886/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.13886","created_at":"2026-07-05T00:15:57.257105+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13886v1","created_at":"2026-07-05T00:15:57.257105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13886","created_at":"2026-07-05T00:15:57.257105+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6IC3EJIJDRH","created_at":"2026-07-05T00:15:57.257105+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6IC3EJIJDRHYKGU","created_at":"2026-07-05T00:15:57.257105+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6IC3EJI","created_at":"2026-07-05T00:15:57.257105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03771","citing_title":"Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing","ref_index":865,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY","json":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY.json","graph_json":"https://pith.science/api/pith-number/H6IC3EJIJDRHYKGUHSLG56JYYY/graph.json","events_json":"https://pith.science/api/pith-number/H6IC3EJIJDRHYKGUHSLG56JYYY/events.json","paper":"https://pith.science/paper/H6IC3EJI"},"agent_actions":{"view_html":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY","download_json":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY.json","view_paper":"https://pith.science/paper/H6IC3EJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13886&json=true","fetch_graph":"https://pith.science/api/pith-number/H6IC3EJIJDRHYKGUHSLG56JYYY/graph.json","fetch_events":"https://pith.science/api/pith-number/H6IC3EJIJDRHYKGUHSLG56JYYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY/action/storage_attestation","attest_author":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY/action/author_attestation","sign_citation":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY/action/citation_signature","submit_replication":"https://pith.science/pith/H6IC3EJIJDRHYKGUHSLG56JYYY/action/replication_record"}},"created_at":"2026-07-05T00:15:57.257105+00:00","updated_at":"2026-07-05T00:15:57.257105+00:00"}