{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RTVI2NXLEKHAFDVYUFV7BLK4YM","short_pith_number":"pith:RTVI2NXL","schema_version":"1.0","canonical_sha256":"8cea8d36eb228e028eb8a16bf0ad5cc336c30191c68775685a184be6293ea851","source":{"kind":"arxiv","id":"2006.07310","version":2},"attestation_state":"computed","paper":{"title":"Reservoir Computing meets Recurrent Kernels and Structured Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"stat.ML","authors_text":"Florent Krzakala, Jonathan Dong, Mushegh Rafayelyan, Ruben Ohana","submitted_at":"2020-06-12T16:46:34Z","abstract_excerpt":"Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks have a deep connection with kernel methods. Our contributions are threefold: a) We rigorously establish the recurrent kernel limit of Reservoir Computing and prove its convergence. b) We test our models on chaotic time series prediction, a classic but challenging benchmark in Reservoir Computing, and show how the Recurrent Kernel is competitive and computationally efficient whe"},"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":"2006.07310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-06-12T16:46:34Z","cross_cats_sorted":["cs.LG","eess.SP"],"title_canon_sha256":"a449a5345787ea2634c71fe1425d27d0c5bd9aeef18d4959df835ddc9b6e603d","abstract_canon_sha256":"08ddc0f36b914c7c6709ba3324a16990cd6d11f239040124b3a2b774c01e42c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:58.104695Z","signature_b64":"ksYqQfLKtqM724Hr8uKtPcGD5tqaT0TrPZvIu/oiSo3nX+UE5h+BHxHHhal3KFUg1mdqDkbYDqPu1zN/k9pHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cea8d36eb228e028eb8a16bf0ad5cc336c30191c68775685a184be6293ea851","last_reissued_at":"2026-07-05T02:15:58.104270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:58.104270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reservoir Computing meets Recurrent Kernels and Structured Transforms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"stat.ML","authors_text":"Florent Krzakala, Jonathan Dong, Mushegh Rafayelyan, Ruben Ohana","submitted_at":"2020-06-12T16:46:34Z","abstract_excerpt":"Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained. In the large size limit, such random neural networks have a deep connection with kernel methods. Our contributions are threefold: a) We rigorously establish the recurrent kernel limit of Reservoir Computing and prove its convergence. b) We test our models on chaotic time series prediction, a classic but challenging benchmark in Reservoir Computing, and show how the Recurrent Kernel is competitive and computationally efficient whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07310","kind":"arxiv","version":2},"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/2006.07310/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":"2006.07310","created_at":"2026-07-05T02:15:58.104336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07310v2","created_at":"2026-07-05T02:15:58.104336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07310","created_at":"2026-07-05T02:15:58.104336+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTVI2NXLEKHA","created_at":"2026-07-05T02:15:58.104336+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTVI2NXLEKHAFDVY","created_at":"2026-07-05T02:15:58.104336+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTVI2NXL","created_at":"2026-07-05T02:15:58.104336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01410","citing_title":"Unwrapping photonic reservoirs: enhanced expressivity via random Fourier encoding over stretched domains","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM","json":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM.json","graph_json":"https://pith.science/api/pith-number/RTVI2NXLEKHAFDVYUFV7BLK4YM/graph.json","events_json":"https://pith.science/api/pith-number/RTVI2NXLEKHAFDVYUFV7BLK4YM/events.json","paper":"https://pith.science/paper/RTVI2NXL"},"agent_actions":{"view_html":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM","download_json":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM.json","view_paper":"https://pith.science/paper/RTVI2NXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07310&json=true","fetch_graph":"https://pith.science/api/pith-number/RTVI2NXLEKHAFDVYUFV7BLK4YM/graph.json","fetch_events":"https://pith.science/api/pith-number/RTVI2NXLEKHAFDVYUFV7BLK4YM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM/action/storage_attestation","attest_author":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM/action/author_attestation","sign_citation":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM/action/citation_signature","submit_replication":"https://pith.science/pith/RTVI2NXLEKHAFDVYUFV7BLK4YM/action/replication_record"}},"created_at":"2026-07-05T02:15:58.104336+00:00","updated_at":"2026-07-05T02:15:58.104336+00:00"}