{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DB3QE3GNVTPZJ4PR2SWP3242XC","short_pith_number":"pith:DB3QE3GN","schema_version":"1.0","canonical_sha256":"1877026ccdacdf94f1f1d4acfdeb9ab8bcec31ff662ad19acda6d10184f1f86f","source":{"kind":"arxiv","id":"2203.03445","version":2},"attestation_state":"computed","paper":{"title":"S-Rocket: Selective Random Convolution Kernels for Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hojjat Salehinejad, Shahrokh Valaee, Tang Jin, Yang Wang, Yuanhao Yu","submitted_at":"2022-03-07T15:02:12Z","abstract_excerpt":"Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-D convolution kernels of different configurations. The output of the convolution operation on each time series is represented by a partial positive value (PPV). A concatenation of PPVs from all kernels is the input feature vector to a Ridge regression classifier. Unlike typical deep learning models, the kernels are not trained and there is no weighted/trainable connection between kernels or concatenated features and "},"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":"2203.03445","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-07T15:02:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26d841fcaca6006cf790aeb0f3d2f275485842471f1e6b3db78fa697d9767145","abstract_canon_sha256":"4aaceb3aa93d333421ebca7101f32431a5764c93a5c56723e7ecf062e4920f0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:54.222910Z","signature_b64":"eCGEHDIJDNWoeW/yaK4kyFomQi+cZ/fnXlFwWIkGq55OpUsOYYM9vBhlN2xDFdlYrRjzduDK9uQV5N90sKpCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1877026ccdacdf94f1f1d4acfdeb9ab8bcec31ff662ad19acda6d10184f1f86f","last_reissued_at":"2026-07-05T04:58:54.222431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:54.222431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-Rocket: Selective Random Convolution Kernels for Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hojjat Salehinejad, Shahrokh Valaee, Tang Jin, Yang Wang, Yuanhao Yu","submitted_at":"2022-03-07T15:02:12Z","abstract_excerpt":"Random convolution kernel transform (Rocket) is a fast, efficient, and novel approach for time series feature extraction using a large number of independent randomly initialized 1-D convolution kernels of different configurations. The output of the convolution operation on each time series is represented by a partial positive value (PPV). A concatenation of PPVs from all kernels is the input feature vector to a Ridge regression classifier. Unlike typical deep learning models, the kernels are not trained and there is no weighted/trainable connection between kernels or concatenated features and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03445","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/2203.03445/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":"2203.03445","created_at":"2026-07-05T04:58:54.222496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03445v2","created_at":"2026-07-05T04:58:54.222496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03445","created_at":"2026-07-05T04:58:54.222496+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB3QE3GNVTPZ","created_at":"2026-07-05T04:58:54.222496+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB3QE3GNVTPZJ4PR","created_at":"2026-07-05T04:58:54.222496+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB3QE3GN","created_at":"2026-07-05T04:58:54.222496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.01115","citing_title":"Time series classification with random convolution kernels: pooling operators and input representations matter","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07953","citing_title":"Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC","json":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC.json","graph_json":"https://pith.science/api/pith-number/DB3QE3GNVTPZJ4PR2SWP3242XC/graph.json","events_json":"https://pith.science/api/pith-number/DB3QE3GNVTPZJ4PR2SWP3242XC/events.json","paper":"https://pith.science/paper/DB3QE3GN"},"agent_actions":{"view_html":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC","download_json":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC.json","view_paper":"https://pith.science/paper/DB3QE3GN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03445&json=true","fetch_graph":"https://pith.science/api/pith-number/DB3QE3GNVTPZJ4PR2SWP3242XC/graph.json","fetch_events":"https://pith.science/api/pith-number/DB3QE3GNVTPZJ4PR2SWP3242XC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC/action/storage_attestation","attest_author":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC/action/author_attestation","sign_citation":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC/action/citation_signature","submit_replication":"https://pith.science/pith/DB3QE3GNVTPZJ4PR2SWP3242XC/action/replication_record"}},"created_at":"2026-07-05T04:58:54.222496+00:00","updated_at":"2026-07-05T04:58:54.222496+00:00"}