{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FSSPGEJQUTBIJR4ZN4TSA7ALCS","short_pith_number":"pith:FSSPGEJQ","schema_version":"1.0","canonical_sha256":"2ca4f31130a4c284c7996f27207c0b14a26d3c16b0dbeb66bf08a0acb56b9640","source":{"kind":"arxiv","id":"2002.10061","version":3},"attestation_state":"computed","paper":{"title":"Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Long, Jing Jiang, Lu Liu, Michael Blumenstein, Tianyi Zhou, Wensi Tang","submitted_at":"2020-02-24T03:33:58Z","abstract_excerpt":"The Receptive Field (RF) size has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. Large efforts have been taken to choose the appropriate size because it has a huge influence on the performance and differs significantly for each dataset. In this paper, we propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and universal rule. Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multipl"},"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":"2002.10061","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T03:33:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"21ab9a6d692de6bb8eb4b2d9d1c1f9d2a5fe44ecde8e654b30ddc0e083038f5b","abstract_canon_sha256":"f2375498c6e75a4a57ed2131d7055c5d056b2b810a1c12ae77f53d059d44b3d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:36.065140Z","signature_b64":"ZaK50oPS2Ffs7oID8GVAQtF+CizoCc3WyNmi5R93Sqsb5+fsccQNZWXrjxEhINxUrwDr4q14pQYtYyPamND7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ca4f31130a4c284c7996f27207c0b14a26d3c16b0dbeb66bf08a0acb56b9640","last_reissued_at":"2026-07-05T04:32:36.064657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:36.064657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guodong Long, Jing Jiang, Lu Liu, Michael Blumenstein, Tianyi Zhou, Wensi Tang","submitted_at":"2020-02-24T03:33:58Z","abstract_excerpt":"The Receptive Field (RF) size has been one of the most important factors for One Dimensional Convolutional Neural Networks (1D-CNNs) on time series classification tasks. Large efforts have been taken to choose the appropriate size because it has a huge influence on the performance and differs significantly for each dataset. In this paper, we propose an Omni-Scale block (OS-block) for 1D-CNNs, where the kernel sizes are decided by a simple and universal rule. Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multipl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10061","kind":"arxiv","version":3},"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/2002.10061/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":"2002.10061","created_at":"2026-07-05T04:32:36.064716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10061v3","created_at":"2026-07-05T04:32:36.064716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10061","created_at":"2026-07-05T04:32:36.064716+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSSPGEJQUTBI","created_at":"2026-07-05T04:32:36.064716+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSSPGEJQUTBIJR4Z","created_at":"2026-07-05T04:32:36.064716+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSSPGEJQ","created_at":"2026-07-05T04:32:36.064716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22055","citing_title":"Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02577","citing_title":"ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04475","citing_title":"Discrete Prototypical Memories for Federated Time Series Foundation Models","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS","json":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS.json","graph_json":"https://pith.science/api/pith-number/FSSPGEJQUTBIJR4ZN4TSA7ALCS/graph.json","events_json":"https://pith.science/api/pith-number/FSSPGEJQUTBIJR4ZN4TSA7ALCS/events.json","paper":"https://pith.science/paper/FSSPGEJQ"},"agent_actions":{"view_html":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS","download_json":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS.json","view_paper":"https://pith.science/paper/FSSPGEJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10061&json=true","fetch_graph":"https://pith.science/api/pith-number/FSSPGEJQUTBIJR4ZN4TSA7ALCS/graph.json","fetch_events":"https://pith.science/api/pith-number/FSSPGEJQUTBIJR4ZN4TSA7ALCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS/action/storage_attestation","attest_author":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS/action/author_attestation","sign_citation":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS/action/citation_signature","submit_replication":"https://pith.science/pith/FSSPGEJQUTBIJR4ZN4TSA7ALCS/action/replication_record"}},"created_at":"2026-07-05T04:32:36.064716+00:00","updated_at":"2026-07-05T04:32:36.064716+00:00"}