{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FPMKDWRHIR4CQ4JR5FLI3OB52K","short_pith_number":"pith:FPMKDWRH","schema_version":"1.0","canonical_sha256":"2bd8a1da274478287131e9568db83dd2867355f73dfa492b766069397b2d4d88","source":{"kind":"arxiv","id":"2201.11739","version":1},"attestation_state":"computed","paper":{"title":"Robust Augmentation for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hong Yang, Travis Desell","submitted_at":"2022-01-27T18:57:49Z","abstract_excerpt":"Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets may contain fewer than 100 training examples. In this paper, we show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance in a statistically significant way for convolutional, recurrent, and self-attention based architectures for time series classification. We evaluate these methods on 26 datasets f"},"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":"2201.11739","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-27T18:57:49Z","cross_cats_sorted":[],"title_canon_sha256":"4f8857941598909881a4b33a09c816f5b3a29b0122a45a10f84a718b6ae41894","abstract_canon_sha256":"74e0897ec24d4ef1bed47bbfe27456c495c3f9e2504d9b0f2e0e39d5469bb757"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:09.731203Z","signature_b64":"MJK2RKRxiT82wF068l4XNjMfGMuaB+BSiBX3FpNqdUuMcp/veZx5BGUsrhakZPKaCl1m8vLy7/XgC+4tWuagCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bd8a1da274478287131e9568db83dd2867355f73dfa492b766069397b2d4d88","last_reissued_at":"2026-07-05T03:52:09.730748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:09.730748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Augmentation for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hong Yang, Travis Desell","submitted_at":"2022-01-27T18:57:49Z","abstract_excerpt":"Neural networks are capable of learning powerful representations of data, but they are susceptible to overfitting due to the number of parameters. This is particularly challenging in the domain of time series classification, where datasets may contain fewer than 100 training examples. In this paper, we show that the simple methods of cutout, cutmix, mixup, and window warp improve the robustness and overall performance in a statistically significant way for convolutional, recurrent, and self-attention based architectures for time series classification. We evaluate these methods on 26 datasets f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11739","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/2201.11739/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":"2201.11739","created_at":"2026-07-05T03:52:09.730814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11739v1","created_at":"2026-07-05T03:52:09.730814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11739","created_at":"2026-07-05T03:52:09.730814+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPMKDWRHIR4C","created_at":"2026-07-05T03:52:09.730814+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPMKDWRHIR4CQ4JR","created_at":"2026-07-05T03:52:09.730814+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPMKDWRH","created_at":"2026-07-05T03:52:09.730814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20656","citing_title":"Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K","json":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K.json","graph_json":"https://pith.science/api/pith-number/FPMKDWRHIR4CQ4JR5FLI3OB52K/graph.json","events_json":"https://pith.science/api/pith-number/FPMKDWRHIR4CQ4JR5FLI3OB52K/events.json","paper":"https://pith.science/paper/FPMKDWRH"},"agent_actions":{"view_html":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K","download_json":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K.json","view_paper":"https://pith.science/paper/FPMKDWRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11739&json=true","fetch_graph":"https://pith.science/api/pith-number/FPMKDWRHIR4CQ4JR5FLI3OB52K/graph.json","fetch_events":"https://pith.science/api/pith-number/FPMKDWRHIR4CQ4JR5FLI3OB52K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K/action/storage_attestation","attest_author":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K/action/author_attestation","sign_citation":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K/action/citation_signature","submit_replication":"https://pith.science/pith/FPMKDWRHIR4CQ4JR5FLI3OB52K/action/replication_record"}},"created_at":"2026-07-05T03:52:09.730814+00:00","updated_at":"2026-07-05T03:52:09.730814+00:00"}