{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LP23IWK5RJBO2TXILFYCIZW63S","short_pith_number":"pith:LP23IWK5","schema_version":"1.0","canonical_sha256":"5bf5b4595d8a42ed4ee859702466dedc80e92b6fe6e85db7d21a2a6b8ef1cbf4","source":{"kind":"arxiv","id":"2601.21726","version":2},"attestation_state":"computed","paper":{"title":"DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Wang, Qingsong Wen, Siru Zhong, Yiqiu Liu, Yuxuan Liang, Zezhi Shao, Zhiqing Cui","submitted_at":"2026-01-29T13:49:20Z","abstract_excerpt":"Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency. In this paper, we introduce DropoutTS, a model-agnostic plugin that shifts the paradigm from \"what\" to learn to \"how much\" to learn. DropoutTS employs a Sample-Adaptive Dropout mechanism: leveraging spectral sparsity to efficiently quantify instance-level noise via reconstruction residuals, it dynamically calibrates model learning capacity by mapping noise to adaptive"},"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":"2601.21726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T13:49:20Z","cross_cats_sorted":[],"title_canon_sha256":"6a9f1efabb8f938b7bff8ed45f78629817bb970890ecd224c500c593004faa73","abstract_canon_sha256":"0ec1db5a7148e5f897b5c56e07b27850117453fdb8ba2259ae7519673f692fea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:23.663339Z","signature_b64":"EvDhCSk1/rBzqKHkbKi03O+Md6GGKcEVgPJI5JS04lTfBFwhQPSrFjloAzXcIc3pnMvE0JZVVeLXZLSMP7yTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf5b4595d8a42ed4ee859702466dedc80e92b6fe6e85db7d21a2a6b8ef1cbf4","last_reissued_at":"2026-05-26T01:03:23.662274Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:23.662274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Wang, Qingsong Wen, Siru Zhong, Yiqiu Liu, Yuxuan Liang, Zezhi Shao, Zhiqing Cui","submitted_at":"2026-01-29T13:49:20Z","abstract_excerpt":"Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency. In this paper, we introduce DropoutTS, a model-agnostic plugin that shifts the paradigm from \"what\" to learn to \"how much\" to learn. DropoutTS employs a Sample-Adaptive Dropout mechanism: leveraging spectral sparsity to efficiently quantify instance-level noise via reconstruction residuals, it dynamically calibrates model learning capacity by mapping noise to adaptive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21726","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/2601.21726/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":"2601.21726","created_at":"2026-05-26T01:03:23.662440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21726v2","created_at":"2026-05-26T01:03:23.662440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21726","created_at":"2026-05-26T01:03:23.662440+00:00"},{"alias_kind":"pith_short_12","alias_value":"LP23IWK5RJBO","created_at":"2026-05-26T01:03:23.662440+00:00"},{"alias_kind":"pith_short_16","alias_value":"LP23IWK5RJBO2TXI","created_at":"2026-05-26T01:03:23.662440+00:00"},{"alias_kind":"pith_short_8","alias_value":"LP23IWK5","created_at":"2026-05-26T01:03:23.662440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06310","citing_title":"Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S","json":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S.json","graph_json":"https://pith.science/api/pith-number/LP23IWK5RJBO2TXILFYCIZW63S/graph.json","events_json":"https://pith.science/api/pith-number/LP23IWK5RJBO2TXILFYCIZW63S/events.json","paper":"https://pith.science/paper/LP23IWK5"},"agent_actions":{"view_html":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S","download_json":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S.json","view_paper":"https://pith.science/paper/LP23IWK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21726&json=true","fetch_graph":"https://pith.science/api/pith-number/LP23IWK5RJBO2TXILFYCIZW63S/graph.json","fetch_events":"https://pith.science/api/pith-number/LP23IWK5RJBO2TXILFYCIZW63S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S/action/storage_attestation","attest_author":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S/action/author_attestation","sign_citation":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S/action/citation_signature","submit_replication":"https://pith.science/pith/LP23IWK5RJBO2TXILFYCIZW63S/action/replication_record"}},"created_at":"2026-05-26T01:03:23.662440+00:00","updated_at":"2026-05-26T01:03:23.662440+00:00"}