{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LAO5PSNT23OC4MPNDSKEIVEZMJ","short_pith_number":"pith:LAO5PSNT","schema_version":"1.0","canonical_sha256":"581dd7c9b3d6dc2e31ed1c94445499625dcbaeee775585f3fde00f90a5e9efc0","source":{"kind":"arxiv","id":"2412.04532","version":3},"attestation_state":"computed","paper":{"title":"WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Judy Fox, Md. Khairul Islam","submitted_at":"2024-12-05T17:15:07Z","abstract_excerpt":"Interpreting complex time series forecasting models is challenging due to the temporal dependencies between time steps and the dynamic relevance of input features over time. Existing interpretation methods are limited by focusing mostly on classification tasks, evaluating using custom baseline models instead of the latest time series models, using simple synthetic datasets, and requiring training another model. We introduce a novel interpretation method, \\textit{Windowed Temporal Saliency Rescaling (WinTSR)} addressing these limitations. WinTSR explicitly captures temporal dependencies among t"},"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":"2412.04532","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-05T17:15:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f20211dac964dc9c9ca085fa3bc0f8ab9c6fa4854aff69e5f2cc5b40e10fa23f","abstract_canon_sha256":"7f3195436c3db32b7eeaddbbac66b868e7d0c39d6577c7d013442b616a4cd4a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:21.148536Z","signature_b64":"OWseuIORlTOt/06QsgrTJRj4soxYqjjVVxViH+lbfTF3kwFFQ0PxcREQGtSz1EYbfSbm6syAZI5wYvI0Vgm1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"581dd7c9b3d6dc2e31ed1c94445499625dcbaeee775585f3fde00f90a5e9efc0","last_reissued_at":"2026-07-05T10:27:21.148014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:21.148014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WinTSR: A Windowed Temporal Saliency Rescaling Method for Interpreting Time Series Deep Learning Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Judy Fox, Md. Khairul Islam","submitted_at":"2024-12-05T17:15:07Z","abstract_excerpt":"Interpreting complex time series forecasting models is challenging due to the temporal dependencies between time steps and the dynamic relevance of input features over time. Existing interpretation methods are limited by focusing mostly on classification tasks, evaluating using custom baseline models instead of the latest time series models, using simple synthetic datasets, and requiring training another model. We introduce a novel interpretation method, \\textit{Windowed Temporal Saliency Rescaling (WinTSR)} addressing these limitations. WinTSR explicitly captures temporal dependencies among t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04532","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/2412.04532/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":"2412.04532","created_at":"2026-07-05T10:27:21.148101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04532v3","created_at":"2026-07-05T10:27:21.148101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04532","created_at":"2026-07-05T10:27:21.148101+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAO5PSNT23OC","created_at":"2026-07-05T10:27:21.148101+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAO5PSNT23OC4MPN","created_at":"2026-07-05T10:27:21.148101+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAO5PSNT","created_at":"2026-07-05T10:27:21.148101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ","json":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ.json","graph_json":"https://pith.science/api/pith-number/LAO5PSNT23OC4MPNDSKEIVEZMJ/graph.json","events_json":"https://pith.science/api/pith-number/LAO5PSNT23OC4MPNDSKEIVEZMJ/events.json","paper":"https://pith.science/paper/LAO5PSNT"},"agent_actions":{"view_html":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ","download_json":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ.json","view_paper":"https://pith.science/paper/LAO5PSNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04532&json=true","fetch_graph":"https://pith.science/api/pith-number/LAO5PSNT23OC4MPNDSKEIVEZMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LAO5PSNT23OC4MPNDSKEIVEZMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ/action/storage_attestation","attest_author":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ/action/author_attestation","sign_citation":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ/action/citation_signature","submit_replication":"https://pith.science/pith/LAO5PSNT23OC4MPNDSKEIVEZMJ/action/replication_record"}},"created_at":"2026-07-05T10:27:21.148101+00:00","updated_at":"2026-07-05T10:27:21.148101+00:00"}