{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JMD5QZRJ3RT2LFOXZAIRZAAKWE","short_pith_number":"pith:JMD5QZRJ","schema_version":"1.0","canonical_sha256":"4b07d86629dc67a595d7c8111c800ab13f7929445cf079a0d1ca147dd1c9f3e9","source":{"kind":"arxiv","id":"2207.11486","version":1},"attestation_state":"computed","paper":{"title":"Time Series Prediction under Distribution Shift using Differentiable Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.ST"],"primary_cat":"cs.LG","authors_text":"Jase Clarkson, Stefanos Bennett","submitted_at":"2022-07-23T10:32:37Z","abstract_excerpt":"Time series prediction is often complicated by distribution shift which demands adaptive models to accommodate time-varying distributions. We frame time series prediction under distribution shift as a weighted empirical risk minimisation problem. The weighting of previous observations in the empirical risk is determined by a forgetting mechanism which controls the trade-off between the relevancy and effective sample size that is used for the estimation of the predictive model. In contrast to previous work, we propose a gradient-based learning method for the parameters of the forgetting mechani"},"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":"2207.11486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-23T10:32:37Z","cross_cats_sorted":["q-fin.ST"],"title_canon_sha256":"785d0f0bc709aa8abbc19e7d75720ca88441ebd530672318eecf9970944d68b9","abstract_canon_sha256":"96ac01d48fa78e4b092099454d515857df529e798d2e7902f7f66c07f56f2bb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:05.906969Z","signature_b64":"k6PqxT333aKXQwClBb3h6LdYoKk3x2sSOr5VZhXVvqBJD/EmGjYWjtaZduWLDxAA563ViO5XjFsERMF2vw7SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b07d86629dc67a595d7c8111c800ab13f7929445cf079a0d1ca147dd1c9f3e9","last_reissued_at":"2026-07-05T04:43:05.906374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:05.906374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Series Prediction under Distribution Shift using Differentiable Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.ST"],"primary_cat":"cs.LG","authors_text":"Jase Clarkson, Stefanos Bennett","submitted_at":"2022-07-23T10:32:37Z","abstract_excerpt":"Time series prediction is often complicated by distribution shift which demands adaptive models to accommodate time-varying distributions. We frame time series prediction under distribution shift as a weighted empirical risk minimisation problem. The weighting of previous observations in the empirical risk is determined by a forgetting mechanism which controls the trade-off between the relevancy and effective sample size that is used for the estimation of the predictive model. In contrast to previous work, we propose a gradient-based learning method for the parameters of the forgetting mechani"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11486","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/2207.11486/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":"2207.11486","created_at":"2026-07-05T04:43:05.906448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11486v1","created_at":"2026-07-05T04:43:05.906448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11486","created_at":"2026-07-05T04:43:05.906448+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMD5QZRJ3RT2","created_at":"2026-07-05T04:43:05.906448+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMD5QZRJ3RT2LFOX","created_at":"2026-07-05T04:43:05.906448+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMD5QZRJ","created_at":"2026-07-05T04:43:05.906448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13868","citing_title":"Out-of-Distribution Generalization in Time Series: A Survey","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE","json":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE.json","graph_json":"https://pith.science/api/pith-number/JMD5QZRJ3RT2LFOXZAIRZAAKWE/graph.json","events_json":"https://pith.science/api/pith-number/JMD5QZRJ3RT2LFOXZAIRZAAKWE/events.json","paper":"https://pith.science/paper/JMD5QZRJ"},"agent_actions":{"view_html":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE","download_json":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE.json","view_paper":"https://pith.science/paper/JMD5QZRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11486&json=true","fetch_graph":"https://pith.science/api/pith-number/JMD5QZRJ3RT2LFOXZAIRZAAKWE/graph.json","fetch_events":"https://pith.science/api/pith-number/JMD5QZRJ3RT2LFOXZAIRZAAKWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE/action/storage_attestation","attest_author":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE/action/author_attestation","sign_citation":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE/action/citation_signature","submit_replication":"https://pith.science/pith/JMD5QZRJ3RT2LFOXZAIRZAAKWE/action/replication_record"}},"created_at":"2026-07-05T04:43:05.906448+00:00","updated_at":"2026-07-05T04:43:05.906448+00:00"}