{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:72OKKSGGE3JSN67PX3OTP34YTN","short_pith_number":"pith:72OKKSGG","schema_version":"1.0","canonical_sha256":"fe9ca548c626d326fbefbedd37ef989b44c0707627890f7da2252c489b9b0e79","source":{"kind":"arxiv","id":"2406.07438","version":3},"attestation_state":"computed","paper":{"title":"DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Vasileios Lampos, Yuxuan Shu","submitted_at":"2024-06-11T16:45:48Z","abstract_excerpt":"In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of using exogenous variables in enhancing the prediction of the target endogenous variable. To address this limitation, we present DeformTime, a neural network architecture that attempts to capture correlated temporal patterns from the input space, and hence, improve forecasting accuracy. It deploys two core operations performed by deformable attention blocks (DABs): learning dependencies across variables from different"},"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":"2406.07438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T16:45:48Z","cross_cats_sorted":[],"title_canon_sha256":"182f492a0b3661905416d4cb9552868f7bf73470116efb731ff95fcc4d478631","abstract_canon_sha256":"debd43c7ee5b7153cd6e47f2f329e56bccc1ebb6868ffa21097c3f83e7bc7e97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:58.983775Z","signature_b64":"oq67QfFB6hPVPJpxg4ypT3almNccnyMhedMzw31IpuywSeIVtAS/Wmt2QpSY7egXA05xeXQQmv53PAMcx3FnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9ca548c626d326fbefbedd37ef989b44c0707627890f7da2252c489b9b0e79","last_reissued_at":"2026-07-05T10:42:58.983329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:58.983329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Vasileios Lampos, Yuxuan Shu","submitted_at":"2024-06-11T16:45:48Z","abstract_excerpt":"In multivariable time series (MTS) forecasting, existing state-of-the-art deep learning approaches tend to focus on autoregressive formulations and often overlook the potential of using exogenous variables in enhancing the prediction of the target endogenous variable. To address this limitation, we present DeformTime, a neural network architecture that attempts to capture correlated temporal patterns from the input space, and hence, improve forecasting accuracy. It deploys two core operations performed by deformable attention blocks (DABs): learning dependencies across variables from different"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07438","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/2406.07438/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":"2406.07438","created_at":"2026-07-05T10:42:58.983381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07438v3","created_at":"2026-07-05T10:42:58.983381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07438","created_at":"2026-07-05T10:42:58.983381+00:00"},{"alias_kind":"pith_short_12","alias_value":"72OKKSGGE3JS","created_at":"2026-07-05T10:42:58.983381+00:00"},{"alias_kind":"pith_short_16","alias_value":"72OKKSGGE3JSN67P","created_at":"2026-07-05T10:42:58.983381+00:00"},{"alias_kind":"pith_short_8","alias_value":"72OKKSGG","created_at":"2026-07-05T10:42:58.983381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19639","citing_title":"Directly Learning Stock Trading Strategies Through Profit Guided Loss Functions","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN","json":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN.json","graph_json":"https://pith.science/api/pith-number/72OKKSGGE3JSN67PX3OTP34YTN/graph.json","events_json":"https://pith.science/api/pith-number/72OKKSGGE3JSN67PX3OTP34YTN/events.json","paper":"https://pith.science/paper/72OKKSGG"},"agent_actions":{"view_html":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN","download_json":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN.json","view_paper":"https://pith.science/paper/72OKKSGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07438&json=true","fetch_graph":"https://pith.science/api/pith-number/72OKKSGGE3JSN67PX3OTP34YTN/graph.json","fetch_events":"https://pith.science/api/pith-number/72OKKSGGE3JSN67PX3OTP34YTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN/action/storage_attestation","attest_author":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN/action/author_attestation","sign_citation":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN/action/citation_signature","submit_replication":"https://pith.science/pith/72OKKSGGE3JSN67PX3OTP34YTN/action/replication_record"}},"created_at":"2026-07-05T10:42:58.983381+00:00","updated_at":"2026-07-05T10:42:58.983381+00:00"}