{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IHHEHCRSM2VSVEWPQAQXKHODBC","short_pith_number":"pith:IHHEHCRS","schema_version":"1.0","canonical_sha256":"41ce438a3266ab2a92cf8021751dc308937795a9d8b342d549250f3f60853479","source":{"kind":"arxiv","id":"2505.12917","version":2},"attestation_state":"computed","paper":{"title":"Temporal Query Network for Efficient Multivariate Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunyun Qiu, Haijie Wu, Haojun Chen, Shengsheng Lin, Weiwei Lin","submitted_at":"2025-05-19T09:55:10Z","abstract_excerpt":"Sufficiently modeling the correlations among variables (aka channels) is crucial for achieving accurate multivariate time series forecasting (MTSF). In this paper, we propose a novel technique called Temporal Query (TQ) to more effectively capture multivariate correlations, thereby improving model performance in MTSF tasks. Technically, the TQ technique employs periodically shifted learnable vectors as queries in the attention mechanism to capture global inter-variable patterns, while the keys and values are derived from the raw input data to encode local, sample-level correlations. Building u"},"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":"2505.12917","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T09:55:10Z","cross_cats_sorted":[],"title_canon_sha256":"4c72cd314e5653f0bf1a450295e51bb480699dfeb26367b3a37b55340f664d37","abstract_canon_sha256":"9334f47c0f1fd73d669e1be2f61b448bb90b270df0e15be212c737100df0b6d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:17.837474Z","signature_b64":"HtZ5PNi6v65alnKkBYOYeuXl5CxH+MnxLM03r+RqsTQcx28Tz0pSkENxJLSb2/K6PmCTAI8yKD32io1LSwuxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41ce438a3266ab2a92cf8021751dc308937795a9d8b342d549250f3f60853479","last_reissued_at":"2026-07-05T12:09:17.837068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:17.837068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Query Network for Efficient Multivariate Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunyun Qiu, Haijie Wu, Haojun Chen, Shengsheng Lin, Weiwei Lin","submitted_at":"2025-05-19T09:55:10Z","abstract_excerpt":"Sufficiently modeling the correlations among variables (aka channels) is crucial for achieving accurate multivariate time series forecasting (MTSF). In this paper, we propose a novel technique called Temporal Query (TQ) to more effectively capture multivariate correlations, thereby improving model performance in MTSF tasks. Technically, the TQ technique employs periodically shifted learnable vectors as queries in the attention mechanism to capture global inter-variable patterns, while the keys and values are derived from the raw input data to encode local, sample-level correlations. Building u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12917","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/2505.12917/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":"2505.12917","created_at":"2026-07-05T12:09:17.837125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12917v2","created_at":"2026-07-05T12:09:17.837125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12917","created_at":"2026-07-05T12:09:17.837125+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHHEHCRSM2VS","created_at":"2026-07-05T12:09:17.837125+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHHEHCRSM2VSVEWP","created_at":"2026-07-05T12:09:17.837125+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHHEHCRS","created_at":"2026-07-05T12:09:17.837125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.25914","citing_title":"ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC","json":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC.json","graph_json":"https://pith.science/api/pith-number/IHHEHCRSM2VSVEWPQAQXKHODBC/graph.json","events_json":"https://pith.science/api/pith-number/IHHEHCRSM2VSVEWPQAQXKHODBC/events.json","paper":"https://pith.science/paper/IHHEHCRS"},"agent_actions":{"view_html":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC","download_json":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC.json","view_paper":"https://pith.science/paper/IHHEHCRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12917&json=true","fetch_graph":"https://pith.science/api/pith-number/IHHEHCRSM2VSVEWPQAQXKHODBC/graph.json","fetch_events":"https://pith.science/api/pith-number/IHHEHCRSM2VSVEWPQAQXKHODBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC/action/storage_attestation","attest_author":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC/action/author_attestation","sign_citation":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC/action/citation_signature","submit_replication":"https://pith.science/pith/IHHEHCRSM2VSVEWPQAQXKHODBC/action/replication_record"}},"created_at":"2026-07-05T12:09:17.837125+00:00","updated_at":"2026-07-05T12:09:17.837125+00:00"}