{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2WHHFKQORAF5NXKUDMFN5XYCG7","short_pith_number":"pith:2WHHFKQO","schema_version":"1.0","canonical_sha256":"d58e72aa0e880bd6dd541b0adedf0237c0e9cbcf86e3af5f256c696911f11ccc","source":{"kind":"arxiv","id":"2510.03244","version":2},"attestation_state":"computed","paper":{"title":"VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Danny Dongning Sun, Fei Ma, Hang Yu, Hongkang Zhang, Jian Xu, Shao-Lun Huang, Tongtong Feng, Xiao-Ping Zhang, Yanlong Wang, Zijian Zhang","submitted_at":"2025-09-25T14:02:26Z","abstract_excerpt":"Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies. Meanwhile, existing cross-modal methods predominantly rely on textual modalities, leaving the spatial pattern recognition capabilities of vision models underexplored for time series analysis. To address these limitations, we propose VFEM, a cross-modal forecasting model that leverages pre-trained large vision models (LVMs) to capture complex cross-variable patterns. VFEM transforms multivariate time series into visual r"},"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":"2510.03244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-25T14:02:26Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"278479586ae777b2370584a407e6b6f485fd3849064f73b63fa24f153ef25533","abstract_canon_sha256":"c1d7729f0f988c636402a500558f9bd53ff5d1bc20e07adffce36027ef459688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:10.432841Z","signature_b64":"jm2U0fBCbDBvKasT1oHnSjbq3BcrpbSBmTjQbrT6PimXqLO018lfb+4BkWfAasRhMfFfp7m3I4vIAp4RrQM6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d58e72aa0e880bd6dd541b0adedf0237c0e9cbcf86e3af5f256c696911f11ccc","last_reissued_at":"2026-06-09T02:07:10.431965Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:10.431965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Danny Dongning Sun, Fei Ma, Hang Yu, Hongkang Zhang, Jian Xu, Shao-Lun Huang, Tongtong Feng, Xiao-Ping Zhang, Yanlong Wang, Zijian Zhang","submitted_at":"2025-09-25T14:02:26Z","abstract_excerpt":"Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies. Meanwhile, existing cross-modal methods predominantly rely on textual modalities, leaving the spatial pattern recognition capabilities of vision models underexplored for time series analysis. To address these limitations, we propose VFEM, a cross-modal forecasting model that leverages pre-trained large vision models (LVMs) to capture complex cross-variable patterns. VFEM transforms multivariate time series into visual r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03244","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/2510.03244/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":"2510.03244","created_at":"2026-06-09T02:07:10.432097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03244v2","created_at":"2026-06-09T02:07:10.432097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03244","created_at":"2026-06-09T02:07:10.432097+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WHHFKQORAF5","created_at":"2026-06-09T02:07:10.432097+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WHHFKQORAF5NXKU","created_at":"2026-06-09T02:07:10.432097+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WHHFKQO","created_at":"2026-06-09T02:07:10.432097+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/2WHHFKQORAF5NXKUDMFN5XYCG7","json":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7.json","graph_json":"https://pith.science/api/pith-number/2WHHFKQORAF5NXKUDMFN5XYCG7/graph.json","events_json":"https://pith.science/api/pith-number/2WHHFKQORAF5NXKUDMFN5XYCG7/events.json","paper":"https://pith.science/paper/2WHHFKQO"},"agent_actions":{"view_html":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7","download_json":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7.json","view_paper":"https://pith.science/paper/2WHHFKQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03244&json=true","fetch_graph":"https://pith.science/api/pith-number/2WHHFKQORAF5NXKUDMFN5XYCG7/graph.json","fetch_events":"https://pith.science/api/pith-number/2WHHFKQORAF5NXKUDMFN5XYCG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7/action/storage_attestation","attest_author":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7/action/author_attestation","sign_citation":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7/action/citation_signature","submit_replication":"https://pith.science/pith/2WHHFKQORAF5NXKUDMFN5XYCG7/action/replication_record"}},"created_at":"2026-06-09T02:07:10.432097+00:00","updated_at":"2026-06-09T02:07:10.432097+00:00"}