{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KKELCZJZMQ2F33274FMXXBKNPF","short_pith_number":"pith:KKELCZJZ","schema_version":"1.0","canonical_sha256":"5288b1653964345def5fe1597b854d7973a91984ca01e85cb129dc1520109a69","source":{"kind":"arxiv","id":"2406.01638","version":5},"attestation_state":"computed","paper":{"title":"TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Long, Chenxi Liu, Hao Miao, Lingzheng Zhang, Qianxiong Xu, Rui Zhao, Sun Yang, Ziyue Li","submitted_at":"2024-06-03T00:27:29Z","abstract_excerpt":"Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suffer from limited learnable parameters and small-scale training data. Recently, large language models (LLMs) combining time series with textual prompts have achieved promising performance in MTSF. However, we discovered that current LLM-based solutions fall short in learning disentangled embeddings. We introduce TimeCMA, an intuitive yet effective framework for MTSF via cross-modality alignment. Specifically, we prese"},"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":"2406.01638","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T00:27:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"afad02765863137763b4df7ea30b3f8c63d426ee3e9c6bc7ce9a536cca8d3e0a","abstract_canon_sha256":"324a9b0e9d2098021f19981c9ca6a79ba5a896da6549acfc60c49eaff711c65e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:12.909587Z","signature_b64":"bgdBYuh3AlV7Mb/U2VgO9JdKWwf9LAG66eykCfSXe8G6fTZAH+qeMMeRBsJsEvS+lgMpGsgqztLtrMV8zNNkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5288b1653964345def5fe1597b854d7973a91984ca01e85cb129dc1520109a69","last_reissued_at":"2026-07-05T10:41:12.909082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:12.909082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Cheng Long, Chenxi Liu, Hao Miao, Lingzheng Zhang, Qianxiong Xu, Rui Zhao, Sun Yang, Ziyue Li","submitted_at":"2024-06-03T00:27:29Z","abstract_excerpt":"Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suffer from limited learnable parameters and small-scale training data. Recently, large language models (LLMs) combining time series with textual prompts have achieved promising performance in MTSF. However, we discovered that current LLM-based solutions fall short in learning disentangled embeddings. We introduce TimeCMA, an intuitive yet effective framework for MTSF via cross-modality alignment. Specifically, we prese"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01638","kind":"arxiv","version":5},"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/2406.01638/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":"2406.01638","created_at":"2026-07-05T10:41:12.909143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01638v5","created_at":"2026-07-05T10:41:12.909143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01638","created_at":"2026-07-05T10:41:12.909143+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKELCZJZMQ2F","created_at":"2026-07-05T10:41:12.909143+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKELCZJZMQ2F3327","created_at":"2026-07-05T10:41:12.909143+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKELCZJZ","created_at":"2026-07-05T10:41:12.909143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.23090","citing_title":"MAP4TS: A Multi-Aspect Prompting Framework for Time-Series Forecasting with Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11512","citing_title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14422","citing_title":"What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF","json":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF.json","graph_json":"https://pith.science/api/pith-number/KKELCZJZMQ2F33274FMXXBKNPF/graph.json","events_json":"https://pith.science/api/pith-number/KKELCZJZMQ2F33274FMXXBKNPF/events.json","paper":"https://pith.science/paper/KKELCZJZ"},"agent_actions":{"view_html":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF","download_json":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF.json","view_paper":"https://pith.science/paper/KKELCZJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01638&json=true","fetch_graph":"https://pith.science/api/pith-number/KKELCZJZMQ2F33274FMXXBKNPF/graph.json","fetch_events":"https://pith.science/api/pith-number/KKELCZJZMQ2F33274FMXXBKNPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF/action/storage_attestation","attest_author":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF/action/author_attestation","sign_citation":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF/action/citation_signature","submit_replication":"https://pith.science/pith/KKELCZJZMQ2F33274FMXXBKNPF/action/replication_record"}},"created_at":"2026-07-05T10:41:12.909143+00:00","updated_at":"2026-07-05T10:41:12.909143+00:00"}