{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7S5HM2SACAOTPRQTXOYJQO2HOU","short_pith_number":"pith:7S5HM2SA","schema_version":"1.0","canonical_sha256":"fcba766a40101d37c613bbb0983b47751dac5e9d301dd75a47b789aa83d06b66","source":{"kind":"arxiv","id":"2401.05012","version":2},"attestation_state":"computed","paper":{"title":"HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengyi Yang, Ming Jin, Qingsong Wen, Shubao Zhao, Yi Wang, Zengxiang Li, Zhaoxiang Hou","submitted_at":"2024-01-10T09:00:03Z","abstract_excerpt":"Time series forecasting is a critical and challenging task in practical application. Recent advancements in pre-trained foundation models for time series forecasting have gained significant interest. However, current methods often overlook the multi-scale nature of time series, which is essential for accurate forecasting. To address this, we propose HiMTM, a hierarchical multi-scale masked time series modeling with self-distillation for long-term forecasting. HiMTM integrates four key components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales"},"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":"2401.05012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-10T09:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"75f00bbb9d5783e88fe6bee759e604c623853e1528b13e3026c5572883cdeb62","abstract_canon_sha256":"ac9d6d08410ff81acb8060a10077bccda545ab77edc60ddf73924ffc24de66fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:53.308824Z","signature_b64":"0M3fXRxi07WKiARDJOLJftthTItRUuFSQIlf81ExBIYn5qO4siY6Wt8UbF2uUGM0Q7Z9dwHEVEukW7/tdDG/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcba766a40101d37c613bbb0983b47751dac5e9d301dd75a47b789aa83d06b66","last_reissued_at":"2026-07-05T08:50:53.308415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:53.308415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling with Self-Distillation for Long-Term Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chengyi Yang, Ming Jin, Qingsong Wen, Shubao Zhao, Yi Wang, Zengxiang Li, Zhaoxiang Hou","submitted_at":"2024-01-10T09:00:03Z","abstract_excerpt":"Time series forecasting is a critical and challenging task in practical application. Recent advancements in pre-trained foundation models for time series forecasting have gained significant interest. However, current methods often overlook the multi-scale nature of time series, which is essential for accurate forecasting. To address this, we propose HiMTM, a hierarchical multi-scale masked time series modeling with self-distillation for long-term forecasting. HiMTM integrates four key components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05012","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/2401.05012/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":"2401.05012","created_at":"2026-07-05T08:50:53.308472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05012v2","created_at":"2026-07-05T08:50:53.308472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05012","created_at":"2026-07-05T08:50:53.308472+00:00"},{"alias_kind":"pith_short_12","alias_value":"7S5HM2SACAOT","created_at":"2026-07-05T08:50:53.308472+00:00"},{"alias_kind":"pith_short_16","alias_value":"7S5HM2SACAOTPRQT","created_at":"2026-07-05T08:50:53.308472+00:00"},{"alias_kind":"pith_short_8","alias_value":"7S5HM2SA","created_at":"2026-07-05T08:50:53.308472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2407.13278","citing_title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20577","citing_title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20577","citing_title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU","json":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU.json","graph_json":"https://pith.science/api/pith-number/7S5HM2SACAOTPRQTXOYJQO2HOU/graph.json","events_json":"https://pith.science/api/pith-number/7S5HM2SACAOTPRQTXOYJQO2HOU/events.json","paper":"https://pith.science/paper/7S5HM2SA"},"agent_actions":{"view_html":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU","download_json":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU.json","view_paper":"https://pith.science/paper/7S5HM2SA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05012&json=true","fetch_graph":"https://pith.science/api/pith-number/7S5HM2SACAOTPRQTXOYJQO2HOU/graph.json","fetch_events":"https://pith.science/api/pith-number/7S5HM2SACAOTPRQTXOYJQO2HOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU/action/storage_attestation","attest_author":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU/action/author_attestation","sign_citation":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU/action/citation_signature","submit_replication":"https://pith.science/pith/7S5HM2SACAOTPRQTXOYJQO2HOU/action/replication_record"}},"created_at":"2026-07-05T08:50:53.308472+00:00","updated_at":"2026-07-05T08:50:53.308472+00:00"}