{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GVLUD46V43Q3DOY3FRI32BOOXM","short_pith_number":"pith:GVLUD46V","schema_version":"1.0","canonical_sha256":"355741f3d5e6e1b1bb1b2c51bd05cebb174e5509b6568de1b18bbc2a94eaf268","source":{"kind":"arxiv","id":"2101.09645","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Time Series Forecasting With Shared Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Sheng, Jiaze E, Xiao Zhang, Xiuzheng Cheng, Zekai Chen","submitted_at":"2021-01-24T04:25:08Z","abstract_excerpt":"Time series forecasting is a key component in many industrial and business decision processes and recurrent neural network (RNN) based models have achieved impressive progress on various time series forecasting tasks. However, most of the existing methods focus on single-task forecasting problems by learning separately based on limited supervised objectives, which often suffer from insufficient training instances. As the Transformer architecture and other attention-based models have demonstrated its great capability of capturing long term dependency, we propose two self-attention based sharing"},"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":"2101.09645","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-24T04:25:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a64666fffc746c270871b0affe5e548dfc973ece48d19ec1795a025f623dc023","abstract_canon_sha256":"0b3163896e264ecf5cd0c68c74d4357680f11474e6eecd23ce5656d3da2a84d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:09:21.307170Z","signature_b64":"lizjYkTuesmC5SVld87F8HKSxiFyT4I63kO6vVFx7zAQ7Gbn5N0Pp2zBnTTO0//xj7hil1yO4Cppfrc7uZR1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355741f3d5e6e1b1bb1b2c51bd05cebb174e5509b6568de1b18bbc2a94eaf268","last_reissued_at":"2026-07-05T02:09:21.306655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:09:21.306655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Time Series Forecasting With Shared Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Sheng, Jiaze E, Xiao Zhang, Xiuzheng Cheng, Zekai Chen","submitted_at":"2021-01-24T04:25:08Z","abstract_excerpt":"Time series forecasting is a key component in many industrial and business decision processes and recurrent neural network (RNN) based models have achieved impressive progress on various time series forecasting tasks. However, most of the existing methods focus on single-task forecasting problems by learning separately based on limited supervised objectives, which often suffer from insufficient training instances. As the Transformer architecture and other attention-based models have demonstrated its great capability of capturing long term dependency, we propose two self-attention based sharing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09645","kind":"arxiv","version":1},"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/2101.09645/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":"2101.09645","created_at":"2026-07-05T02:09:21.306727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.09645v1","created_at":"2026-07-05T02:09:21.306727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09645","created_at":"2026-07-05T02:09:21.306727+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVLUD46V43Q3","created_at":"2026-07-05T02:09:21.306727+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVLUD46V43Q3DOY3","created_at":"2026-07-05T02:09:21.306727+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVLUD46V","created_at":"2026-07-05T02:09:21.306727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07858","citing_title":"Mamba Adaptive Anomaly Transformer with association discrepancy for time series","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM","json":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM.json","graph_json":"https://pith.science/api/pith-number/GVLUD46V43Q3DOY3FRI32BOOXM/graph.json","events_json":"https://pith.science/api/pith-number/GVLUD46V43Q3DOY3FRI32BOOXM/events.json","paper":"https://pith.science/paper/GVLUD46V"},"agent_actions":{"view_html":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM","download_json":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM.json","view_paper":"https://pith.science/paper/GVLUD46V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/GVLUD46V43Q3DOY3FRI32BOOXM/graph.json","fetch_events":"https://pith.science/api/pith-number/GVLUD46V43Q3DOY3FRI32BOOXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM/action/storage_attestation","attest_author":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM/action/author_attestation","sign_citation":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM/action/citation_signature","submit_replication":"https://pith.science/pith/GVLUD46V43Q3DOY3FRI32BOOXM/action/replication_record"}},"created_at":"2026-07-05T02:09:21.306727+00:00","updated_at":"2026-07-05T02:09:21.306727+00:00"}