{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KKKHDYCKLFH4SHQI2CJARKJOTH","short_pith_number":"pith:KKKHDYCK","schema_version":"1.0","canonical_sha256":"529471e04a594fc91e08d09208a92e99d1d54a96fcd5208cb660b1d6eaf66592","source":{"kind":"arxiv","id":"2205.13504","version":3},"attestation_state":"computed","paper":{"title":"Are Transformers Effective for Time Series Forecasting?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ailing Zeng, Lei Zhang, Muxi Chen, Qiang Xu","submitted_at":"2022-05-26T17:17:08Z","abstract_excerpt":"Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task. Despite the growing performance over the past few years, we question the validity of this line of research in this work. Specifically, Transformers is arguably the most successful solution to extract the semantic correlations among the elements in a long sequence. However, in time series modeling, we are to extract the temporal relations in an ordered set of continuous points. While employing positional encoding and using tokens to embed sub-series in Transformers facilitate p"},"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":"2205.13504","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-05-26T17:17:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d1e91df11fe753faec6f172507abc922033732ef882ab823eae4cdec0238ff8b","abstract_canon_sha256":"596b3bd099f147e8cfe5528d4c9437f1dc6b70a7c249cea892a77d4a163c8203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:23.126183Z","signature_b64":"xor4Jq7ahn+iM9CO4eF7pC8WLgTLdZZ5KPBXm9Ie/bU/pIfAnitZb8XIhwl/RjzPaUr03D28oqZGZUUswV8FAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"529471e04a594fc91e08d09208a92e99d1d54a96fcd5208cb660b1d6eaf66592","last_reissued_at":"2026-07-05T04:49:23.125629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:23.125629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Transformers Effective for Time Series Forecasting?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ailing Zeng, Lei Zhang, Muxi Chen, Qiang Xu","submitted_at":"2022-05-26T17:17:08Z","abstract_excerpt":"Recently, there has been a surge of Transformer-based solutions for the long-term time series forecasting (LTSF) task. Despite the growing performance over the past few years, we question the validity of this line of research in this work. Specifically, Transformers is arguably the most successful solution to extract the semantic correlations among the elements in a long sequence. However, in time series modeling, we are to extract the temporal relations in an ordered set of continuous points. While employing positional encoding and using tokens to embed sub-series in Transformers facilitate p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13504","kind":"arxiv","version":3},"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/2205.13504/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":"2205.13504","created_at":"2026-07-05T04:49:23.125701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13504v3","created_at":"2026-07-05T04:49:23.125701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13504","created_at":"2026-07-05T04:49:23.125701+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKKHDYCKLFH4","created_at":"2026-07-05T04:49:23.125701+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKKHDYCKLFH4SHQI","created_at":"2026-07-05T04:49:23.125701+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKKHDYCK","created_at":"2026-07-05T04:49:23.125701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08234","citing_title":"RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07250","citing_title":"Flow-PIN: A Two-Stage Power-Flow-Guided Method for System-Wide Multivariate Profile Inpainting in Distribution Networks","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18049","citing_title":"ConTex: Reformulating Counterfactual Generation For Time Series Forecasting","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13513","citing_title":"CloudCons: A Comprehensive End-to-End Benchmark for Cloud Resource Consolidation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05332","citing_title":"GITCO: Gated Inference-Time Context Optimization in TSFMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11287","citing_title":"Beyond Similarity: Temporal Operator Attention for Time Series Analysis","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28866","citing_title":"Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10721","citing_title":"Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20577","citing_title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15774","citing_title":"Time Series Forecasting Through the Lens of Dynamics","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25826","citing_title":"Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20577","citing_title":"MSTN: A Lightweight and Fast Model for General TimeSeries Analysis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12116","citing_title":"Neural CDEs as Correctors for Learned Time Series Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2211.14730","citing_title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11287","citing_title":"Beyond Similarity: Temporal Operator Attention for Time Series Analysis","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09067","citing_title":"Temporal Patch Shuffle (TPS): Leveraging Patch-Level Shuffling to Boost Generalization and Robustness in Time Series Forecasting","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH","json":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH.json","graph_json":"https://pith.science/api/pith-number/KKKHDYCKLFH4SHQI2CJARKJOTH/graph.json","events_json":"https://pith.science/api/pith-number/KKKHDYCKLFH4SHQI2CJARKJOTH/events.json","paper":"https://pith.science/paper/KKKHDYCK"},"agent_actions":{"view_html":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH","download_json":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH.json","view_paper":"https://pith.science/paper/KKKHDYCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13504&json=true","fetch_graph":"https://pith.science/api/pith-number/KKKHDYCKLFH4SHQI2CJARKJOTH/graph.json","fetch_events":"https://pith.science/api/pith-number/KKKHDYCKLFH4SHQI2CJARKJOTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH/action/storage_attestation","attest_author":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH/action/author_attestation","sign_citation":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH/action/citation_signature","submit_replication":"https://pith.science/pith/KKKHDYCKLFH4SHQI2CJARKJOTH/action/replication_record"}},"created_at":"2026-07-05T04:49:23.125701+00:00","updated_at":"2026-07-05T04:49:23.125701+00:00"}