{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JX4KUQE2VX7IV5BP4Y4OXK3GIW","short_pith_number":"pith:JX4KUQE2","schema_version":"1.0","canonical_sha256":"4df8aa409aadfe8af42fe638ebab6645acbea643d13217bb2dd37fa914b654eb","source":{"kind":"arxiv","id":"2310.00655","version":2},"attestation_state":"computed","paper":{"title":"PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junwei Liang, Yujin Tang, Zeying Gong","submitted_at":"2023-10-01T12:47:59Z","abstract_excerpt":"Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of temporal information. To tackle these challenges, we propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Diverging from conventional CNNs in this field, which often employ multiple scales or numerous branches, our method relies exclusively on depthwise separable convolutions. Th"},"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":"2310.00655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T12:47:59Z","cross_cats_sorted":[],"title_canon_sha256":"fd40fe8d7484e94efec2dbe8267f0517577f25088539ea4675047bd2c4e48cac","abstract_canon_sha256":"17a85a61d354bdf04ed10d518b0c564ec61cd162bc4edf58540577265aa0149a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:24.423491Z","signature_b64":"hgfDZSdtIRHsxxl906VnPQ04hFSABwyatx2cLiWBnTnyd9XgEOrIvjsRAZZAbAbJqn3Z85w7df5gZgZpMRYvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df8aa409aadfe8af42fe638ebab6645acbea643d13217bb2dd37fa914b654eb","last_reissued_at":"2026-07-05T09:19:24.423063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:24.423063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junwei Liang, Yujin Tang, Zeying Gong","submitted_at":"2023-10-01T12:47:59Z","abstract_excerpt":"Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of temporal information. To tackle these challenges, we propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Diverging from conventional CNNs in this field, which often employ multiple scales or numerous branches, our method relies exclusively on depthwise separable convolutions. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00655","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/2310.00655/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":"2310.00655","created_at":"2026-07-05T09:19:24.423118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00655v2","created_at":"2026-07-05T09:19:24.423118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00655","created_at":"2026-07-05T09:19:24.423118+00:00"},{"alias_kind":"pith_short_12","alias_value":"JX4KUQE2VX7I","created_at":"2026-07-05T09:19:24.423118+00:00"},{"alias_kind":"pith_short_16","alias_value":"JX4KUQE2VX7IV5BP","created_at":"2026-07-05T09:19:24.423118+00:00"},{"alias_kind":"pith_short_8","alias_value":"JX4KUQE2","created_at":"2026-07-05T09:19:24.423118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26549","citing_title":"PMDformer: Patch-Mean Decoupling Information Transformer for Long-term Forecasting","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24389","citing_title":"SinFormer: A Tailored Transformer for Robust Radio Frequency Fingerprint Identification","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28166","citing_title":"QuITE: Query-Based Irregular Time Series Embedding","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27981","citing_title":"ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW","json":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW.json","graph_json":"https://pith.science/api/pith-number/JX4KUQE2VX7IV5BP4Y4OXK3GIW/graph.json","events_json":"https://pith.science/api/pith-number/JX4KUQE2VX7IV5BP4Y4OXK3GIW/events.json","paper":"https://pith.science/paper/JX4KUQE2"},"agent_actions":{"view_html":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW","download_json":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW.json","view_paper":"https://pith.science/paper/JX4KUQE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00655&json=true","fetch_graph":"https://pith.science/api/pith-number/JX4KUQE2VX7IV5BP4Y4OXK3GIW/graph.json","fetch_events":"https://pith.science/api/pith-number/JX4KUQE2VX7IV5BP4Y4OXK3GIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW/action/storage_attestation","attest_author":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW/action/author_attestation","sign_citation":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW/action/citation_signature","submit_replication":"https://pith.science/pith/JX4KUQE2VX7IV5BP4Y4OXK3GIW/action/replication_record"}},"created_at":"2026-07-05T09:19:24.423118+00:00","updated_at":"2026-07-05T09:19:24.423118+00:00"}