{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MXWGWCFQFFUEMMRASYM5ZATBOU","short_pith_number":"pith:MXWGWCFQ","schema_version":"1.0","canonical_sha256":"65ec6b08b029684632209619dc8261750b8e39c0011039ff5c0d2862693ef7a1","source":{"kind":"arxiv","id":"2301.01772","version":1},"attestation_state":"computed","paper":{"title":"Infomaxformer: Maximum Entropy Transformer for Long Time-Series Forecasting Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peiwang Tang, Xianchao Zhang","submitted_at":"2023-01-04T14:08:21Z","abstract_excerpt":"The Transformer architecture yields state-of-the-art results in many tasks such as natural language processing (NLP) and computer vision (CV), since the ability to efficiently capture the precise long-range dependency coupling between input sequences. With this advanced capability, however, the quadratic time complexity and high memory usage prevents the Transformer from dealing with long time-series forecasting problem (LTFP). To address these difficulties: (i) we revisit the learned attention patterns of the vanilla self-attention, redesigned the calculation method of self-attention based 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":"2301.01772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-04T14:08:21Z","cross_cats_sorted":[],"title_canon_sha256":"650ff976de1fff79d3d7ef6a5f074f190ef2094d243d7918c06b4722a3465e35","abstract_canon_sha256":"beae3b110a0648be40ed84de64c35e41d27923922271899b380d4ba00e22badd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:45.687257Z","signature_b64":"hWFqKzgS9IL8CG3+nogg6jownbQBjxPu/qXKVrqEnVj75EaYjIlhosPf8DZtRVqnUo+ITwOAzRmO+6UVcuisCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ec6b08b029684632209619dc8261750b8e39c0011039ff5c0d2862693ef7a1","last_reissued_at":"2026-07-05T05:30:45.686771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:45.686771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infomaxformer: Maximum Entropy Transformer for Long Time-Series Forecasting Problem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peiwang Tang, Xianchao Zhang","submitted_at":"2023-01-04T14:08:21Z","abstract_excerpt":"The Transformer architecture yields state-of-the-art results in many tasks such as natural language processing (NLP) and computer vision (CV), since the ability to efficiently capture the precise long-range dependency coupling between input sequences. With this advanced capability, however, the quadratic time complexity and high memory usage prevents the Transformer from dealing with long time-series forecasting problem (LTFP). To address these difficulties: (i) we revisit the learned attention patterns of the vanilla self-attention, redesigned the calculation method of self-attention based th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01772","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/2301.01772/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":"2301.01772","created_at":"2026-07-05T05:30:45.686831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01772v1","created_at":"2026-07-05T05:30:45.686831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01772","created_at":"2026-07-05T05:30:45.686831+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXWGWCFQFFUE","created_at":"2026-07-05T05:30:45.686831+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXWGWCFQFFUEMMRA","created_at":"2026-07-05T05:30:45.686831+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXWGWCFQ","created_at":"2026-07-05T05:30:45.686831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10592","citing_title":"Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU","json":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU.json","graph_json":"https://pith.science/api/pith-number/MXWGWCFQFFUEMMRASYM5ZATBOU/graph.json","events_json":"https://pith.science/api/pith-number/MXWGWCFQFFUEMMRASYM5ZATBOU/events.json","paper":"https://pith.science/paper/MXWGWCFQ"},"agent_actions":{"view_html":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU","download_json":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU.json","view_paper":"https://pith.science/paper/MXWGWCFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01772&json=true","fetch_graph":"https://pith.science/api/pith-number/MXWGWCFQFFUEMMRASYM5ZATBOU/graph.json","fetch_events":"https://pith.science/api/pith-number/MXWGWCFQFFUEMMRASYM5ZATBOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU/action/storage_attestation","attest_author":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU/action/author_attestation","sign_citation":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU/action/citation_signature","submit_replication":"https://pith.science/pith/MXWGWCFQFFUEMMRASYM5ZATBOU/action/replication_record"}},"created_at":"2026-07-05T05:30:45.686831+00:00","updated_at":"2026-07-05T05:30:45.686831+00:00"}