{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VGMTAEGCOUF6UFEG26CDXOYQKZ","short_pith_number":"pith:VGMTAEGC","schema_version":"1.0","canonical_sha256":"a9993010c2750bea1486d7843bbb105650a9bbba96a5654d4286ba222aaca01a","source":{"kind":"arxiv","id":"2202.06258","version":2},"attestation_state":"computed","paper":{"title":"Flowformer: Linearizing Transformers with Conservation Flows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haixu Wu, Jialong Wu, Jianmin Wang, Jiehui Xu, Mingsheng Long","submitted_at":"2022-02-13T08:44:10Z","abstract_excerpt":"Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling up to bigger models. Previous methods mainly utilize the similarity decomposition and the associativity of matrix multiplication to devise linear-time attention mechanisms. They avoid degeneration of attention to a trivial distribution by reintroducing inductive biases such as the locality, thereby at the expense of model generality and expressiveness. In 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":"2202.06258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T08:44:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"388ba1d7e830da7bf4effbfeb83080d80817f228b5a79f432450d437ddb22f2f","abstract_canon_sha256":"064bc975c614e4614147d3d129cd16799e8a865daedc627315c41c80070dff2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:14.611010Z","signature_b64":"GlqwQnk6LMCrk8PbUF2oIE1jDBzfi0b7kSKktA/4m9ekwFfw1CAHsLx2Nz1m0ONf381v14M1wGp0DbQU+YzCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9993010c2750bea1486d7843bbb105650a9bbba96a5654d4286ba222aaca01a","last_reissued_at":"2026-07-05T04:32:14.610398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:14.610398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flowformer: Linearizing Transformers with Conservation Flows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haixu Wu, Jialong Wu, Jianmin Wang, Jiehui Xu, Mingsheng Long","submitted_at":"2022-02-13T08:44:10Z","abstract_excerpt":"Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling up to bigger models. Previous methods mainly utilize the similarity decomposition and the associativity of matrix multiplication to devise linear-time attention mechanisms. They avoid degeneration of attention to a trivial distribution by reintroducing inductive biases such as the locality, thereby at the expense of model generality and expressiveness. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06258","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/2202.06258/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":"2202.06258","created_at":"2026-07-05T04:32:14.610484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06258v2","created_at":"2026-07-05T04:32:14.610484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06258","created_at":"2026-07-05T04:32:14.610484+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGMTAEGCOUF6","created_at":"2026-07-05T04:32:14.610484+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGMTAEGCOUF6UFEG","created_at":"2026-07-05T04:32:14.610484+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGMTAEGC","created_at":"2026-07-05T04:32:14.610484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00169","citing_title":"ChurnNet: A Optimized Modern AI for Churn Prediction","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00062","citing_title":"RETO: A Rotary-Enhanced Transformer Operator for High-Fidelity Prediction of Automotive Aerodynamics","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ","json":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ.json","graph_json":"https://pith.science/api/pith-number/VGMTAEGCOUF6UFEG26CDXOYQKZ/graph.json","events_json":"https://pith.science/api/pith-number/VGMTAEGCOUF6UFEG26CDXOYQKZ/events.json","paper":"https://pith.science/paper/VGMTAEGC"},"agent_actions":{"view_html":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ","download_json":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ.json","view_paper":"https://pith.science/paper/VGMTAEGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06258&json=true","fetch_graph":"https://pith.science/api/pith-number/VGMTAEGCOUF6UFEG26CDXOYQKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VGMTAEGCOUF6UFEG26CDXOYQKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ/action/storage_attestation","attest_author":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ/action/author_attestation","sign_citation":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ/action/citation_signature","submit_replication":"https://pith.science/pith/VGMTAEGCOUF6UFEG26CDXOYQKZ/action/replication_record"}},"created_at":"2026-07-05T04:32:14.610484+00:00","updated_at":"2026-07-05T04:32:14.610484+00:00"}