{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5NE2ASQFNL2GAIUYY6TPPDZZHM","short_pith_number":"pith:5NE2ASQF","schema_version":"1.0","canonical_sha256":"eb49a04a056af4602298c7a6f78f393b2eda74dc878bdb5d16fd86ee8167a972","source":{"kind":"arxiv","id":"2507.08637","version":1},"attestation_state":"computed","paper":{"title":"Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Vincenzo Dentamaro","submitted_at":"2025-07-11T14:40:40Z","abstract_excerpt":"Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time complexity that is pivotal to enable successful long-sequence processing without the performance trade-off. WERSA merges content-adaptive random spectral features together with multi-resolution Haar wavelets and learnable parameters to selectively attend to informative scales of data while preserving linear efficiency.\n  Large-scale comparisons \\textbf{on single GP"},"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":"2507.08637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T14:40:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a939d16910e6305f3a5d23f1374bbd68edc007dc10033d9b1739e1436bed1063","abstract_canon_sha256":"a56cb2b1f0dce1cc46d803ec908613e5ddc2a3fa00e7e969d47fc9a5ad484c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:43.737391Z","signature_b64":"KNIL83k58Y4YtahSwdQcwlG+Ib45Uqk0+KHJmEm0yMI+LXWMJo/5PndPf+PBFZkUkPrbjH2r4i8N9M0CJ9ffBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb49a04a056af4602298c7a6f78f393b2eda74dc878bdb5d16fd86ee8167a972","last_reissued_at":"2026-07-05T11:35:43.736796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:43.736796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Attention to Very Long Sequences in Linear Time with Wavelet-Enhanced Random Spectral Attention (WERSA)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Vincenzo Dentamaro","submitted_at":"2025-07-11T14:40:40Z","abstract_excerpt":"Transformer models are computationally costly on long sequences since regular attention has quadratic $O(n^2)$ time complexity. We introduce Wavelet-Enhanced Random Spectral Attention (WERSA), a novel mechanism of linear $O(n)$ time complexity that is pivotal to enable successful long-sequence processing without the performance trade-off. WERSA merges content-adaptive random spectral features together with multi-resolution Haar wavelets and learnable parameters to selectively attend to informative scales of data while preserving linear efficiency.\n  Large-scale comparisons \\textbf{on single GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08637","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/2507.08637/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":"2507.08637","created_at":"2026-07-05T11:35:43.736876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08637v1","created_at":"2026-07-05T11:35:43.736876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08637","created_at":"2026-07-05T11:35:43.736876+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NE2ASQFNL2G","created_at":"2026-07-05T11:35:43.736876+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NE2ASQFNL2GAIUY","created_at":"2026-07-05T11:35:43.736876+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NE2ASQF","created_at":"2026-07-05T11:35:43.736876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM","json":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM.json","graph_json":"https://pith.science/api/pith-number/5NE2ASQFNL2GAIUYY6TPPDZZHM/graph.json","events_json":"https://pith.science/api/pith-number/5NE2ASQFNL2GAIUYY6TPPDZZHM/events.json","paper":"https://pith.science/paper/5NE2ASQF"},"agent_actions":{"view_html":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM","download_json":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM.json","view_paper":"https://pith.science/paper/5NE2ASQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08637&json=true","fetch_graph":"https://pith.science/api/pith-number/5NE2ASQFNL2GAIUYY6TPPDZZHM/graph.json","fetch_events":"https://pith.science/api/pith-number/5NE2ASQFNL2GAIUYY6TPPDZZHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM/action/storage_attestation","attest_author":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM/action/author_attestation","sign_citation":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM/action/citation_signature","submit_replication":"https://pith.science/pith/5NE2ASQFNL2GAIUYY6TPPDZZHM/action/replication_record"}},"created_at":"2026-07-05T11:35:43.736876+00:00","updated_at":"2026-07-05T11:35:43.736876+00:00"}