{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJSSTKQE3WU4E2A7NI7WIRCXPM","short_pith_number":"pith:HJSSTKQE","schema_version":"1.0","canonical_sha256":"3a6529aa04dda9c2681f6a3f6444577b3f22f4e535f03f3bb51a9ad9a8b26c71","source":{"kind":"arxiv","id":"2606.09862","version":1},"attestation_state":"computed","paper":{"title":"Blurry Window Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Axel Laborieux, Christos Sourmpis, Juan Gabriel Kostelec, Qinghai Guo","submitted_at":"2026-05-31T17:43:06Z","abstract_excerpt":"The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios. To overcome this limitation, alternative architectures with linear complexity and finite state size have been introduced, such as State-Space Models (SSMs), Linear Attention (LA), and Attention with Bounded-memory Control (ABC). Though linear models achieve similar language perplexity as Transformers, they are still behind in tasks which require retrieval or recall of specific inf"},"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":"2606.09862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T17:43:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29ecdfe917841e9e16a34c436f999d98ad38e5f590336e116e7619dd311601e7","abstract_canon_sha256":"7a9e51a3fb5059bd5eea056508598f05b1bfc9b7b0fae25c596f179efc89b99f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:30.101009Z","signature_b64":"AGEd4CsXh6lzyGsh+3i0QkUPpxDIu2yJB4HRZs9o5XEjALvqBluPoeeAs0AuW+C6h0fuhrtCfstJHIb4l8PTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6529aa04dda9c2681f6a3f6444577b3f22f4e535f03f3bb51a9ad9a8b26c71","last_reissued_at":"2026-06-10T00:08:30.100121Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:30.100121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blurry Window Attention","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Axel Laborieux, Christos Sourmpis, Juan Gabriel Kostelec, Qinghai Guo","submitted_at":"2026-05-31T17:43:06Z","abstract_excerpt":"The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios. To overcome this limitation, alternative architectures with linear complexity and finite state size have been introduced, such as State-Space Models (SSMs), Linear Attention (LA), and Attention with Bounded-memory Control (ABC). Though linear models achieve similar language perplexity as Transformers, they are still behind in tasks which require retrieval or recall of specific inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09862","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/2606.09862/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":"2606.09862","created_at":"2026-06-10T00:08:30.100271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09862v1","created_at":"2026-06-10T00:08:30.100271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09862","created_at":"2026-06-10T00:08:30.100271+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJSSTKQE3WU4","created_at":"2026-06-10T00:08:30.100271+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJSSTKQE3WU4E2A7","created_at":"2026-06-10T00:08:30.100271+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJSSTKQE","created_at":"2026-06-10T00:08:30.100271+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/HJSSTKQE3WU4E2A7NI7WIRCXPM","json":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM.json","graph_json":"https://pith.science/api/pith-number/HJSSTKQE3WU4E2A7NI7WIRCXPM/graph.json","events_json":"https://pith.science/api/pith-number/HJSSTKQE3WU4E2A7NI7WIRCXPM/events.json","paper":"https://pith.science/paper/HJSSTKQE"},"agent_actions":{"view_html":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM","download_json":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM.json","view_paper":"https://pith.science/paper/HJSSTKQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09862&json=true","fetch_graph":"https://pith.science/api/pith-number/HJSSTKQE3WU4E2A7NI7WIRCXPM/graph.json","fetch_events":"https://pith.science/api/pith-number/HJSSTKQE3WU4E2A7NI7WIRCXPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM/action/storage_attestation","attest_author":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM/action/author_attestation","sign_citation":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM/action/citation_signature","submit_replication":"https://pith.science/pith/HJSSTKQE3WU4E2A7NI7WIRCXPM/action/replication_record"}},"created_at":"2026-06-10T00:08:30.100271+00:00","updated_at":"2026-06-10T00:08:30.100271+00:00"}