{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SHPXYD5AN2FHGFE6PJFIBAJT7O","short_pith_number":"pith:SHPXYD5A","schema_version":"1.0","canonical_sha256":"91df7c0fa06e8a73149e7a4a808133fba3a71feb915efa445976d5b7c0fb0913","source":{"kind":"arxiv","id":"2606.18283","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hassan Raza, Yongchao Huang","submitted_at":"2026-06-09T23:35:17Z","abstract_excerpt":"The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \\textbf{Gaussian Mixture Attention (GMA)}, a probabilistic attention-style sequence mixer that replaces explicit pairwise query--key comparison with routing through $K$ learned Gaussian mixture components. Queries and keys are mapped to posterior \\textit{responsibility} vectors over a shared latent routing space; their overlap defines an implicit responsibility-space affinity, while values are written into and read from "},"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":"2606.18283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T23:35:17Z","cross_cats_sorted":[],"title_canon_sha256":"bb05b00a25af4c96f6050645ca0b6f8b81c3411cec81764e2a57cb619b17687c","abstract_canon_sha256":"2441e86aa011b2acad5dc3ed1352b8053ef92aed834131ec4c5fc57e6903e6a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:56.877641Z","signature_b64":"LHGpd6EFrj6RrY37u8QgvMSWG61xj5vVe1hQUuBGfl7/6jVAP5agK/PeDE0Pd2HaOYnDDfS68lN8iqTWSJM6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91df7c0fa06e8a73149e7a4a808133fba3a71feb915efa445976d5b7c0fb0913","last_reissued_at":"2026-06-19T16:10:56.877255Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:56.877255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hassan Raza, Yongchao Huang","submitted_at":"2026-06-09T23:35:17Z","abstract_excerpt":"The dense token-to-token interaction pattern of standard dot-product attention remains a central bottleneck in scaling Transformer architectures to long contexts. We introduce \\textbf{Gaussian Mixture Attention (GMA)}, a probabilistic attention-style sequence mixer that replaces explicit pairwise query--key comparison with routing through $K$ learned Gaussian mixture components. Queries and keys are mapped to posterior \\textit{responsibility} vectors over a shared latent routing space; their overlap defines an implicit responsibility-space affinity, while values are written into and read from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18283","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/2606.18283/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":"2606.18283","created_at":"2026-06-19T16:10:56.877322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18283v1","created_at":"2026-06-19T16:10:56.877322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18283","created_at":"2026-06-19T16:10:56.877322+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHPXYD5AN2FH","created_at":"2026-06-19T16:10:56.877322+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHPXYD5AN2FHGFE6","created_at":"2026-06-19T16:10:56.877322+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHPXYD5A","created_at":"2026-06-19T16:10:56.877322+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/SHPXYD5AN2FHGFE6PJFIBAJT7O","json":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O.json","graph_json":"https://pith.science/api/pith-number/SHPXYD5AN2FHGFE6PJFIBAJT7O/graph.json","events_json":"https://pith.science/api/pith-number/SHPXYD5AN2FHGFE6PJFIBAJT7O/events.json","paper":"https://pith.science/paper/SHPXYD5A"},"agent_actions":{"view_html":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O","download_json":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O.json","view_paper":"https://pith.science/paper/SHPXYD5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18283&json=true","fetch_graph":"https://pith.science/api/pith-number/SHPXYD5AN2FHGFE6PJFIBAJT7O/graph.json","fetch_events":"https://pith.science/api/pith-number/SHPXYD5AN2FHGFE6PJFIBAJT7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O/action/storage_attestation","attest_author":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O/action/author_attestation","sign_citation":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O/action/citation_signature","submit_replication":"https://pith.science/pith/SHPXYD5AN2FHGFE6PJFIBAJT7O/action/replication_record"}},"created_at":"2026-06-19T16:10:56.877322+00:00","updated_at":"2026-06-19T16:10:56.877322+00:00"}