{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AA43VHFBGZHW3MJYXKXTSQ4M3C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e13b0134597902bc76b870d01fa2ae59e9b35ab3efd4a594f7381f1074e8af04","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T05:22:11Z","title_canon_sha256":"62337a0cda2e1eb436dc1a0568f767caaa300aaf712844bd0ae5e06d1cf2a2ae"},"schema_version":"1.0","source":{"id":"2505.00315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00315","created_at":"2026-07-05T10:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00315v1","created_at":"2026-07-05T10:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00315","created_at":"2026-07-05T10:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"AA43VHFBGZHW","created_at":"2026-07-05T10:57:11Z"},{"alias_kind":"pith_short_16","alias_value":"AA43VHFBGZHW3MJY","created_at":"2026-07-05T10:57:11Z"},{"alias_kind":"pith_short_8","alias_value":"AA43VHFB","created_at":"2026-07-05T10:57:11Z"}],"graph_snapshots":[{"event_id":"sha256:af1bb149fa6d47dec2f5ab66f769f36210bae6769e8e7735dbdc3039103e4105","target":"graph","created_at":"2026-07-05T10:57:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.00315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize that dynamic, learned content-based sparsity can lead to more efficient attention mechanisms. We present Mixture of Sparse Attention (MoSA), a novel approach inspired by Mixture of Experts (MoE) with expert choice routing. MoSA dynamically selects tokens for each attention head, allowing arbitrary sparse attention patterns. By selecting $k$ tokens from a se","authors_text":"J\\\"urgen Schmidhuber, Piotr Pi\\k{e}kos, R\\'obert Csord\\'as","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T05:22:11Z","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00315","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2923ff9df0d11d086f81c2b44fa950fb15d5400b599c6328c1fc560e2bb1e0f3","target":"record","created_at":"2026-07-05T10:57:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e13b0134597902bc76b870d01fa2ae59e9b35ab3efd4a594f7381f1074e8af04","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T05:22:11Z","title_canon_sha256":"62337a0cda2e1eb436dc1a0568f767caaa300aaf712844bd0ae5e06d1cf2a2ae"},"schema_version":"1.0","source":{"id":"2505.00315","kind":"arxiv","version":1}},"canonical_sha256":"0039ba9ca1364f6db138baaf39438cd8899834c4f0beac0cfc97ef3847c09ec3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0039ba9ca1364f6db138baaf39438cd8899834c4f0beac0cfc97ef3847c09ec3","first_computed_at":"2026-07-05T10:57:11.454570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:11.454570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5+QWdzU+NZqixXcSgNNggI2Duc2Bfg3SeN4T8MjLswTYlwFYsy96ooqk61kAFvxFYBsndSNYSlI4bOdXP5BoCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:11.454984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2923ff9df0d11d086f81c2b44fa950fb15d5400b599c6328c1fc560e2bb1e0f3","sha256:af1bb149fa6d47dec2f5ab66f769f36210bae6769e8e7735dbdc3039103e4105"],"state_sha256":"40cb841535f8dc3fb401625d6594157c031c8174257c78708ca0f25408f4349f"}