{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZUMZPCVGS7JWTYE6OKMP46CGF7","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":"fb5cc12a6d6ba534d84e7cff5c6957b0b9482f6046f8cadd7e979e8bf52f816f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T22:17:18Z","title_canon_sha256":"387ce805b6757f181828abc2fadc880d739a8911ef3604ddd4f97d5031c13ebb"},"schema_version":"1.0","source":{"id":"2411.12892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12892","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12892v1","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12892","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZUMZPCVGS7JW","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZUMZPCVGS7JWTYE6","created_at":"2026-07-05T09:38:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZUMZPCVG","created_at":"2026-07-05T09:38:01Z"}],"graph_snapshots":[{"event_id":"sha256:52ee3e7c93295a333f950680f470ace59cb1cf29108a1a2219d04ac024223645","target":"graph","created_at":"2026-07-05T09:38:01Z","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/2411.12892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same way by applying the mapping $V^\\top\\text{softmax}(Kq)$, where $V,K$ are the value and key embeddings respectively. In this work, we argue that this uniform treatment hinders the ability to control contextual sparsity and relevance. As a solution, we introduce the $\\textit{Selective Self-Attention}$ (SSA) layer that augments the softmax nonlinearity with a pri","authors_text":"Amit Roy-Chowdhury, Jiasi Chen, Mingchen Li, Samet Oymak, Xiangyu Chang, Xuechen Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T22:17:18Z","title":"Selective Attention: Enhancing Transformer through Principled Context Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12892","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":"sha256:53cc9881efc4977789bc2fb09fe1ff3f8fb5b541d5b3b05c5bde2332d4d2fbbd","target":"record","created_at":"2026-07-05T09:38:01Z","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":"fb5cc12a6d6ba534d84e7cff5c6957b0b9482f6046f8cadd7e979e8bf52f816f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-19T22:17:18Z","title_canon_sha256":"387ce805b6757f181828abc2fadc880d739a8911ef3604ddd4f97d5031c13ebb"},"schema_version":"1.0","source":{"id":"2411.12892","kind":"arxiv","version":1}},"canonical_sha256":"cd19978aa697d369e09e7298fe78462ff2b669a00d80e87e652aab4557b20801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd19978aa697d369e09e7298fe78462ff2b669a00d80e87e652aab4557b20801","first_computed_at":"2026-07-05T09:38:01.905138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:01.905138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T6emfMvhq9Y+PuOGkbERvpt282HvpK4ol+ZZhayrL/pkjTpxDfhvlD+fJLl8bcO/09Z5UCSkijqlXuaBKfbsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:01.905627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53cc9881efc4977789bc2fb09fe1ff3f8fb5b541d5b3b05c5bde2332d4d2fbbd","sha256:52ee3e7c93295a333f950680f470ace59cb1cf29108a1a2219d04ac024223645"],"state_sha256":"cfb8408c73b2864f0f5c06a9ce1e08a85e0062b07a8ba90ed3a39c2ef6216862"}