{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XONKRPS75GJ4IGL5NIMSK44T5O","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":"8707f86f719bc143d56e26991bd0570616f45cb23c83b46cbbb145af248fa73b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T20:12:35Z","title_canon_sha256":"2514e35e3bb7966f77e08ea96004f50d5f3d1be666533a50d15f5026b93e955c"},"schema_version":"1.0","source":{"id":"2010.04245","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.04245","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"arxiv_version","alias_value":"2010.04245v1","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04245","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_12","alias_value":"XONKRPS75GJ4","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_16","alias_value":"XONKRPS75GJ4IGL5","created_at":"2026-07-05T01:41:34Z"},{"alias_kind":"pith_short_8","alias_value":"XONKRPS7","created_at":"2026-07-05T01:41:34Z"}],"graph_snapshots":[{"event_id":"sha256:2f1c6e92404dad2272318798c617bba1befd2cc3f0549c72245ad08a6465771d","target":"graph","created_at":"2026-07-05T01:41:34Z","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/2010.04245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-resource language translation is a challenging but socially valuable NLP task. Building on recent work adapting the Transformer's normalization to this setting, we propose QKNorm, a normalization technique that modifies the attention mechanism to make the softmax function less prone to arbitrary saturation without sacrificing expressivity. Specifically, we apply $\\ell_2$ normalization along the head dimension of each query and key matrix prior to multiplying them and then scale up by a learnable parameter instead of dividing by the square root of the embedding dimension. We show improvemen","authors_text":"Alex Henry, Prudhvi Raj Dachapally, Shubham Pawar, Yuxuan Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T20:12:35Z","title":"Query-Key Normalization for Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04245","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":"sha256:574e19c8ff4b8f8e16aa2ef1ed7c6f28cb63863408fe3cf0ab9342ae39c52f0e","target":"record","created_at":"2026-07-05T01:41:34Z","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":"8707f86f719bc143d56e26991bd0570616f45cb23c83b46cbbb145af248fa73b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-08T20:12:35Z","title_canon_sha256":"2514e35e3bb7966f77e08ea96004f50d5f3d1be666533a50d15f5026b93e955c"},"schema_version":"1.0","source":{"id":"2010.04245","kind":"arxiv","version":1}},"canonical_sha256":"bb9aa8be5fe993c4197d6a19257393ebad18c26490f198690056d3c86a6b694a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb9aa8be5fe993c4197d6a19257393ebad18c26490f198690056d3c86a6b694a","first_computed_at":"2026-07-05T01:41:34.900545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:34.900545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3GALRxkXI3pJ8lOEJUsWZQsBQMNb1HeTP1Sx/DUsSAxawReDqgTbSmymM2jrHM7DIuzJq/Mo+gQ+eUcFRfX2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:34.901029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.04245","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:574e19c8ff4b8f8e16aa2ef1ed7c6f28cb63863408fe3cf0ab9342ae39c52f0e","sha256:2f1c6e92404dad2272318798c617bba1befd2cc3f0549c72245ad08a6465771d"],"state_sha256":"f16d874e021b94b1ca58d9fb58c082d53012f1b478e37ac0c1951cdffbfcf1a2"}