{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EN53BOIXFTG4ISL4E7AKLS2XIY","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":"450063a6f0c136d0bd73e650e12ecd9de492cf23782c80f67409886ce4368eea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T18:06:14Z","title_canon_sha256":"7fe316b43db7f8816ae95dbd5c039ac74ea4897c2f9dabbde334ca3c40588f49"},"schema_version":"1.0","source":{"id":"1909.00015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00015","created_at":"2026-07-05T00:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00015v2","created_at":"2026-07-05T00:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00015","created_at":"2026-07-05T00:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"EN53BOIXFTG4","created_at":"2026-07-05T00:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"EN53BOIXFTG4ISL4","created_at":"2026-07-05T00:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"EN53BOIX","created_at":"2026-07-05T00:02:50Z"}],"graph_snapshots":[{"event_id":"sha256:d003c96e5e97eaad8c6c26b923b348af0310cfb178e65cd4498ccf68d16f5adc","target":"graph","created_at":"2026-07-05T00:02:50Z","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/1909.00015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are dense, assigning a non-zero weight to all context words. In this work, we introduce the adaptively sparse Transformer, wherein attention heads have flexible, context-dependent sparsity patterns. This sparsity is accomplished by replacing softmax with $\\alpha$-entmax: a differentiab","authors_text":"Andr\\'e F.T. Martins, Gon\\c{c}alo M. Correia, Vlad Niculae","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T18:06:14Z","title":"Adaptively Sparse Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00015","kind":"arxiv","version":2},"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":"sha256:42031720205bb200cf4057ec30547abe098f20316e1ee0deba6a2be004152d7d","target":"record","created_at":"2026-07-05T00:02:50Z","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":"450063a6f0c136d0bd73e650e12ecd9de492cf23782c80f67409886ce4368eea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-30T18:06:14Z","title_canon_sha256":"7fe316b43db7f8816ae95dbd5c039ac74ea4897c2f9dabbde334ca3c40588f49"},"schema_version":"1.0","source":{"id":"1909.00015","kind":"arxiv","version":2}},"canonical_sha256":"237bb0b9172ccdc4497c27c0a5cb57463f41714ebb4b26cef915c1fb9634d28e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"237bb0b9172ccdc4497c27c0a5cb57463f41714ebb4b26cef915c1fb9634d28e","first_computed_at":"2026-07-05T00:02:50.351675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:50.351675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yDaULGkAwclLnP7BX7aoH84Ar6AgI8c/Ez3lv265mTBYdk8ASGO1CCQJCmaa9cpVYRDQE2rg9bAXfVbrCaGaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:50.352089Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42031720205bb200cf4057ec30547abe098f20316e1ee0deba6a2be004152d7d","sha256:d003c96e5e97eaad8c6c26b923b348af0310cfb178e65cd4498ccf68d16f5adc"],"state_sha256":"7c09b2a6b26f895b540c68a4bf4c251dae495483507c70587362a254670f1cbb"}