{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C27DAN36HTP5TMOUGEZTNZDIYW","short_pith_number":"pith:C27DAN36","schema_version":"1.0","canonical_sha256":"16be30377e3cdfd9b1d4313336e468c587d91ab0fd32bd48e11a5470aed34d7f","source":{"kind":"arxiv","id":"1912.11637","version":1},"attestation_state":"computed","paper":{"title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guangxiang Zhao, Junyang Lin, Qi Su, Xuancheng Ren, Xu Sun, Zhiyuan Zhang","submitted_at":"2019-12-25T10:59:31Z","abstract_excerpt":"Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of irrelevant information in the context. To tackle the problem, we propose a novel model called \\textbf{Explicit Sparse Transformer}. Explicit Sparse Transformer is able to improve the concentration of attention on the global context through an explicit selection of the most relevant segments. Extensive experimental results on a series of natural language processing an"},"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":"1912.11637","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-25T10:59:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc555b77501d4626a6eb1a633b922d8bca79dbacb0e5cf0466c06574eee79ddf","abstract_canon_sha256":"bd694b8436dbac10ac73a65e8913c9d14014ce8d4cea3db9f869ac3ecf2daa41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:28.129541Z","signature_b64":"FWIQwk9P5Bj9aVwToBATQtM1ioxC4V3MyNthWeean5t3n50vdDCyQRDsBVkQY6JUk8DRk0sT6U7aO62X4bSxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16be30377e3cdfd9b1d4313336e468c587d91ab0fd32bd48e11a5470aed34d7f","last_reissued_at":"2026-07-05T00:28:28.129119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:28.129119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explicit Sparse Transformer: Concentrated Attention Through Explicit Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guangxiang Zhao, Junyang Lin, Qi Su, Xuancheng Ren, Xu Sun, Zhiyuan Zhang","submitted_at":"2019-12-25T10:59:31Z","abstract_excerpt":"Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of irrelevant information in the context. To tackle the problem, we propose a novel model called \\textbf{Explicit Sparse Transformer}. Explicit Sparse Transformer is able to improve the concentration of attention on the global context through an explicit selection of the most relevant segments. Extensive experimental results on a series of natural language processing an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11637","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/1912.11637/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":"1912.11637","created_at":"2026-07-05T00:28:28.129176+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11637v1","created_at":"2026-07-05T00:28:28.129176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11637","created_at":"2026-07-05T00:28:28.129176+00:00"},{"alias_kind":"pith_short_12","alias_value":"C27DAN36HTP5","created_at":"2026-07-05T00:28:28.129176+00:00"},{"alias_kind":"pith_short_16","alias_value":"C27DAN36HTP5TMOU","created_at":"2026-07-05T00:28:28.129176+00:00"},{"alias_kind":"pith_short_8","alias_value":"C27DAN36","created_at":"2026-07-05T00:28:28.129176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17952","citing_title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03928","citing_title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18109","citing_title":"TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02259","citing_title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24820","citing_title":"Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04421","citing_title":"FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08073","citing_title":"EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW","json":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW.json","graph_json":"https://pith.science/api/pith-number/C27DAN36HTP5TMOUGEZTNZDIYW/graph.json","events_json":"https://pith.science/api/pith-number/C27DAN36HTP5TMOUGEZTNZDIYW/events.json","paper":"https://pith.science/paper/C27DAN36"},"agent_actions":{"view_html":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW","download_json":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW.json","view_paper":"https://pith.science/paper/C27DAN36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11637&json=true","fetch_graph":"https://pith.science/api/pith-number/C27DAN36HTP5TMOUGEZTNZDIYW/graph.json","fetch_events":"https://pith.science/api/pith-number/C27DAN36HTP5TMOUGEZTNZDIYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW/action/storage_attestation","attest_author":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW/action/author_attestation","sign_citation":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW/action/citation_signature","submit_replication":"https://pith.science/pith/C27DAN36HTP5TMOUGEZTNZDIYW/action/replication_record"}},"created_at":"2026-07-05T00:28:28.129176+00:00","updated_at":"2026-07-05T00:28:28.129176+00:00"}