{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:V6LRK23Y7JTIN3YYQ7FKKM47EF","short_pith_number":"pith:V6LRK23Y","schema_version":"1.0","canonical_sha256":"af97156b78fa6686ef1887caa5339f2144501abbad7820346c4dac1076b38b00","source":{"kind":"arxiv","id":"1801.10296","version":2},"attestation_state":"computed","paper":{"title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Sen Wang, Tao Shen, Tianyi Zhou","submitted_at":"2018-01-31T04:30:32Z","abstract_excerpt":"Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, \"reinforced self-attention (ReSA)\", fo"},"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":"1801.10296","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-31T04:30:32Z","cross_cats_sorted":[],"title_canon_sha256":"422af884f0cc437c4d37cbda353fac2ec4bff92696bde1f6940e18e2c056ed03","abstract_canon_sha256":"bc5da25512e650a42ec23c3f017a75e4694fa03f6df3c183260d970b505d18e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:28.083165Z","signature_b64":"CmeOQ+9KFi1O1xmF59lsqgP2Mob1vtvyz23tBCbfiwalgbdlFIlzRSDYCl7i+S76SUMl13NKphSEipH/phfkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af97156b78fa6686ef1887caa5339f2144501abbad7820346c4dac1076b38b00","last_reissued_at":"2026-05-18T00:11:28.082664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:28.082664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Sen Wang, Tao Shen, Tianyi Zhou","submitted_at":"2018-01-31T04:30:32Z","abstract_excerpt":"Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, \"reinforced self-attention (ReSA)\", fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.10296","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1801.10296","created_at":"2026-05-18T00:11:28.082740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.10296v2","created_at":"2026-05-18T00:11:28.082740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.10296","created_at":"2026-05-18T00:11:28.082740+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6LRK23Y7JTI","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6LRK23Y7JTIN3YY","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6LRK23Y","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF","json":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF.json","graph_json":"https://pith.science/api/pith-number/V6LRK23Y7JTIN3YYQ7FKKM47EF/graph.json","events_json":"https://pith.science/api/pith-number/V6LRK23Y7JTIN3YYQ7FKKM47EF/events.json","paper":"https://pith.science/paper/V6LRK23Y"},"agent_actions":{"view_html":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF","download_json":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF.json","view_paper":"https://pith.science/paper/V6LRK23Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.10296&json=true","fetch_graph":"https://pith.science/api/pith-number/V6LRK23Y7JTIN3YYQ7FKKM47EF/graph.json","fetch_events":"https://pith.science/api/pith-number/V6LRK23Y7JTIN3YYQ7FKKM47EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF/action/storage_attestation","attest_author":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF/action/author_attestation","sign_citation":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF/action/citation_signature","submit_replication":"https://pith.science/pith/V6LRK23Y7JTIN3YYQ7FKKM47EF/action/replication_record"}},"created_at":"2026-05-18T00:11:28.082740+00:00","updated_at":"2026-05-18T00:11:28.082740+00:00"}