{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4IQK5BT3QPKXTSDOQ4LHCBKMFP","short_pith_number":"pith:4IQK5BT3","schema_version":"1.0","canonical_sha256":"e220ae867b83d579c86e871671054c2bd01f464f7b6c114276fce47f0f50e1dd","source":{"kind":"arxiv","id":"1709.04696","version":3},"attestation_state":"computed","paper":{"title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Shirui Pan, Tao Shen, Tianyi Zhou","submitted_at":"2017-09-14T10:42:44Z","abstract_excerpt":"Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, \"Directional Self-Attention Network (DiSAN)\", is then proposed to lea"},"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":"1709.04696","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-14T10:42:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4cba82ab7bd848af31aafbebf86c25328edeada52b1ccb947267a3db4890f5f","abstract_canon_sha256":"53886baea3998f3e6143bd7bc8b47de89d80676a36e8b36d518daf6d6109483c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:00.079841Z","signature_b64":"BgDW1ovThgtURjghS4AXu7g6bCP4x72Ib3aZp27rbvUL1ZbNr3uNXuKptQMzJGSHyWkz8OP57jYWqMbhsOYqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e220ae867b83d579c86e871671054c2bd01f464f7b6c114276fce47f0f50e1dd","last_reissued_at":"2026-05-18T00:30:00.079085Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:00.079085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhang, Guodong Long, Jing Jiang, Shirui Pan, Tao Shen, Tianyi Zhou","submitted_at":"2017-09-14T10:42:44Z","abstract_excerpt":"Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively. Attention mechanisms have recently attracted enormous interest due to their highly parallelizable computation, significantly less training time, and flexibility in modeling dependencies. We propose a novel attention mechanism in which the attention between elements from input sequence(s) is directional and multi-dimensional (i.e., feature-wise). A light-weight neural net, \"Directional Self-Attention Network (DiSAN)\", is then proposed to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04696","kind":"arxiv","version":3},"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":"1709.04696","created_at":"2026-05-18T00:30:00.079178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04696v3","created_at":"2026-05-18T00:30:00.079178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04696","created_at":"2026-05-18T00:30:00.079178+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IQK5BT3QPKX","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IQK5BT3QPKXTSDO","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IQK5BT3","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1804.03999","citing_title":"Attention U-Net: Learning Where to Look for the Pancreas","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP","json":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP.json","graph_json":"https://pith.science/api/pith-number/4IQK5BT3QPKXTSDOQ4LHCBKMFP/graph.json","events_json":"https://pith.science/api/pith-number/4IQK5BT3QPKXTSDOQ4LHCBKMFP/events.json","paper":"https://pith.science/paper/4IQK5BT3"},"agent_actions":{"view_html":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP","download_json":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP.json","view_paper":"https://pith.science/paper/4IQK5BT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04696&json=true","fetch_graph":"https://pith.science/api/pith-number/4IQK5BT3QPKXTSDOQ4LHCBKMFP/graph.json","fetch_events":"https://pith.science/api/pith-number/4IQK5BT3QPKXTSDOQ4LHCBKMFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP/action/storage_attestation","attest_author":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP/action/author_attestation","sign_citation":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP/action/citation_signature","submit_replication":"https://pith.science/pith/4IQK5BT3QPKXTSDOQ4LHCBKMFP/action/replication_record"}},"created_at":"2026-05-18T00:30:00.079178+00:00","updated_at":"2026-05-18T00:30:00.079178+00:00"}