{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I6L4WIV6UUFTPG74G23RWIV6BK","short_pith_number":"pith:I6L4WIV6","schema_version":"1.0","canonical_sha256":"4797cb22bea50b379bfc36b71b22be0a9acaafb69b5a4ff1f515e8a4af3a619c","source":{"kind":"arxiv","id":"1909.00188","version":1},"attestation_state":"computed","paper":{"title":"Improving Multi-Head Attention with Capsule Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuhao Gu, Yang Feng","submitted_at":"2019-08-31T10:43:06Z","abstract_excerpt":"Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering "},"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":"1909.00188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T10:43:06Z","cross_cats_sorted":[],"title_canon_sha256":"f0190e54cdb88de555887e8baeb3ad95e7a69f9b7a5700488b1e8c3404cf48dc","abstract_canon_sha256":"4deb1b6615bc31a32a20c03d4a19b6bc52dd95aac69af0e9ad0e060e9d5ee9fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:06.589287Z","signature_b64":"42XDIGh/fe0jcqybkrj+HP1GTov0yDc1FsmVUCVmpGmVyNYSM/Rp0vVT7hJ6Q6RFozRdTAVAFKJtOUDFg2w6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4797cb22bea50b379bfc36b71b22be0a9acaafb69b5a4ff1f515e8a4af3a619c","last_reissued_at":"2026-07-05T00:01:06.588885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:06.588885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multi-Head Attention with Capsule Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shuhao Gu, Yang Feng","submitted_at":"2019-08-31T10:43:06Z","abstract_excerpt":"Multi-head attention advances neural machine translation by working out multiple versions of attention in different subspaces, but the neglect of semantic overlapping between subspaces increases the difficulty of translation and consequently hinders the further improvement of translation performance. In this paper, we employ capsule networks to comb the information from the multiple heads of the attention so that similar information can be clustered and unique information can be reserved. To this end, we adopt two routing mechanisms of Dynamic Routing and EM Routing, to fulfill the clustering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00188","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/1909.00188/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":"1909.00188","created_at":"2026-07-05T00:01:06.588954+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00188v1","created_at":"2026-07-05T00:01:06.588954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00188","created_at":"2026-07-05T00:01:06.588954+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6L4WIV6UUFT","created_at":"2026-07-05T00:01:06.588954+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6L4WIV6UUFTPG74","created_at":"2026-07-05T00:01:06.588954+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6L4WIV6","created_at":"2026-07-05T00:01:06.588954+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/I6L4WIV6UUFTPG74G23RWIV6BK","json":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK.json","graph_json":"https://pith.science/api/pith-number/I6L4WIV6UUFTPG74G23RWIV6BK/graph.json","events_json":"https://pith.science/api/pith-number/I6L4WIV6UUFTPG74G23RWIV6BK/events.json","paper":"https://pith.science/paper/I6L4WIV6"},"agent_actions":{"view_html":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK","download_json":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK.json","view_paper":"https://pith.science/paper/I6L4WIV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00188&json=true","fetch_graph":"https://pith.science/api/pith-number/I6L4WIV6UUFTPG74G23RWIV6BK/graph.json","fetch_events":"https://pith.science/api/pith-number/I6L4WIV6UUFTPG74G23RWIV6BK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK/action/storage_attestation","attest_author":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK/action/author_attestation","sign_citation":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK/action/citation_signature","submit_replication":"https://pith.science/pith/I6L4WIV6UUFTPG74G23RWIV6BK/action/replication_record"}},"created_at":"2026-07-05T00:01:06.588954+00:00","updated_at":"2026-07-05T00:01:06.588954+00:00"}