{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IIVYFSCMFMULXLI624VLD7PIJA","short_pith_number":"pith:IIVYFSCM","schema_version":"1.0","canonical_sha256":"422b82c84c2b28bbad1ed72ab1fde8482762279cf5fec1b9b5de50c0e64b45e4","source":{"kind":"arxiv","id":"1810.10182","version":1},"attestation_state":"computed","paper":{"title":"Modeling Localness for Self-Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Derek F. Wong, Fandong Meng, Lidia S. Chao, Tong Zhang, Zhaopeng Tu","submitted_at":"2018-10-24T04:08:25Z","abstract_excerpt":"Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies and enhance the ability of capturing short-r"},"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":"1810.10182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T04:08:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a072db561a5e731baca6ae405c5b9ac015bc376833025d92c24605f8da5358c","abstract_canon_sha256":"6f64e549bd29b94416fd675812b1dcca6ffe608661e72f16485df74746bc16a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:23.993038Z","signature_b64":"R2QSh0fPj23TsmPgYybH45maUnrhHucW+m9d588vrdouHYV9Tu+Fe+8hIsWaWL1m/edDxKa+2gts/BtOzBAmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422b82c84c2b28bbad1ed72ab1fde8482762279cf5fec1b9b5de50c0e64b45e4","last_reissued_at":"2026-05-18T00:02:23.992363Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:23.992363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Localness for Self-Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Derek F. Wong, Fandong Meng, Lidia S. Chao, Tong Zhang, Zhaopeng Tu","submitted_at":"2018-10-24T04:08:25Z","abstract_excerpt":"Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies and enhance the ability of capturing short-r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10182","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":""},"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":"1810.10182","created_at":"2026-05-18T00:02:23.992477+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10182v1","created_at":"2026-05-18T00:02:23.992477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10182","created_at":"2026-05-18T00:02:23.992477+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIVYFSCMFMUL","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIVYFSCMFMULXLI6","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIVYFSCM","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00188","citing_title":"Improving Multi-Head Attention with Capsule Networks","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA","json":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA.json","graph_json":"https://pith.science/api/pith-number/IIVYFSCMFMULXLI624VLD7PIJA/graph.json","events_json":"https://pith.science/api/pith-number/IIVYFSCMFMULXLI624VLD7PIJA/events.json","paper":"https://pith.science/paper/IIVYFSCM"},"agent_actions":{"view_html":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA","download_json":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA.json","view_paper":"https://pith.science/paper/IIVYFSCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10182&json=true","fetch_graph":"https://pith.science/api/pith-number/IIVYFSCMFMULXLI624VLD7PIJA/graph.json","fetch_events":"https://pith.science/api/pith-number/IIVYFSCMFMULXLI624VLD7PIJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA/action/storage_attestation","attest_author":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA/action/author_attestation","sign_citation":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA/action/citation_signature","submit_replication":"https://pith.science/pith/IIVYFSCMFMULXLI624VLD7PIJA/action/replication_record"}},"created_at":"2026-05-18T00:02:23.992477+00:00","updated_at":"2026-05-18T00:02:23.992477+00:00"}