{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2WMDNDAHRQUI4SDJVRYUHRFJ2R","short_pith_number":"pith:2WMDNDAH","schema_version":"1.0","canonical_sha256":"d598368c078c288e4869ac7143c4a9d45cefd49b9f5fc9a168af6a1b1be57e40","source":{"kind":"arxiv","id":"1705.07704","version":3},"attestation_state":"computed","paper":{"title":"A Regularized Framework for Sparse and Structured Neural Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Mathieu Blondel, Vlad Niculae","submitted_at":"2017-05-22T13:11:24Z","abstract_excerpt":"Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework includes softmax and a slight generalization of the recently-proposed sparsemax as special cases. However, we also show how our framework can incorporate modern structured penalties, resulting in more interpr"},"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":"1705.07704","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-05-22T13:11:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a919a72cb6c18e1f83e1a272b147317468302e021dc79059ce8c67312d6fefe2","abstract_canon_sha256":"82b445c74a9eaf0eacf826defa89dd0ef642c90e121e3ea5be9515c4a2052eb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:56.097878Z","signature_b64":"kl7Cd7aZ4aYdWt2Cw2sO8omlCbCBmVQZKuzZnuoy8s64BqUnXSURwOiEg/0aeLfHAGSIVnU/52usFNOUBtK6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d598368c078c288e4869ac7143c4a9d45cefd49b9f5fc9a168af6a1b1be57e40","last_reissued_at":"2026-05-17T23:52:56.097210Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:56.097210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Regularized Framework for Sparse and Structured Neural Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Mathieu Blondel, Vlad Niculae","submitted_at":"2017-05-22T13:11:24Z","abstract_excerpt":"Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max operator. We show that the gradient of this operator defines a mapping from real values to probabilities, suitable as an attention mechanism. Our framework includes softmax and a slight generalization of the recently-proposed sparsemax as special cases. However, we also show how our framework can incorporate modern structured penalties, resulting in more interpr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07704","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":"1705.07704","created_at":"2026-05-17T23:52:56.097301+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07704v3","created_at":"2026-05-17T23:52:56.097301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07704","created_at":"2026-05-17T23:52:56.097301+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WMDNDAHRQUI","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WMDNDAHRQUI4SDJ","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WMDNDAH","created_at":"2026-05-18T12:30:55.937587+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/2WMDNDAHRQUI4SDJVRYUHRFJ2R","json":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R.json","graph_json":"https://pith.science/api/pith-number/2WMDNDAHRQUI4SDJVRYUHRFJ2R/graph.json","events_json":"https://pith.science/api/pith-number/2WMDNDAHRQUI4SDJVRYUHRFJ2R/events.json","paper":"https://pith.science/paper/2WMDNDAH"},"agent_actions":{"view_html":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R","download_json":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R.json","view_paper":"https://pith.science/paper/2WMDNDAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07704&json=true","fetch_graph":"https://pith.science/api/pith-number/2WMDNDAHRQUI4SDJVRYUHRFJ2R/graph.json","fetch_events":"https://pith.science/api/pith-number/2WMDNDAHRQUI4SDJVRYUHRFJ2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R/action/storage_attestation","attest_author":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R/action/author_attestation","sign_citation":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R/action/citation_signature","submit_replication":"https://pith.science/pith/2WMDNDAHRQUI4SDJVRYUHRFJ2R/action/replication_record"}},"created_at":"2026-05-17T23:52:56.097301+00:00","updated_at":"2026-05-17T23:52:56.097301+00:00"}