{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NKK33Z2DZJFMDHGUXD5NHTGBHH","short_pith_number":"pith:NKK33Z2D","schema_version":"1.0","canonical_sha256":"6a95bde743ca4ac19cd4b8fad3ccc139deae2fe72ca25643d9163c2d15bb30f8","source":{"kind":"arxiv","id":"1703.03130","version":1},"attestation_state":"computed","paper":{"title":"A Structured Self-attentive Sentence Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Bowen Zhou, Cicero Nogueira dos Santos, Minwei Feng, Mo Yu, Yoshua Bengio, Zhouhan Lin","submitted_at":"2017-03-09T04:42:30Z","abstract_excerpt":"This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes with an easy way of visualizing what specific parts of the sentence are encoded into the embedding. We evaluate our model on 3 different tasks: author profiling, sentiment classification, and textual entail"},"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":"1703.03130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-09T04:42:30Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"d67fb98358ea39ad37ffda1511a3e624276f809447ec494799ce53e5e06053bd","abstract_canon_sha256":"2c32c7807e3cb3831892e738a34e960bbd4a7d0935c27ae54d6cd046eeb6125e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:01.408443Z","signature_b64":"xXKAoul2AhAoU2ahpfPbhNyuSi2zwXTrj6ilZOw1WyVy/WbuLNLKtEr7k4PB5eq6cnuc5E1aLhXOu/xMW0EiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a95bde743ca4ac19cd4b8fad3ccc139deae2fe72ca25643d9163c2d15bb30f8","last_reissued_at":"2026-05-18T00:49:01.407701Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:01.407701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Structured Self-attentive Sentence Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Bowen Zhou, Cicero Nogueira dos Santos, Minwei Feng, Mo Yu, Yoshua Bengio, Zhouhan Lin","submitted_at":"2017-03-09T04:42:30Z","abstract_excerpt":"This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes with an easy way of visualizing what specific parts of the sentence are encoded into the embedding. We evaluate our model on 3 different tasks: author profiling, sentiment classification, and textual entail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03130","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":"1703.03130","created_at":"2026-05-18T00:49:01.407825+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03130v1","created_at":"2026-05-18T00:49:01.407825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03130","created_at":"2026-05-18T00:49:01.407825+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKK33Z2DZJFM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKK33Z2DZJFMDHGU","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKK33Z2D","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.08952","citing_title":"Deep Mixture Point Processes: Spatio-temporal Event Prediction with Rich Contextual Information","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06582","citing_title":"AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08871","citing_title":"Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11065","citing_title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11769","citing_title":"Automatically Learning Construction Injury Precursors from Text","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24255","citing_title":"Cognitive State Inference from VR Motion via Motion Foundation Model","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1807.03819","citing_title":"Universal Transformers","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08833","citing_title":"FRACTAL: SSM with Fractional Recurrent Architecture for Computational Temporal Analysis of Long Sequences","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05873","citing_title":"Learning Shared Sentiment Prototypes for Adaptive Multimodal Sentiment Analysis","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"1710.10903","citing_title":"Graph Attention Networks","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"1706.03762","citing_title":"Attention Is All You Need","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH","json":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH.json","graph_json":"https://pith.science/api/pith-number/NKK33Z2DZJFMDHGUXD5NHTGBHH/graph.json","events_json":"https://pith.science/api/pith-number/NKK33Z2DZJFMDHGUXD5NHTGBHH/events.json","paper":"https://pith.science/paper/NKK33Z2D"},"agent_actions":{"view_html":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH","download_json":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH.json","view_paper":"https://pith.science/paper/NKK33Z2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03130&json=true","fetch_graph":"https://pith.science/api/pith-number/NKK33Z2DZJFMDHGUXD5NHTGBHH/graph.json","fetch_events":"https://pith.science/api/pith-number/NKK33Z2DZJFMDHGUXD5NHTGBHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH/action/storage_attestation","attest_author":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH/action/author_attestation","sign_citation":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH/action/citation_signature","submit_replication":"https://pith.science/pith/NKK33Z2DZJFMDHGUXD5NHTGBHH/action/replication_record"}},"created_at":"2026-05-18T00:49:01.407825+00:00","updated_at":"2026-05-18T00:49:01.407825+00:00"}