{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DAZOZWWAFEGG76DEJKCEXS6EEB","short_pith_number":"pith:DAZOZWWA","schema_version":"1.0","canonical_sha256":"1832ecdac0290c6ff8644a844bcbc42048ddf5824432e921e0fff8abc7caef5a","source":{"kind":"arxiv","id":"1811.02338","version":2},"attestation_state":"computed","paper":{"title":"Learning to Embed Sentences Using Attentive Recursive Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanwang Zhang, Jiaxin Shi, Juanzi Li, Lei Hou, Zhiyuan Liu","submitted_at":"2018-11-06T13:12:22Z","abstract_excerpt":"Sentence embedding is an effective feature representation for most deep learning-based NLP tasks. One prevailing line of methods is using recursive latent tree-structured networks to embed sentences with task-specific structures. However, existing models have no explicit mechanism to emphasize task-informative words in the tree structure. To this end, we propose an Attentive Recursive Tree model (AR-Tree), where the words are dynamically located according to their importance in the task. Specifically, we construct the latent tree for a sentence in a proposed important-first strategy, and place"},"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":"1811.02338","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T13:12:22Z","cross_cats_sorted":[],"title_canon_sha256":"9e4177b2b262be5e2bf52a33378d0546304fef56dfa56dc0cac52a2c88749afa","abstract_canon_sha256":"4dbc7d3bd678312b9456acdf0d861a4b4edac0143de28f87169bbce951f053a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.113870Z","signature_b64":"7a9dEDplHSSdkFJ4m0h/ZWdQs1yjeyNBDxHA4HeibZawgWTUrLzhh/KXulA30wkLNkm5psrsEFdtIusvRlGSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1832ecdac0290c6ff8644a844bcbc42048ddf5824432e921e0fff8abc7caef5a","last_reissued_at":"2026-05-18T00:00:39.113411Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.113411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Embed Sentences Using Attentive Recursive Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanwang Zhang, Jiaxin Shi, Juanzi Li, Lei Hou, Zhiyuan Liu","submitted_at":"2018-11-06T13:12:22Z","abstract_excerpt":"Sentence embedding is an effective feature representation for most deep learning-based NLP tasks. One prevailing line of methods is using recursive latent tree-structured networks to embed sentences with task-specific structures. However, existing models have no explicit mechanism to emphasize task-informative words in the tree structure. To this end, we propose an Attentive Recursive Tree model (AR-Tree), where the words are dynamically located according to their importance in the task. Specifically, we construct the latent tree for a sentence in a proposed important-first strategy, and place"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02338","kind":"arxiv","version":2},"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":"1811.02338","created_at":"2026-05-18T00:00:39.113483+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02338v2","created_at":"2026-05-18T00:00:39.113483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02338","created_at":"2026-05-18T00:00:39.113483+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAZOZWWAFEGG","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAZOZWWAFEGG76DE","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAZOZWWA","created_at":"2026-05-18T12:32:19.392346+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/DAZOZWWAFEGG76DEJKCEXS6EEB","json":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB.json","graph_json":"https://pith.science/api/pith-number/DAZOZWWAFEGG76DEJKCEXS6EEB/graph.json","events_json":"https://pith.science/api/pith-number/DAZOZWWAFEGG76DEJKCEXS6EEB/events.json","paper":"https://pith.science/paper/DAZOZWWA"},"agent_actions":{"view_html":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB","download_json":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB.json","view_paper":"https://pith.science/paper/DAZOZWWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02338&json=true","fetch_graph":"https://pith.science/api/pith-number/DAZOZWWAFEGG76DEJKCEXS6EEB/graph.json","fetch_events":"https://pith.science/api/pith-number/DAZOZWWAFEGG76DEJKCEXS6EEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB/action/storage_attestation","attest_author":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB/action/author_attestation","sign_citation":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB/action/citation_signature","submit_replication":"https://pith.science/pith/DAZOZWWAFEGG76DEJKCEXS6EEB/action/replication_record"}},"created_at":"2026-05-18T00:00:39.113483+00:00","updated_at":"2026-05-18T00:00:39.113483+00:00"}