{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:D3PGK25RQ6J7H2UZXY3YA34PLY","short_pith_number":"pith:D3PGK25R","schema_version":"1.0","canonical_sha256":"1ede656bb18793f3ea99be37806f8f5e10f28a12e77b8a1192788b6a241af80a","source":{"kind":"arxiv","id":"1503.00185","version":5},"attestation_state":"computed","paper":{"title":"When Are Tree Structures Necessary for Deep Learning of Representations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dan Jurafsky, Eudard Hovy, Jiwei Li, Minh-Thang Luong","submitted_at":"2015-02-28T21:39:31Z","abstract_excerpt":"Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark {\\bf recursive} neural models against sequential {\\bf recurrent} neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discou"},"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":"1503.00185","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-02-28T21:39:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2cc4b24fa4d6ac88e3911217dfeb3c7f222153b1590e13d14e044238da88eb62","abstract_canon_sha256":"51073f1e56cf6f1490f3722cc6d6ae9745cd7ca1f081e2add1215c26830890d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:11.034866Z","signature_b64":"Hw0ecpp882uJlH/59pWshsIFmgIsq2jPAjnRxoHrrQxYf7FzN4jWP03dUwilNXzJ8XMIBqQm/DoicKJPy4ttAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ede656bb18793f3ea99be37806f8f5e10f28a12e77b8a1192788b6a241af80a","last_reissued_at":"2026-05-18T01:35:11.034158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:11.034158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Are Tree Structures Necessary for Deep Learning of Representations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dan Jurafsky, Eudard Hovy, Jiwei Li, Minh-Thang Luong","submitted_at":"2015-02-28T21:39:31Z","abstract_excerpt":"Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark {\\bf recursive} neural models against sequential {\\bf recurrent} neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.00185","kind":"arxiv","version":5},"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":"1503.00185","created_at":"2026-05-18T01:35:11.034266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.00185v5","created_at":"2026-05-18T01:35:11.034266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.00185","created_at":"2026-05-18T01:35:11.034266+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3PGK25RQ6J7","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3PGK25RQ6J7H2UZ","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3PGK25R","created_at":"2026-05-18T12:29:17.054201+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/D3PGK25RQ6J7H2UZXY3YA34PLY","json":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY.json","graph_json":"https://pith.science/api/pith-number/D3PGK25RQ6J7H2UZXY3YA34PLY/graph.json","events_json":"https://pith.science/api/pith-number/D3PGK25RQ6J7H2UZXY3YA34PLY/events.json","paper":"https://pith.science/paper/D3PGK25R"},"agent_actions":{"view_html":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY","download_json":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY.json","view_paper":"https://pith.science/paper/D3PGK25R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.00185&json=true","fetch_graph":"https://pith.science/api/pith-number/D3PGK25RQ6J7H2UZXY3YA34PLY/graph.json","fetch_events":"https://pith.science/api/pith-number/D3PGK25RQ6J7H2UZXY3YA34PLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY/action/storage_attestation","attest_author":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY/action/author_attestation","sign_citation":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY/action/citation_signature","submit_replication":"https://pith.science/pith/D3PGK25RQ6J7H2UZXY3YA34PLY/action/replication_record"}},"created_at":"2026-05-18T01:35:11.034266+00:00","updated_at":"2026-05-18T01:35:11.034266+00:00"}