{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZKNWXLARD36GKXTVQ6VWOV2EE3","short_pith_number":"pith:ZKNWXLAR","schema_version":"1.0","canonical_sha256":"ca9b6bac111efc655e7587ab67574426e76f927ae141bd0c3b84c095ffe6eca3","source":{"kind":"arxiv","id":"1503.00075","version":3},"attestation_state":"computed","paper":{"title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Kai Sheng Tai, Richard Socher","submitted_at":"2015-02-28T06:31:50Z","abstract_excerpt":"Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LST"},"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":"1503.00075","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-28T06:31:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c0bb8be94602a98fe393cd773c95aae695f2ba3a7e3eca3a294cd149c680cc95","abstract_canon_sha256":"57919850648b827c1bc0b0e5aea810a73830995c2c82bb11dc0ed6416cbc04ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:59:57.682824Z","signature_b64":"XcllF0LS/LiYV7+SUxC33M82ceezl3lMqacU2oc9cHYCEfTnUC1Ca6ZWEdm+NSY3iiPDGJZj60YCAWk6tfK+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca9b6bac111efc655e7587ab67574426e76f927ae141bd0c3b84c095ffe6eca3","last_reissued_at":"2026-05-18T01:59:57.682303Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:59:57.682303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Kai Sheng Tai, Richard Socher","submitted_at":"2015-02-28T06:31:50Z","abstract_excerpt":"Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of sequence modeling tasks. The only underlying LSTM structure that has been explored so far is a linear chain. However, natural language exhibits syntactic properties that would naturally combine words to phrases. We introduce the Tree-LSTM, a generalization of LSTMs to tree-structured network topologies. Tree-LSTMs outperform all existing systems and strong LST"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.00075","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":"1503.00075","created_at":"2026-05-18T01:59:57.682407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.00075v3","created_at":"2026-05-18T01:59:57.682407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.00075","created_at":"2026-05-18T01:59:57.682407+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKNWXLARD36G","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKNWXLARD36GKXTV","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKNWXLAR","created_at":"2026-05-18T12:29:52.810259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.12029","citing_title":"A Neural-based Program Decompiler","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06690","citing_title":"A Scalable Framework for Multilevel Streaming Data Analytics using Deep Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17108","citing_title":"Parallel Recursive LSTM","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2603.07520","citing_title":"On the Effectiveness of Code Representation in Deep Learning-Based Automated Patch Correctness Assessment","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08155","citing_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3","json":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3.json","graph_json":"https://pith.science/api/pith-number/ZKNWXLARD36GKXTVQ6VWOV2EE3/graph.json","events_json":"https://pith.science/api/pith-number/ZKNWXLARD36GKXTVQ6VWOV2EE3/events.json","paper":"https://pith.science/paper/ZKNWXLAR"},"agent_actions":{"view_html":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3","download_json":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3.json","view_paper":"https://pith.science/paper/ZKNWXLAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.00075&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKNWXLARD36GKXTVQ6VWOV2EE3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKNWXLARD36GKXTVQ6VWOV2EE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3/action/storage_attestation","attest_author":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3/action/author_attestation","sign_citation":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3/action/citation_signature","submit_replication":"https://pith.science/pith/ZKNWXLARD36GKXTVQ6VWOV2EE3/action/replication_record"}},"created_at":"2026-05-18T01:59:57.682407+00:00","updated_at":"2026-05-18T01:59:57.682407+00:00"}