{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SBEKGIHJGSH6BEMAQQNGSROLG7","short_pith_number":"pith:SBEKGIHJ","schema_version":"1.0","canonical_sha256":"9048a320e9348fe09180841a6945cb37ec97c942a9bd2c9dcd6e3af7b4611b20","source":{"kind":"arxiv","id":"1705.09189","version":1},"attestation_state":"computed","paper":{"title":"Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Jean Maillard, Stephen Clark","submitted_at":"2017-05-25T14:09:48Z","abstract_excerpt":"We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied along a tree structure found by a fully differentiable natural language chart parser. Our model simultaneously optimises both the composition function and the parser, thus eliminating the need for externally-provided parse trees which are normally required for Tree-LSTM. It can therefore be seen as a tree-based RNN that is unsupervised with respect to the parse trees. As it is fully differentiable, our model is easily tr"},"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":"1705.09189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-25T14:09:48Z","cross_cats_sorted":[],"title_canon_sha256":"b3e4b351a739a544ca938ab136510fb95d57743d36ab6c2b9a888f2283289a74","abstract_canon_sha256":"e59ce514469373b0a958b2a1506b3bb85eadc46bdd1e21fb93b9311cbb33b93d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:32.136211Z","signature_b64":"z/0ArrpMyDEWwoD4h+m+QCi0aGHnSdGYg6Yb8ocG89MjUXXL03uvMWYHUCCy9AqqX9R4m3uGzaGkZlYQYVwOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9048a320e9348fe09180841a6945cb37ec97c942a9bd2c9dcd6e3af7b4611b20","last_reissued_at":"2026-07-05T00:33:32.135853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:32.135853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Jean Maillard, Stephen Clark","submitted_at":"2017-05-25T14:09:48Z","abstract_excerpt":"We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied along a tree structure found by a fully differentiable natural language chart parser. Our model simultaneously optimises both the composition function and the parser, thus eliminating the need for externally-provided parse trees which are normally required for Tree-LSTM. It can therefore be seen as a tree-based RNN that is unsupervised with respect to the parse trees. As it is fully differentiable, our model is easily tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09189","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1705.09189/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1705.09189","created_at":"2026-07-05T00:33:32.135912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.09189v1","created_at":"2026-07-05T00:33:32.135912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09189","created_at":"2026-07-05T00:33:32.135912+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBEKGIHJGSH6","created_at":"2026-07-05T00:33:32.135912+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBEKGIHJGSH6BEMA","created_at":"2026-07-05T00:33:32.135912+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBEKGIHJ","created_at":"2026-07-05T00:33:32.135912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1906.09992","citing_title":"Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7","json":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7.json","graph_json":"https://pith.science/api/pith-number/SBEKGIHJGSH6BEMAQQNGSROLG7/graph.json","events_json":"https://pith.science/api/pith-number/SBEKGIHJGSH6BEMAQQNGSROLG7/events.json","paper":"https://pith.science/paper/SBEKGIHJ"},"agent_actions":{"view_html":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7","download_json":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7.json","view_paper":"https://pith.science/paper/SBEKGIHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.09189&json=true","fetch_graph":"https://pith.science/api/pith-number/SBEKGIHJGSH6BEMAQQNGSROLG7/graph.json","fetch_events":"https://pith.science/api/pith-number/SBEKGIHJGSH6BEMAQQNGSROLG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7/action/storage_attestation","attest_author":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7/action/author_attestation","sign_citation":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7/action/citation_signature","submit_replication":"https://pith.science/pith/SBEKGIHJGSH6BEMAQQNGSROLG7/action/replication_record"}},"created_at":"2026-07-05T00:33:32.135912+00:00","updated_at":"2026-07-05T00:33:32.135912+00:00"}