{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:37F3E5FURSDVXYZ4UTUZAXAOJV","short_pith_number":"pith:37F3E5FU","schema_version":"1.0","canonical_sha256":"dfcbb274b48c875be33ca4e9905c0e4d5f2474d5ec0bf19fdb2d71f101da3951","source":{"kind":"arxiv","id":"1406.1827","version":4},"attestation_state":"computed","paper":{"title":"Recursive Neural Networks Can Learn Logical Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Christopher Potts, Samuel R. Bowman","submitted_at":"2014-06-06T22:09:27Z","abstract_excerpt":"Tree-structured recursive neural networks (TreeRNNs) for sentence meaning have been successful for many applications, but it remains an open question whether the fixed-length representations that they learn can support tasks as demanding as logical deduction. We pursue this question by evaluating whether two such models---plain TreeRNNs and tree-structured neural tensor networks (TreeRNTNs)---can correctly learn to identify logical relationships such as entailment and contradiction using these representations. In our first set of experiments, we generate artificial data from a logical grammar "},"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":"1406.1827","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-06-06T22:09:27Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"ef6486ff85950a9e7261081e14ee2f2de450cef80d22f42f952b7da57c7f53e3","abstract_canon_sha256":"9020422f058b9d54c75d7aa0a9dc278dcaa88db8f2f9f278cfb619ef62b863a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:09:54.629216Z","signature_b64":"u0h6jnfrcLifh77M8Uoka2ggEVRAK9AhRRBB0D8Wd6aBx1uwTQDtGJ5qzgikAnJur+4Cgc8po3c7qJV1rLczAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfcbb274b48c875be33ca4e9905c0e4d5f2474d5ec0bf19fdb2d71f101da3951","last_reissued_at":"2026-05-18T02:09:54.628485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:09:54.628485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recursive Neural Networks Can Learn Logical Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Christopher D. Manning, Christopher Potts, Samuel R. Bowman","submitted_at":"2014-06-06T22:09:27Z","abstract_excerpt":"Tree-structured recursive neural networks (TreeRNNs) for sentence meaning have been successful for many applications, but it remains an open question whether the fixed-length representations that they learn can support tasks as demanding as logical deduction. We pursue this question by evaluating whether two such models---plain TreeRNNs and tree-structured neural tensor networks (TreeRNTNs)---can correctly learn to identify logical relationships such as entailment and contradiction using these representations. In our first set of experiments, we generate artificial data from a logical grammar "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1827","kind":"arxiv","version":4},"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":"1406.1827","created_at":"2026-05-18T02:09:54.628604+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.1827v4","created_at":"2026-05-18T02:09:54.628604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1827","created_at":"2026-05-18T02:09:54.628604+00:00"},{"alias_kind":"pith_short_12","alias_value":"37F3E5FURSDV","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_16","alias_value":"37F3E5FURSDVXYZ4","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_8","alias_value":"37F3E5FU","created_at":"2026-05-18T12:28:11.866339+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/37F3E5FURSDVXYZ4UTUZAXAOJV","json":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV.json","graph_json":"https://pith.science/api/pith-number/37F3E5FURSDVXYZ4UTUZAXAOJV/graph.json","events_json":"https://pith.science/api/pith-number/37F3E5FURSDVXYZ4UTUZAXAOJV/events.json","paper":"https://pith.science/paper/37F3E5FU"},"agent_actions":{"view_html":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV","download_json":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV.json","view_paper":"https://pith.science/paper/37F3E5FU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.1827&json=true","fetch_graph":"https://pith.science/api/pith-number/37F3E5FURSDVXYZ4UTUZAXAOJV/graph.json","fetch_events":"https://pith.science/api/pith-number/37F3E5FURSDVXYZ4UTUZAXAOJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV/action/storage_attestation","attest_author":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV/action/author_attestation","sign_citation":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV/action/citation_signature","submit_replication":"https://pith.science/pith/37F3E5FURSDVXYZ4UTUZAXAOJV/action/replication_record"}},"created_at":"2026-05-18T02:09:54.628604+00:00","updated_at":"2026-05-18T02:09:54.628604+00:00"}