{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ITSFS4PWU36LHWEVJPLORZA5DR","short_pith_number":"pith:ITSFS4PW","schema_version":"1.0","canonical_sha256":"44e45971f6a6fcb3d8954bd6e8e41d1c4aace4d9c2af1da9daa48516a880d01f","source":{"kind":"arxiv","id":"2101.02258","version":1},"attestation_state":"computed","paper":{"title":"Can RNNs learn Recursive Nested Subject-Verb Agreements?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beno\\^it Crabb\\'e, Jean-R\\'emi King, Maxime Oquab, Stanislas Dehaene, Th\\'eo Desbordes, Yair Lakretz","submitted_at":"2021-01-06T20:47:02Z","abstract_excerpt":"One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remains unclear whether and how this code could be implemented in neural circuits. Recent advances in Recurrent Neural Networks (RNNs), which achieve near-human performance in some language tasks, provide a compelling model to address such questions. Here, we present a new framework to study recursive processing in RNNs, using subject-verb agreement as a probe into the representations of the neural network. We trained six "},"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":"2101.02258","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-06T20:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"011de6c309633137051add3672979dcedbf812f43c10ca25669edde602a8ec44","abstract_canon_sha256":"57d46e52d8f924d6f9bf682c582c11f7555b547486ece28ff76bca3f72e6f2a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:11.856005Z","signature_b64":"pN7b4A9KmDAI2fA81u/NZuV1gf/C4+KomIzIA9genjhgTfNsnFQwjprWJ8cp3WTw0eW9P8j4Rz38KC+j2q0eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44e45971f6a6fcb3d8954bd6e8e41d1c4aace4d9c2af1da9daa48516a880d01f","last_reissued_at":"2026-07-05T02:05:11.855495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:11.855495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can RNNs learn Recursive Nested Subject-Verb Agreements?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beno\\^it Crabb\\'e, Jean-R\\'emi King, Maxime Oquab, Stanislas Dehaene, Th\\'eo Desbordes, Yair Lakretz","submitted_at":"2021-01-06T20:47:02Z","abstract_excerpt":"One of the fundamental principles of contemporary linguistics states that language processing requires the ability to extract recursively nested tree structures. However, it remains unclear whether and how this code could be implemented in neural circuits. Recent advances in Recurrent Neural Networks (RNNs), which achieve near-human performance in some language tasks, provide a compelling model to address such questions. Here, we present a new framework to study recursive processing in RNNs, using subject-verb agreement as a probe into the representations of the neural network. We trained six "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02258","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/2101.02258/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":"2101.02258","created_at":"2026-07-05T02:05:11.855566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02258v1","created_at":"2026-07-05T02:05:11.855566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02258","created_at":"2026-07-05T02:05:11.855566+00:00"},{"alias_kind":"pith_short_12","alias_value":"ITSFS4PWU36L","created_at":"2026-07-05T02:05:11.855566+00:00"},{"alias_kind":"pith_short_16","alias_value":"ITSFS4PWU36LHWEV","created_at":"2026-07-05T02:05:11.855566+00:00"},{"alias_kind":"pith_short_8","alias_value":"ITSFS4PW","created_at":"2026-07-05T02:05:11.855566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00197","citing_title":"Learning Model Successors","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR","json":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR.json","graph_json":"https://pith.science/api/pith-number/ITSFS4PWU36LHWEVJPLORZA5DR/graph.json","events_json":"https://pith.science/api/pith-number/ITSFS4PWU36LHWEVJPLORZA5DR/events.json","paper":"https://pith.science/paper/ITSFS4PW"},"agent_actions":{"view_html":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR","download_json":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR.json","view_paper":"https://pith.science/paper/ITSFS4PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02258&json=true","fetch_graph":"https://pith.science/api/pith-number/ITSFS4PWU36LHWEVJPLORZA5DR/graph.json","fetch_events":"https://pith.science/api/pith-number/ITSFS4PWU36LHWEVJPLORZA5DR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR/action/storage_attestation","attest_author":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR/action/author_attestation","sign_citation":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR/action/citation_signature","submit_replication":"https://pith.science/pith/ITSFS4PWU36LHWEVJPLORZA5DR/action/replication_record"}},"created_at":"2026-07-05T02:05:11.855566+00:00","updated_at":"2026-07-05T02:05:11.855566+00:00"}