{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:L5VFQ23MUBIAXIU6FST6EXWEQP","short_pith_number":"pith:L5VFQ23M","schema_version":"1.0","canonical_sha256":"5f6a586b6ca0500ba29e2ca7e25ec483e1ee9b74a832df2b73b672b1ebce3499","source":{"kind":"arxiv","id":"1911.03329","version":1},"attestation_state":"computed","paper":{"title":"Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Mirac Suzgun, Sebastian Gehrmann, Stuart M. Shieber, Yonatan Belinkov","submitted_at":"2019-11-08T15:33:51Z","abstract_excerpt":"We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-based mechanisms. We provide the first demonstration of neural networks recognizing the generalized Dyck languages, which express the core of what it means to be a language with hierarchical structure. Our memory-augmented architectures are easy to train in an end-to-end fashion and can learn the Dyck languages over as many as six parenthesis-pairs, in addition to two deterministic palindrome languages and the string-r"},"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":"1911.03329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T15:33:51Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"00af9a91dd27835700008f5a566b9124a3a917b5e5c82bcefa7e2bad0e5f8562","abstract_canon_sha256":"d9efe12c6d6ee3861a92e8dcc43fe971ad4c6c56213b2413cfb36642a5663570"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:01.580522Z","signature_b64":"k5Plc8w1YxyQFbVxHs3hoUvGGtt57EqEZIDoHmoqYdW9LhYDpav5fI/n7o5NmZoPRBtw/qHkg3HhI148Up0RCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f6a586b6ca0500ba29e2ca7e25ec483e1ee9b74a832df2b73b672b1ebce3499","last_reissued_at":"2026-07-05T00:18:01.580092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:01.580092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Mirac Suzgun, Sebastian Gehrmann, Stuart M. Shieber, Yonatan Belinkov","submitted_at":"2019-11-08T15:33:51Z","abstract_excerpt":"We introduce three memory-augmented Recurrent Neural Networks (MARNNs) and explore their capabilities on a series of simple language modeling tasks whose solutions require stack-based mechanisms. We provide the first demonstration of neural networks recognizing the generalized Dyck languages, which express the core of what it means to be a language with hierarchical structure. Our memory-augmented architectures are easy to train in an end-to-end fashion and can learn the Dyck languages over as many as six parenthesis-pairs, in addition to two deterministic palindrome languages and the string-r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03329","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/1911.03329/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":"1911.03329","created_at":"2026-07-05T00:18:01.580148+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03329v1","created_at":"2026-07-05T00:18:01.580148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03329","created_at":"2026-07-05T00:18:01.580148+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5VFQ23MUBIA","created_at":"2026-07-05T00:18:01.580148+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5VFQ23MUBIAXIU6","created_at":"2026-07-05T00:18:01.580148+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5VFQ23M","created_at":"2026-07-05T00:18:01.580148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05171","citing_title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17857","citing_title":"On the Emergence of Syntax by Means of Local Interaction","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP","json":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP.json","graph_json":"https://pith.science/api/pith-number/L5VFQ23MUBIAXIU6FST6EXWEQP/graph.json","events_json":"https://pith.science/api/pith-number/L5VFQ23MUBIAXIU6FST6EXWEQP/events.json","paper":"https://pith.science/paper/L5VFQ23M"},"agent_actions":{"view_html":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP","download_json":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP.json","view_paper":"https://pith.science/paper/L5VFQ23M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03329&json=true","fetch_graph":"https://pith.science/api/pith-number/L5VFQ23MUBIAXIU6FST6EXWEQP/graph.json","fetch_events":"https://pith.science/api/pith-number/L5VFQ23MUBIAXIU6FST6EXWEQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP/action/storage_attestation","attest_author":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP/action/author_attestation","sign_citation":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP/action/citation_signature","submit_replication":"https://pith.science/pith/L5VFQ23MUBIAXIU6FST6EXWEQP/action/replication_record"}},"created_at":"2026-07-05T00:18:01.580148+00:00","updated_at":"2026-07-05T00:18:01.580148+00:00"}