{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:F4GADWCCSD2AOH56P5VIHQBDZJ","short_pith_number":"pith:F4GADWCC","schema_version":"1.0","canonical_sha256":"2f0c01d84290f4071fbe7f6a83c023ca5b4cfb1d55e85f49f388dc683a90e976","source":{"kind":"arxiv","id":"1811.01001","version":1},"attestation_state":"computed","paper":{"title":"On Evaluating the Generalization of LSTM Models in Formal Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mirac Suzgun, Stuart M. Shieber, Yonatan Belinkov","submitted_at":"2018-11-02T17:37:39Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established themselves as a dominant model for language processing. Yet, there still remains an uncertainty regarding their language learning capabilities. In this paper, we empirically evaluate the inductive learning capabilities of Long Short-Term Memory networks, a popular extension of simple RNNs, to learn simple formal languages, in particular $a^nb^n$, $a^nb^nc^n$, and $a^nb^nc^nd^n$. We investigate the influence of various aspects of learning, such as training data regimes and model capacity, on the generalization to"},"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":"1811.01001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T17:37:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dc284ea3dc4ad581270d3aa9ecb1d8d8e6a51235193cad43c725204aefea4357","abstract_canon_sha256":"55b9072767ddea4d0af0c767c103015f90e7256239c53932507833354525a44b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:39.694039Z","signature_b64":"VX57U3VohuG5+ndZZcnmgiA4h1g1KI4YiEpjHbbkLYo/vw4/iX1pcQZI/Aa/NXmjEVBxoX2okB/lu6X6WpqIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0c01d84290f4071fbe7f6a83c023ca5b4cfb1d55e85f49f388dc683a90e976","last_reissued_at":"2026-05-18T00:01:39.693409Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:39.693409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Evaluating the Generalization of LSTM Models in Formal Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mirac Suzgun, Stuart M. Shieber, Yonatan Belinkov","submitted_at":"2018-11-02T17:37:39Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established themselves as a dominant model for language processing. Yet, there still remains an uncertainty regarding their language learning capabilities. In this paper, we empirically evaluate the inductive learning capabilities of Long Short-Term Memory networks, a popular extension of simple RNNs, to learn simple formal languages, in particular $a^nb^n$, $a^nb^nc^n$, and $a^nb^nc^nd^n$. We investigate the influence of various aspects of learning, such as training data regimes and model capacity, on the generalization to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01001","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":""},"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":"1811.01001","created_at":"2026-05-18T00:01:39.693495+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01001v1","created_at":"2026-05-18T00:01:39.693495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01001","created_at":"2026-05-18T00:01:39.693495+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4GADWCCSD2A","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4GADWCCSD2AOH56","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4GADWCC","created_at":"2026-05-18T12:32:22.470017+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/F4GADWCCSD2AOH56P5VIHQBDZJ","json":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ.json","graph_json":"https://pith.science/api/pith-number/F4GADWCCSD2AOH56P5VIHQBDZJ/graph.json","events_json":"https://pith.science/api/pith-number/F4GADWCCSD2AOH56P5VIHQBDZJ/events.json","paper":"https://pith.science/paper/F4GADWCC"},"agent_actions":{"view_html":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ","download_json":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ.json","view_paper":"https://pith.science/paper/F4GADWCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01001&json=true","fetch_graph":"https://pith.science/api/pith-number/F4GADWCCSD2AOH56P5VIHQBDZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/F4GADWCCSD2AOH56P5VIHQBDZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ/action/storage_attestation","attest_author":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ/action/author_attestation","sign_citation":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ/action/citation_signature","submit_replication":"https://pith.science/pith/F4GADWCCSD2AOH56P5VIHQBDZJ/action/replication_record"}},"created_at":"2026-05-18T00:01:39.693495+00:00","updated_at":"2026-05-18T00:01:39.693495+00:00"}