{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P6GVMDRV2ADTA2XPOWTRV5PZ3F","short_pith_number":"pith:P6GVMDRV","schema_version":"1.0","canonical_sha256":"7f8d560e35d007306aef75a71af5f9d97001d8e12b599c06bb2f41c9a86adede","source":{"kind":"arxiv","id":"1807.03595","version":1},"attestation_state":"computed","paper":{"title":"Revisiting the Hierarchical Multiscale LSTM","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Alishahi, \\'Akos K\\'ad\\'ar, Grzegorz Chrupa{\\l}a, Marc-Alexandre C\\^ot\\'e","submitted_at":"2018-07-10T12:46:30Z","abstract_excerpt":"Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics studies. However, the high complexity of the architecture, training procedure and implementations might hinder its applicability. We provide a detailed reproduction and ablation study of the architecture, shedding light on some of the potential caveats of re-purposing complex deep-learning architectures. We further show that simplifying certain aspects of the archi"},"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":"1807.03595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-07-10T12:46:30Z","cross_cats_sorted":[],"title_canon_sha256":"b0c3bc11c3201fc7bafd69f78589221a8ae99d52bbaf131d97e5ca20ee7da77c","abstract_canon_sha256":"3db5a4f229def1846121c7546e231eb30486b9ee6f0544031662b66750340717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:09.910665Z","signature_b64":"FXCNpfX3gQPFwaaCQnXB9mceibnF6j7K44pZOlY+ozWMRTP13/iVz9iIhOG8LEMRD2Q4sREvliRI5BrP1BQWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8d560e35d007306aef75a71af5f9d97001d8e12b599c06bb2f41c9a86adede","last_reissued_at":"2026-05-18T00:11:09.909859Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:09.909859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting the Hierarchical Multiscale LSTM","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Alishahi, \\'Akos K\\'ad\\'ar, Grzegorz Chrupa{\\l}a, Marc-Alexandre C\\^ot\\'e","submitted_at":"2018-07-10T12:46:30Z","abstract_excerpt":"Hierarchical Multiscale LSTM (Chung et al., 2016a) is a state-of-the-art language model that learns interpretable structure from character-level input. Such models can provide fertile ground for (cognitive) computational linguistics studies. However, the high complexity of the architecture, training procedure and implementations might hinder its applicability. We provide a detailed reproduction and ablation study of the architecture, shedding light on some of the potential caveats of re-purposing complex deep-learning architectures. We further show that simplifying certain aspects of the archi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03595","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":"1807.03595","created_at":"2026-05-18T00:11:09.909975+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03595v1","created_at":"2026-05-18T00:11:09.909975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03595","created_at":"2026-05-18T00:11:09.909975+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6GVMDRV2ADT","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6GVMDRV2ADTA2XP","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6GVMDRV","created_at":"2026-05-18T12:32:43.782077+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/P6GVMDRV2ADTA2XPOWTRV5PZ3F","json":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F.json","graph_json":"https://pith.science/api/pith-number/P6GVMDRV2ADTA2XPOWTRV5PZ3F/graph.json","events_json":"https://pith.science/api/pith-number/P6GVMDRV2ADTA2XPOWTRV5PZ3F/events.json","paper":"https://pith.science/paper/P6GVMDRV"},"agent_actions":{"view_html":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F","download_json":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F.json","view_paper":"https://pith.science/paper/P6GVMDRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03595&json=true","fetch_graph":"https://pith.science/api/pith-number/P6GVMDRV2ADTA2XPOWTRV5PZ3F/graph.json","fetch_events":"https://pith.science/api/pith-number/P6GVMDRV2ADTA2XPOWTRV5PZ3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F/action/storage_attestation","attest_author":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F/action/author_attestation","sign_citation":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F/action/citation_signature","submit_replication":"https://pith.science/pith/P6GVMDRV2ADTA2XPOWTRV5PZ3F/action/replication_record"}},"created_at":"2026-05-18T00:11:09.909975+00:00","updated_at":"2026-05-18T00:11:09.909975+00:00"}