{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YG66L77OBCW2Z3E4DUWOCBWGPD","short_pith_number":"pith:YG66L77O","schema_version":"1.0","canonical_sha256":"c1bde5ffee08adacec9c1d2ce106c678c750b50421527ea8b63c7dd6268fd67a","source":{"kind":"arxiv","id":"1907.00455","version":1},"attestation_state":"computed","paper":{"title":"Multiplicative Models for Recurrent Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Diego Maupom\\'e, Marie-Jean Meurs","submitted_at":"2019-06-30T20:51:43Z","abstract_excerpt":"Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrating second-order terms in the hidden-state update. One such model, multiplicative Long Short-Term Memory (mLSTM) is particularly interesting in its original formulation because of the sharing of its second-order term, referred to as the intermediate state. We explore these archit"},"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":"1907.00455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-30T20:51:43Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"aede22e70062bd204a043c2e49b439cb373df266935960a45fdccee1fd477f9c","abstract_canon_sha256":"7767477592f5523496a19bbf6fd159b7e488a76f0ad418336f4da7b1c2648013"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:51.623840Z","signature_b64":"r2Uu4TL+HezIHcl2AQQQ1MQV72BmAVU7CV1hvRFEqe1tJ7kEsLh0o0t0h8Vx4YlL7fheewaEKGEFQhCsqsn9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1bde5ffee08adacec9c1d2ce106c678c750b50421527ea8b63c7dd6268fd67a","last_reissued_at":"2026-05-17T23:41:51.623191Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:51.623191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiplicative Models for Recurrent Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Diego Maupom\\'e, Marie-Jean Meurs","submitted_at":"2019-06-30T20:51:43Z","abstract_excerpt":"Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating sequences due to high correlation between hidden states. These challenges can be mitigated by integrating second-order terms in the hidden-state update. One such model, multiplicative Long Short-Term Memory (mLSTM) is particularly interesting in its original formulation because of the sharing of its second-order term, referred to as the intermediate state. We explore these archit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00455","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":"1907.00455","created_at":"2026-05-17T23:41:51.623273+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00455v1","created_at":"2026-05-17T23:41:51.623273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00455","created_at":"2026-05-17T23:41:51.623273+00:00"},{"alias_kind":"pith_short_12","alias_value":"YG66L77OBCW2","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"YG66L77OBCW2Z3E4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"YG66L77O","created_at":"2026-05-18T12:33:33.725879+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/YG66L77OBCW2Z3E4DUWOCBWGPD","json":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD.json","graph_json":"https://pith.science/api/pith-number/YG66L77OBCW2Z3E4DUWOCBWGPD/graph.json","events_json":"https://pith.science/api/pith-number/YG66L77OBCW2Z3E4DUWOCBWGPD/events.json","paper":"https://pith.science/paper/YG66L77O"},"agent_actions":{"view_html":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD","download_json":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD.json","view_paper":"https://pith.science/paper/YG66L77O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00455&json=true","fetch_graph":"https://pith.science/api/pith-number/YG66L77OBCW2Z3E4DUWOCBWGPD/graph.json","fetch_events":"https://pith.science/api/pith-number/YG66L77OBCW2Z3E4DUWOCBWGPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD/action/storage_attestation","attest_author":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD/action/author_attestation","sign_citation":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD/action/citation_signature","submit_replication":"https://pith.science/pith/YG66L77OBCW2Z3E4DUWOCBWGPD/action/replication_record"}},"created_at":"2026-05-17T23:41:51.623273+00:00","updated_at":"2026-05-17T23:41:51.623273+00:00"}