{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AF2GQ7OMQSAHKUZPDG2SYBHMXR","short_pith_number":"pith:AF2GQ7OM","schema_version":"1.0","canonical_sha256":"0174687dcc848075532f19b52c04ecbc571c5663c793cc2171cd275427e93748","source":{"kind":"arxiv","id":"1912.10454","version":1},"attestation_state":"computed","paper":{"title":"On the Initialization of Long Short-Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Akshay Pai, Lauge Sorensen, Mads Nielsen, Marc Modat, M. Jorge Cardoso, Mostafa Mehdipour Ghazi, Sebastien Ourselin","submitted_at":"2019-12-22T14:19:43Z","abstract_excerpt":"Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM) networks. It is based on a normalized random initialization of the network weights that aims at preserving the variance of the network input and output in the same range. The method is applied to standard LSTMs for univariate time series regression and to LSTMs robust to missing values for multivariate disease progression modeling. The results show that in all cas"},"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":"1912.10454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-22T14:19:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fe291e4a4650ccc159b60366a08244d33a10bcbe07d8d746dadc609a0443d1c6","abstract_canon_sha256":"711e5dba08a02e7c97186a9eb7d03414f0f443b574cea0189024aa21e51afb2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:50.175364Z","signature_b64":"IBjLZt3HFndBJ34EtuD+QXPGJfpZdTLjOOguUIVCUqEWem6TgCOz8U5UVSu7WifIJStp+PA9pKU9YFS7azxnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0174687dcc848075532f19b52c04ecbc571c5663c793cc2171cd275427e93748","last_reissued_at":"2026-07-05T00:27:50.174979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:50.174979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Initialization of Long Short-Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Akshay Pai, Lauge Sorensen, Mads Nielsen, Marc Modat, M. Jorge Cardoso, Mostafa Mehdipour Ghazi, Sebastien Ourselin","submitted_at":"2019-12-22T14:19:43Z","abstract_excerpt":"Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM) networks. It is based on a normalized random initialization of the network weights that aims at preserving the variance of the network input and output in the same range. The method is applied to standard LSTMs for univariate time series regression and to LSTMs robust to missing values for multivariate disease progression modeling. The results show that in all cas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.10454","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/1912.10454/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":"1912.10454","created_at":"2026-07-05T00:27:50.175038+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.10454v1","created_at":"2026-07-05T00:27:50.175038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.10454","created_at":"2026-07-05T00:27:50.175038+00:00"},{"alias_kind":"pith_short_12","alias_value":"AF2GQ7OMQSAH","created_at":"2026-07-05T00:27:50.175038+00:00"},{"alias_kind":"pith_short_16","alias_value":"AF2GQ7OMQSAHKUZP","created_at":"2026-07-05T00:27:50.175038+00:00"},{"alias_kind":"pith_short_8","alias_value":"AF2GQ7OM","created_at":"2026-07-05T00:27:50.175038+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/AF2GQ7OMQSAHKUZPDG2SYBHMXR","json":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR.json","graph_json":"https://pith.science/api/pith-number/AF2GQ7OMQSAHKUZPDG2SYBHMXR/graph.json","events_json":"https://pith.science/api/pith-number/AF2GQ7OMQSAHKUZPDG2SYBHMXR/events.json","paper":"https://pith.science/paper/AF2GQ7OM"},"agent_actions":{"view_html":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR","download_json":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR.json","view_paper":"https://pith.science/paper/AF2GQ7OM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.10454&json=true","fetch_graph":"https://pith.science/api/pith-number/AF2GQ7OMQSAHKUZPDG2SYBHMXR/graph.json","fetch_events":"https://pith.science/api/pith-number/AF2GQ7OMQSAHKUZPDG2SYBHMXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR/action/storage_attestation","attest_author":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR/action/author_attestation","sign_citation":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR/action/citation_signature","submit_replication":"https://pith.science/pith/AF2GQ7OMQSAHKUZPDG2SYBHMXR/action/replication_record"}},"created_at":"2026-07-05T00:27:50.175038+00:00","updated_at":"2026-07-05T00:27:50.175038+00:00"}