{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SZRPR4CDBOIU26VRMFGQS56DSU","short_pith_number":"pith:SZRPR4CD","schema_version":"1.0","canonical_sha256":"9662f8f0430b914d7ab1614d0977c3953df4aa80543cafd8d7f77f24c0d1044b","source":{"kind":"arxiv","id":"1808.08097","version":1},"attestation_state":"computed","paper":{"title":"Memory Time Span in LSTMs for Multi-Speaker Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Van hamme, Jeroen Zegers","submitted_at":"2018-08-24T11:36:15Z","abstract_excerpt":"With deep learning approaches becoming state-of-the-art in many speech (as well as non-speech) related machine learning tasks, efforts are being taken to delve into the neural networks which are often considered as a black box. In this paper it is analyzed how recurrent neural network (RNNs) cope with temporal dependencies by determining the relevant memory time span in a long short-term memory (LSTM) cell. This is done by leaking the state variable with a controlled lifetime and evaluating the task performance. This technique can be used for any task to estimate the time span the LSTM exploit"},"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":"1808.08097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-24T11:36:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6d22549e951860136b3ed85f8890c8c622752d8d015052945bd7fe8a9af6d352","abstract_canon_sha256":"fe2213cbfa09f6a0eab108e76f4a8d0fef19158e85c70c8553bb33ba8941c331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:22.439885Z","signature_b64":"NslJeyh5AQCkohTiEew9lOYgIyodMHPW7ua7cMoj+U0c+MtVJebk0F8iM00O3Aqc5DEuhxv2dMh8s8D9Id81Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9662f8f0430b914d7ab1614d0977c3953df4aa80543cafd8d7f77f24c0d1044b","last_reissued_at":"2026-05-18T00:07:22.439273Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:22.439273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Time Span in LSTMs for Multi-Speaker Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugo Van hamme, Jeroen Zegers","submitted_at":"2018-08-24T11:36:15Z","abstract_excerpt":"With deep learning approaches becoming state-of-the-art in many speech (as well as non-speech) related machine learning tasks, efforts are being taken to delve into the neural networks which are often considered as a black box. In this paper it is analyzed how recurrent neural network (RNNs) cope with temporal dependencies by determining the relevant memory time span in a long short-term memory (LSTM) cell. This is done by leaking the state variable with a controlled lifetime and evaluating the task performance. This technique can be used for any task to estimate the time span the LSTM exploit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08097","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":"1808.08097","created_at":"2026-05-18T00:07:22.439409+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08097v1","created_at":"2026-05-18T00:07:22.439409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08097","created_at":"2026-05-18T00:07:22.439409+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZRPR4CDBOIU","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZRPR4CDBOIU26VR","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZRPR4CD","created_at":"2026-05-18T12:32:53.628368+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/SZRPR4CDBOIU26VRMFGQS56DSU","json":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU.json","graph_json":"https://pith.science/api/pith-number/SZRPR4CDBOIU26VRMFGQS56DSU/graph.json","events_json":"https://pith.science/api/pith-number/SZRPR4CDBOIU26VRMFGQS56DSU/events.json","paper":"https://pith.science/paper/SZRPR4CD"},"agent_actions":{"view_html":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU","download_json":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU.json","view_paper":"https://pith.science/paper/SZRPR4CD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08097&json=true","fetch_graph":"https://pith.science/api/pith-number/SZRPR4CDBOIU26VRMFGQS56DSU/graph.json","fetch_events":"https://pith.science/api/pith-number/SZRPR4CDBOIU26VRMFGQS56DSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU/action/storage_attestation","attest_author":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU/action/author_attestation","sign_citation":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU/action/citation_signature","submit_replication":"https://pith.science/pith/SZRPR4CDBOIU26VRMFGQS56DSU/action/replication_record"}},"created_at":"2026-05-18T00:07:22.439409+00:00","updated_at":"2026-05-18T00:07:22.439409+00:00"}