{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RWELO46L76MPVY6MFETJ2XWVQX","short_pith_number":"pith:RWELO46L","schema_version":"1.0","canonical_sha256":"8d88b773cbff98fae3cc29269d5ed585d18005bbbfd3c581d057323a35a6c839","source":{"kind":"arxiv","id":"1412.7753","version":2},"attestation_state":"computed","paper":{"title":"Learning Longer Memory in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Armand Joulin, Marc'Aurelio Ranzato, Michael Mathieu, Sumit Chopra, Tomas Mikolov","submitted_at":"2014-12-24T20:58:18Z","abstract_excerpt":"Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this paper, we show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. We encourage some of the hidden units to change their s"},"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":"1412.7753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2014-12-24T20:58:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"408fa665fab1b0e356ea2013d247e3f888ab2ab96b5ce006a107ba24c7a31989","abstract_canon_sha256":"39c5c492c4796ce7c0aecc6b9c0993eeb7699a8c803d0245b354abe39e27029b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:32.827282Z","signature_b64":"1HxX1L+WF0JoSZOGIQS8AyYXra/tPxQX8DElUGUzJvcDlgNJFwZb+Bg9lUyY6/FPCRUH3yXxUciNZVXKksQdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d88b773cbff98fae3cc29269d5ed585d18005bbbfd3c581d057323a35a6c839","last_reissued_at":"2026-05-18T02:18:32.826901Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:32.826901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Longer Memory in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Armand Joulin, Marc'Aurelio Ranzato, Michael Mathieu, Sumit Chopra, Tomas Mikolov","submitted_at":"2014-12-24T20:58:18Z","abstract_excerpt":"Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due to the so-called vanishing gradient problem. In this paper, we show that learning longer term patterns in real data, such as in natural language, is perfectly possible using gradient descent. This is achieved by using a slight structural modification of the simple recurrent neural network architecture. We encourage some of the hidden units to change their s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.7753","kind":"arxiv","version":2},"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":"1412.7753","created_at":"2026-05-18T02:18:32.826961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.7753v2","created_at":"2026-05-18T02:18:32.826961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.7753","created_at":"2026-05-18T02:18:32.826961+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWELO46L76MP","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWELO46L76MPVY6M","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWELO46L","created_at":"2026-05-18T12:28:46.137349+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/RWELO46L76MPVY6MFETJ2XWVQX","json":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX.json","graph_json":"https://pith.science/api/pith-number/RWELO46L76MPVY6MFETJ2XWVQX/graph.json","events_json":"https://pith.science/api/pith-number/RWELO46L76MPVY6MFETJ2XWVQX/events.json","paper":"https://pith.science/paper/RWELO46L"},"agent_actions":{"view_html":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX","download_json":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX.json","view_paper":"https://pith.science/paper/RWELO46L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.7753&json=true","fetch_graph":"https://pith.science/api/pith-number/RWELO46L76MPVY6MFETJ2XWVQX/graph.json","fetch_events":"https://pith.science/api/pith-number/RWELO46L76MPVY6MFETJ2XWVQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX/action/storage_attestation","attest_author":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX/action/author_attestation","sign_citation":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX/action/citation_signature","submit_replication":"https://pith.science/pith/RWELO46L76MPVY6MFETJ2XWVQX/action/replication_record"}},"created_at":"2026-05-18T02:18:32.826961+00:00","updated_at":"2026-05-18T02:18:32.826961+00:00"}