{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FTQGSHUDQ5D5HLUV6LXOT65FCD","short_pith_number":"pith:FTQGSHUD","schema_version":"1.0","canonical_sha256":"2ce0691e838747d3ae95f2eee9fba510cba8e1cdef38cf7a54c8d042cd84f67f","source":{"kind":"arxiv","id":"1708.01009","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Activation Regularization for Language RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Richard Socher, Stephen Merity","submitted_at":"2017-08-03T05:53:53Z","abstract_excerpt":"Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve performance. Both of these can require substantial modifications to the machine learning model or to the underlying RNN configurations. We revisit traditional regularization techniques, specifically L2 regularization on RNN activations and slowness regularization over successive hidden states, to improve the performance of RNNs on the task of language modeling. Both "},"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":"1708.01009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-03T05:53:53Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"6a597fb46181b2dcf47969adb562746eede6ddd438b17ab16f988c75ca3aa34e","abstract_canon_sha256":"f6c0870219a3651ba701ab3c58c20ccdcf768c66af212032463e8f659de33283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:40.843693Z","signature_b64":"SLL1UBCcv7MM8kYlvYaLsxsHFq5OZdsL+HciBRlZWIWxfusxFwvs6kJDg+rDGspV/BfrjJ7S4UWWbIoX8ZnNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ce0691e838747d3ae95f2eee9fba510cba8e1cdef38cf7a54c8d042cd84f67f","last_reissued_at":"2026-05-18T00:38:40.843030Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:40.843030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Activation Regularization for Language RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Bryan McCann, Richard Socher, Stephen Merity","submitted_at":"2017-08-03T05:53:53Z","abstract_excerpt":"Recurrent neural networks (RNNs) serve as a fundamental building block for many sequence tasks across natural language processing. Recent research has focused on recurrent dropout techniques or custom RNN cells in order to improve performance. Both of these can require substantial modifications to the machine learning model or to the underlying RNN configurations. We revisit traditional regularization techniques, specifically L2 regularization on RNN activations and slowness regularization over successive hidden states, to improve the performance of RNNs on the task of language modeling. Both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01009","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":"1708.01009","created_at":"2026-05-18T00:38:40.843115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01009v1","created_at":"2026-05-18T00:38:40.843115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01009","created_at":"2026-05-18T00:38:40.843115+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTQGSHUDQ5D5","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTQGSHUDQ5D5HLUV","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTQGSHUD","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01476","citing_title":"ConsistentFeature: A Plug-and-Play Component for Neural Network Regularization","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD","json":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD.json","graph_json":"https://pith.science/api/pith-number/FTQGSHUDQ5D5HLUV6LXOT65FCD/graph.json","events_json":"https://pith.science/api/pith-number/FTQGSHUDQ5D5HLUV6LXOT65FCD/events.json","paper":"https://pith.science/paper/FTQGSHUD"},"agent_actions":{"view_html":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD","download_json":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD.json","view_paper":"https://pith.science/paper/FTQGSHUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01009&json=true","fetch_graph":"https://pith.science/api/pith-number/FTQGSHUDQ5D5HLUV6LXOT65FCD/graph.json","fetch_events":"https://pith.science/api/pith-number/FTQGSHUDQ5D5HLUV6LXOT65FCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD/action/storage_attestation","attest_author":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD/action/author_attestation","sign_citation":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD/action/citation_signature","submit_replication":"https://pith.science/pith/FTQGSHUDQ5D5HLUV6LXOT65FCD/action/replication_record"}},"created_at":"2026-05-18T00:38:40.843115+00:00","updated_at":"2026-05-18T00:38:40.843115+00:00"}