{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BGNOTKMUXTYQAPCMEHHVB67OP7","short_pith_number":"pith:BGNOTKMU","canonical_record":{"source":{"id":"1708.02182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-07T16:03:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e7dbc91cdde810fff496da1dc96a14d3ba5daf29bd51cc237904b1455b50a43f","abstract_canon_sha256":"5094005a94c09f55c343af9edd840dbf87328187b3249a8ac9ae21cbfcc61a4f"},"schema_version":"1.0"},"canonical_sha256":"099ae9a994bcf1003c4c21cf50fbee7fe9d8f329cd057549499922aa2448d034","source":{"kind":"arxiv","id":"1708.02182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02182","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02182v1","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02182","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"BGNOTKMUXTYQ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BGNOTKMUXTYQAPCM","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BGNOTKMU","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BGNOTKMUXTYQAPCMEHHVB67OP7","target":"record","payload":{"canonical_record":{"source":{"id":"1708.02182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-07T16:03:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"e7dbc91cdde810fff496da1dc96a14d3ba5daf29bd51cc237904b1455b50a43f","abstract_canon_sha256":"5094005a94c09f55c343af9edd840dbf87328187b3249a8ac9ae21cbfcc61a4f"},"schema_version":"1.0"},"canonical_sha256":"099ae9a994bcf1003c4c21cf50fbee7fe9d8f329cd057549499922aa2448d034","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:25.038185Z","signature_b64":"2swWtNvwWSFRvWeEMo3F9qheHYObw/dSFoUC3O3gp9J3G64zJen09fzBPw90sDOzH8xHvVxEbPO+nw+BbgLQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099ae9a994bcf1003c4c21cf50fbee7fe9d8f329cd057549499922aa2448d034","last_reissued_at":"2026-05-18T00:38:25.037552Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:25.037552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.02182","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCJ7zxrqRku2jBDcTQ7emxVC0swmlQgbnubIF3cllQX5dsJuenQdNTOulw+hfT3Ppw7WqQd+CMp6yLEVgzyaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:51:55.981920Z"},"content_sha256":"c5c9f651c3f4d4d9a3164c8e7101b34b2c7fd4886ac4d58dae25b36825083de1","schema_version":"1.0","event_id":"sha256:c5c9f651c3f4d4d9a3164c8e7101b34b2c7fd4886ac4d58dae25b36825083de1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BGNOTKMUXTYQAPCMEHHVB67OP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing and Optimizing LSTM Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Nitish Shirish Keskar, Richard Socher, Stephen Merity","submitted_at":"2017-08-07T16:03:44Z","abstract_excerpt":"Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this paper, we consider the specific problem of word-level language modeling and investigate strategies for regularizing and optimizing LSTM-based models. We propose the weight-dropped LSTM which uses DropConnect on hidden-to-hidden weights as a form of recurrent regularization. Further, we introduce NT-ASGD, a variant of the averaged stochastic gradient method, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02182","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rxVTznWE4oMaLE5IYtm13tuQKmmDD1jxjWUfkE0rskT7KwXeU6KoMbKKJyKMNVIRGXIlrNaCe30Ogp51G0xSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:51:55.982292Z"},"content_sha256":"6a10dca8a04e6b07e332bf51a9a82f42c6c772825610743ab7273aa188ad80a1","schema_version":"1.0","event_id":"sha256:6a10dca8a04e6b07e332bf51a9a82f42c6c772825610743ab7273aa188ad80a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/bundle.json","state_url":"https://pith.science/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T01:51:55Z","links":{"resolver":"https://pith.science/pith/BGNOTKMUXTYQAPCMEHHVB67OP7","bundle":"https://pith.science/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/bundle.json","state":"https://pith.science/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGNOTKMUXTYQAPCMEHHVB67OP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BGNOTKMUXTYQAPCMEHHVB67OP7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5094005a94c09f55c343af9edd840dbf87328187b3249a8ac9ae21cbfcc61a4f","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-07T16:03:44Z","title_canon_sha256":"e7dbc91cdde810fff496da1dc96a14d3ba5daf29bd51cc237904b1455b50a43f"},"schema_version":"1.0","source":{"id":"1708.02182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02182","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02182v1","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02182","created_at":"2026-05-18T00:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"BGNOTKMUXTYQ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BGNOTKMUXTYQAPCM","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BGNOTKMU","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:6a10dca8a04e6b07e332bf51a9a82f42c6c772825610743ab7273aa188ad80a1","target":"graph","created_at":"2026-05-18T00:38:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this paper, we consider the specific problem of word-level language modeling and investigate strategies for regularizing and optimizing LSTM-based models. We propose the weight-dropped LSTM which uses DropConnect on hidden-to-hidden weights as a form of recurrent regularization. Further, we introduce NT-ASGD, a variant of the averaged stochastic gradient method, whe","authors_text":"Nitish Shirish Keskar, Richard Socher, Stephen Merity","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-07T16:03:44Z","title":"Regularizing and Optimizing LSTM Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02182","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c5c9f651c3f4d4d9a3164c8e7101b34b2c7fd4886ac4d58dae25b36825083de1","target":"record","created_at":"2026-05-18T00:38:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5094005a94c09f55c343af9edd840dbf87328187b3249a8ac9ae21cbfcc61a4f","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-07T16:03:44Z","title_canon_sha256":"e7dbc91cdde810fff496da1dc96a14d3ba5daf29bd51cc237904b1455b50a43f"},"schema_version":"1.0","source":{"id":"1708.02182","kind":"arxiv","version":1}},"canonical_sha256":"099ae9a994bcf1003c4c21cf50fbee7fe9d8f329cd057549499922aa2448d034","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"099ae9a994bcf1003c4c21cf50fbee7fe9d8f329cd057549499922aa2448d034","first_computed_at":"2026-05-18T00:38:25.037552Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:25.037552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2swWtNvwWSFRvWeEMo3F9qheHYObw/dSFoUC3O3gp9J3G64zJen09fzBPw90sDOzH8xHvVxEbPO+nw+BbgLQCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:25.038185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.02182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5c9f651c3f4d4d9a3164c8e7101b34b2c7fd4886ac4d58dae25b36825083de1","sha256:6a10dca8a04e6b07e332bf51a9a82f42c6c772825610743ab7273aa188ad80a1"],"state_sha256":"f229d41b7322bf81ab6a6de790831acda2909d3fc51754bbd935d0a1226169fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"muFVWOXkf11qyH7p1zrkukLlTBfzKKxcwDQ84FX+n9SeqzHqXkjhvveBKvBJDKaf3OjD8ZRV/dmTuxqzDEl8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:51:55.984349Z","bundle_sha256":"0ec4da7f1ff7d235633a8c8ef5eac57958fa604f7c8bc59fcda111de770352df"}}