{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A6H2RNQDOW42BDLOWMQBNGOXVM","short_pith_number":"pith:A6H2RNQD","canonical_record":{"source":{"id":"1902.02380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-06T19:49:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c8f00b919dfc3a80e86eab061e526bc1bc2ebd54c2729194e2e2b94c8a279dc","abstract_canon_sha256":"23f5dccccc36a64073090ed4b59b31dc70035c1830c1bbaadaf0a41828284116"},"schema_version":"1.0"},"canonical_sha256":"078fa8b60375b9a08d6eb3201699d7ab05ea319355f3fc01465f220be7e30beb","source":{"kind":"arxiv","id":"1902.02380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02380","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02380v1","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02380","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"pith_short_12","alias_value":"A6H2RNQDOW42","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A6H2RNQDOW42BDLO","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A6H2RNQD","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A6H2RNQDOW42BDLOWMQBNGOXVM","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-06T19:49:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c8f00b919dfc3a80e86eab061e526bc1bc2ebd54c2729194e2e2b94c8a279dc","abstract_canon_sha256":"23f5dccccc36a64073090ed4b59b31dc70035c1830c1bbaadaf0a41828284116"},"schema_version":"1.0"},"canonical_sha256":"078fa8b60375b9a08d6eb3201699d7ab05ea319355f3fc01465f220be7e30beb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:08.864939Z","signature_b64":"Q6HWzpDjkbZfvBiUsKuq9o3ZTXU0Pmt6s8zXSEn/LDhDysM7P5A23RZuywVC6E3oVZCedtMj78MWLYJu8DcuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"078fa8b60375b9a08d6eb3201699d7ab05ea319355f3fc01465f220be7e30beb","last_reissued_at":"2026-05-17T23:49:08.864299Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:08.864299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02380","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":"2026-05-17T23:49:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tqovo54OCn+UjwYFEKFgfK5CIOYw3IkH9Y8w73dicRVK1x+X5bAB6i6jYkCNa0PyNvBTBqggwWYh9YMB5P5JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T01:34:57.069723Z"},"content_sha256":"8418f689a70d010b5cb4e747eebf0c22223d4e7dece3ad68935c9eea60273e2d","schema_version":"1.0","event_id":"sha256:8418f689a70d010b5cb4e747eebf0c22223d4e7dece3ad68935c9eea60273e2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A6H2RNQDOW42BDLOWMQBNGOXVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression of Recurrent Neural Networks for Efficient Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrey V. Savchenko, Artem M. Grachev, Dmitry I. Ignatov","submitted_at":"2019-02-06T19:49:22Z","abstract_excerpt":"Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications. In this paper we consider several compression techniques for recurrent neural networks including Long-Short Term Memory models. We make particular attention to the high-dimensional output problem caused by the very large vocabulary size. We focus on effective compression methods in the context of their exploitation on devices: pruning, quantization, and matri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02380","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":"2026-05-17T23:49:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnCF81uw/GaOM9bMPez8kDU+XE35Gj+0Jcfg5zlXgNiai6xsjWb8sxtr+L5//3qjASbsdXpDGcGlfkYyo84IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T01:34:57.070378Z"},"content_sha256":"e60927d37a085da9a72f8ceb45da50b56b3df113fdb2b1a2276350b2664a3f1b","schema_version":"1.0","event_id":"sha256:e60927d37a085da9a72f8ceb45da50b56b3df113fdb2b1a2276350b2664a3f1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/bundle.json","state_url":"https://pith.science/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/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":"2026-07-04T01:34:57Z","links":{"resolver":"https://pith.science/pith/A6H2RNQDOW42BDLOWMQBNGOXVM","bundle":"https://pith.science/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/bundle.json","state":"https://pith.science/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6H2RNQDOW42BDLOWMQBNGOXVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A6H2RNQDOW42BDLOWMQBNGOXVM","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":"23f5dccccc36a64073090ed4b59b31dc70035c1830c1bbaadaf0a41828284116","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-06T19:49:22Z","title_canon_sha256":"9c8f00b919dfc3a80e86eab061e526bc1bc2ebd54c2729194e2e2b94c8a279dc"},"schema_version":"1.0","source":{"id":"1902.02380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02380","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02380v1","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02380","created_at":"2026-05-17T23:49:08Z"},{"alias_kind":"pith_short_12","alias_value":"A6H2RNQDOW42","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"A6H2RNQDOW42BDLO","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"A6H2RNQD","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:e60927d37a085da9a72f8ceb45da50b56b3df113fdb2b1a2276350b2664a3f1b","target":"graph","created_at":"2026-05-17T23:49:08Z","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 have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications. In this paper we consider several compression techniques for recurrent neural networks including Long-Short Term Memory models. We make particular attention to the high-dimensional output problem caused by the very large vocabulary size. We focus on effective compression methods in the context of their exploitation on devices: pruning, quantization, and matri","authors_text":"Andrey V. Savchenko, Artem M. Grachev, Dmitry I. Ignatov","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-06T19:49:22Z","title":"Compression of Recurrent Neural Networks for Efficient Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02380","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":"sha256:8418f689a70d010b5cb4e747eebf0c22223d4e7dece3ad68935c9eea60273e2d","target":"record","created_at":"2026-05-17T23:49:08Z","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":"23f5dccccc36a64073090ed4b59b31dc70035c1830c1bbaadaf0a41828284116","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-06T19:49:22Z","title_canon_sha256":"9c8f00b919dfc3a80e86eab061e526bc1bc2ebd54c2729194e2e2b94c8a279dc"},"schema_version":"1.0","source":{"id":"1902.02380","kind":"arxiv","version":1}},"canonical_sha256":"078fa8b60375b9a08d6eb3201699d7ab05ea319355f3fc01465f220be7e30beb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"078fa8b60375b9a08d6eb3201699d7ab05ea319355f3fc01465f220be7e30beb","first_computed_at":"2026-05-17T23:49:08.864299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:08.864299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q6HWzpDjkbZfvBiUsKuq9o3ZTXU0Pmt6s8zXSEn/LDhDysM7P5A23RZuywVC6E3oVZCedtMj78MWLYJu8DcuDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:08.864939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8418f689a70d010b5cb4e747eebf0c22223d4e7dece3ad68935c9eea60273e2d","sha256:e60927d37a085da9a72f8ceb45da50b56b3df113fdb2b1a2276350b2664a3f1b"],"state_sha256":"93c196669a15615cd616518895f5fae8c82d33fd7330e114ffc2f937f6573c91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mo6XH82OLxlhEMkfJny27MIpkvmn+Znxu+R/KGK4TxM5D0cyDN3XBS0Kw35/CHRVQ9NBQfK1vSG9sKjNoTU6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T01:34:57.073997Z","bundle_sha256":"d06ec82c06979f243e737f5e38bc8a30cd373fad617fb22038c4b6985319957a"}}