{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AP64NI7KIUJMDZBRDRLSHAPH4I","short_pith_number":"pith:AP64NI7K","canonical_record":{"source":{"id":"1906.05506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T06:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"c6470f43f01fa2910db7eabcb323991421ef3137ca1d9393ac4877d2cb0671ae","abstract_canon_sha256":"a8718a4e80b4af19aa6348146836fb4ef9940bf7fc3b610e63d6c2415293b6b4"},"schema_version":"1.0"},"canonical_sha256":"03fdc6a3ea4512c1e4311c572381e7e22791ccfa54b759c008ce00e9e7649060","source":{"kind":"arxiv","id":"1906.05506","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05506","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05506v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05506","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"AP64NI7KIUJM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AP64NI7KIUJMDZBR","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AP64NI7K","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AP64NI7KIUJMDZBRDRLSHAPH4I","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T06:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"c6470f43f01fa2910db7eabcb323991421ef3137ca1d9393ac4877d2cb0671ae","abstract_canon_sha256":"a8718a4e80b4af19aa6348146836fb4ef9940bf7fc3b610e63d6c2415293b6b4"},"schema_version":"1.0"},"canonical_sha256":"03fdc6a3ea4512c1e4311c572381e7e22791ccfa54b759c008ce00e9e7649060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:25.200152Z","signature_b64":"64CaDSXPboTguI6f/5kW0UNu92nEGHThQCzsnWV8VVYmmP5HA6/FXDnxIx9sk0OjlHJ6OqIH5mXMNEZv2W6CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03fdc6a3ea4512c1e4311c572381e7e22791ccfa54b759c008ce00e9e7649060","last_reissued_at":"2026-05-17T23:43:25.199702Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:25.199702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05506","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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M5UIyP03l7sPbWMbv03ejcD8AUdJHBNJGcF+yoTnemi7AL+kje1u8sxJw2YOx4EMaCqW/BCv7r0AXOQb1yTKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:12:54.517548Z"},"content_sha256":"62dd4a2ba9986019a15e1e7d3535927db05109582308336e698ec8c5f5e726bb","schema_version":"1.0","event_id":"sha256:62dd4a2ba9986019a15e1e7d3535927db05109582308336e698ec8c5f5e726bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AP64NI7KIUJMDZBRDRLSHAPH4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Character n-gram Embeddings to Improve RNN Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Suzuki, Masaaki Nagata, Sho Takase","submitted_at":"2019-06-13T06:52:45Z","abstract_excerpt":"This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our proposed method constructs word embeddings from character n-gram embeddings and combines them with ordinary word embeddings. We demonstrate that the proposed method achieves the best perplexities on the language modeling datasets: Penn Treebank, WikiText-2, and WikiText-103. Moreover, we conduct experiments on application tasks: machine translation and headl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05506","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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iEG9TsBRbKYd9pXFI/CtdSE/FkzWpyH5HzLqx7F6ePYwpjKliDRXGxJqlHvJmTwLDJhXjQCGL5xhHiwtny1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:12:54.517901Z"},"content_sha256":"b4ce2126cbe0971eff0443e831fb7f74f9ad940f29e66e048058415172d0e1ba","schema_version":"1.0","event_id":"sha256:b4ce2126cbe0971eff0443e831fb7f74f9ad940f29e66e048058415172d0e1ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/bundle.json","state_url":"https://pith.science/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/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":"2026-05-30T06:12:54Z","links":{"resolver":"https://pith.science/pith/AP64NI7KIUJMDZBRDRLSHAPH4I","bundle":"https://pith.science/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/bundle.json","state":"https://pith.science/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AP64NI7KIUJMDZBRDRLSHAPH4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AP64NI7KIUJMDZBRDRLSHAPH4I","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":"a8718a4e80b4af19aa6348146836fb4ef9940bf7fc3b610e63d6c2415293b6b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T06:52:45Z","title_canon_sha256":"c6470f43f01fa2910db7eabcb323991421ef3137ca1d9393ac4877d2cb0671ae"},"schema_version":"1.0","source":{"id":"1906.05506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05506","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05506v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05506","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"AP64NI7KIUJM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AP64NI7KIUJMDZBR","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AP64NI7K","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:b4ce2126cbe0971eff0443e831fb7f74f9ad940f29e66e048058415172d0e1ba","target":"graph","created_at":"2026-05-17T23:43:25Z","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":"This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our proposed method constructs word embeddings from character n-gram embeddings and combines them with ordinary word embeddings. We demonstrate that the proposed method achieves the best perplexities on the language modeling datasets: Penn Treebank, WikiText-2, and WikiText-103. Moreover, we conduct experiments on application tasks: machine translation and headl","authors_text":"Jun Suzuki, Masaaki Nagata, Sho Takase","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T06:52:45Z","title":"Character n-gram Embeddings to Improve RNN Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05506","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":"sha256:62dd4a2ba9986019a15e1e7d3535927db05109582308336e698ec8c5f5e726bb","target":"record","created_at":"2026-05-17T23:43:25Z","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":"a8718a4e80b4af19aa6348146836fb4ef9940bf7fc3b610e63d6c2415293b6b4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T06:52:45Z","title_canon_sha256":"c6470f43f01fa2910db7eabcb323991421ef3137ca1d9393ac4877d2cb0671ae"},"schema_version":"1.0","source":{"id":"1906.05506","kind":"arxiv","version":1}},"canonical_sha256":"03fdc6a3ea4512c1e4311c572381e7e22791ccfa54b759c008ce00e9e7649060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03fdc6a3ea4512c1e4311c572381e7e22791ccfa54b759c008ce00e9e7649060","first_computed_at":"2026-05-17T23:43:25.199702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:25.199702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64CaDSXPboTguI6f/5kW0UNu92nEGHThQCzsnWV8VVYmmP5HA6/FXDnxIx9sk0OjlHJ6OqIH5mXMNEZv2W6CBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:25.200152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62dd4a2ba9986019a15e1e7d3535927db05109582308336e698ec8c5f5e726bb","sha256:b4ce2126cbe0971eff0443e831fb7f74f9ad940f29e66e048058415172d0e1ba"],"state_sha256":"5d35a8d0b688649dae0fe0da44761cf255b2234b0ce223a3d026187303fdc8dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZgXa7gYtg9GILIgpx7Ldib62YEAlcoboe8qPVhodoyYccQsSb+mVtCpnrc7bnaZ6BOoVc1qpfedGIKxUAqYwCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:12:54.520086Z","bundle_sha256":"644030778769402fc1c628e6176ecf09ed5a5fed759706fec846622c0bd4f0f0"}}