{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:L5JDU755IEO6WESYPERV4EK7VA","short_pith_number":"pith:L5JDU755","canonical_record":{"source":{"id":"1609.03777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-13T11:41:48Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"20bfbceed00808e5a6aa51ea2e6c0ee6e4af6c53c5b432cb1ec90f2fdb73cc49","abstract_canon_sha256":"9b1782dfed127f2821b6ad8ebbf13c07642b7b4e689516e1d9ede07049677b74"},"schema_version":"1.0"},"canonical_sha256":"5f523a7fbd411deb125879235e115fa8324a5fd36e3dfc29b7ac1a6a78e8a1d9","source":{"kind":"arxiv","id":"1609.03777","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03777","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03777v2","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03777","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"L5JDU755IEO6","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"L5JDU755IEO6WESY","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"L5JDU755","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:L5JDU755IEO6WESYPERV4EK7VA","target":"record","payload":{"canonical_record":{"source":{"id":"1609.03777","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-13T11:41:48Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"20bfbceed00808e5a6aa51ea2e6c0ee6e4af6c53c5b432cb1ec90f2fdb73cc49","abstract_canon_sha256":"9b1782dfed127f2821b6ad8ebbf13c07642b7b4e689516e1d9ede07049677b74"},"schema_version":"1.0"},"canonical_sha256":"5f523a7fbd411deb125879235e115fa8324a5fd36e3dfc29b7ac1a6a78e8a1d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:33.961727Z","signature_b64":"PzLv2n+V9e37zOpn/nBklTMFB3nKU97FtaJpyAge9nMBxKqE3MHYANl0Zgie3hRNyECXXCKh4UdyM3BMQGnzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f523a7fbd411deb125879235e115fa8324a5fd36e3dfc29b7ac1a6a78e8a1d9","last_reissued_at":"2026-05-18T00:51:33.961219Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:33.961219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.03777","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4y7DQAxw14caVRFaQUTxyjdIRpsVEc1XyItENRpOO2Pzzq1X0mICovGDUJxQntuVxftDDmHxlk2l6HDEe1+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:12:52.480983Z"},"content_sha256":"d93aa50c6e43c5443776d5c6e6ab8029f57bb8368e4841536c302d405c1e8a72","schema_version":"1.0","event_id":"sha256:d93aa50c6e43c5443776d5c6e6ab8029f57bb8368e4841536c302d405c1e8a72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:L5JDU755IEO6WESYPERV4EK7VA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Character-Level Language Modeling with Hierarchical Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.LG","authors_text":"Kyuyeon Hwang, Wonyong Sung","submitted_at":"2016-09-13T11:41:48Z","abstract_excerpt":"Recurrent neural network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs need to consider longer history of tokens to properly predict the next one. We address this problem by proposing hierarchical RNN architectures, which consist of multiple modules with different timescales. Despite the multi-timescale structures, the input and output layers operate with the character-level clock, which allows the existing RNN CLM t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03777","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:51:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vUWzLY+rE6cShY/5KWEG+Pp7rCBx4EpFrEXoxl2Ph25J3ltzb5jkCAIhZfRGpuOfA9rlIS7YG5/PIhBSGwrqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T00:12:52.481369Z"},"content_sha256":"081078f9e9182ce1919f7a6a8d54dbca696a5ca8c66cec02fdf92e80388214b7","schema_version":"1.0","event_id":"sha256:081078f9e9182ce1919f7a6a8d54dbca696a5ca8c66cec02fdf92e80388214b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5JDU755IEO6WESYPERV4EK7VA/bundle.json","state_url":"https://pith.science/pith/L5JDU755IEO6WESYPERV4EK7VA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5JDU755IEO6WESYPERV4EK7VA/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":"2026-06-12T00:12:52Z","links":{"resolver":"https://pith.science/pith/L5JDU755IEO6WESYPERV4EK7VA","bundle":"https://pith.science/pith/L5JDU755IEO6WESYPERV4EK7VA/bundle.json","state":"https://pith.science/pith/L5JDU755IEO6WESYPERV4EK7VA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5JDU755IEO6WESYPERV4EK7VA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:L5JDU755IEO6WESYPERV4EK7VA","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":"9b1782dfed127f2821b6ad8ebbf13c07642b7b4e689516e1d9ede07049677b74","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-13T11:41:48Z","title_canon_sha256":"20bfbceed00808e5a6aa51ea2e6c0ee6e4af6c53c5b432cb1ec90f2fdb73cc49"},"schema_version":"1.0","source":{"id":"1609.03777","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.03777","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"arxiv_version","alias_value":"1609.03777v2","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.03777","created_at":"2026-05-18T00:51:33Z"},{"alias_kind":"pith_short_12","alias_value":"L5JDU755IEO6","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"L5JDU755IEO6WESY","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"L5JDU755","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:081078f9e9182ce1919f7a6a8d54dbca696a5ca8c66cec02fdf92e80388214b7","target":"graph","created_at":"2026-05-18T00:51:33Z","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 network (RNN) based character-level language models (CLMs) are extremely useful for modeling out-of-vocabulary words by nature. However, their performance is generally much worse than the word-level language models (WLMs), since CLMs need to consider longer history of tokens to properly predict the next one. We address this problem by proposing hierarchical RNN architectures, which consist of multiple modules with different timescales. Despite the multi-timescale structures, the input and output layers operate with the character-level clock, which allows the existing RNN CLM t","authors_text":"Kyuyeon Hwang, Wonyong Sung","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-13T11:41:48Z","title":"Character-Level Language Modeling with Hierarchical Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.03777","kind":"arxiv","version":2},"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:d93aa50c6e43c5443776d5c6e6ab8029f57bb8368e4841536c302d405c1e8a72","target":"record","created_at":"2026-05-18T00:51:33Z","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":"9b1782dfed127f2821b6ad8ebbf13c07642b7b4e689516e1d9ede07049677b74","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-13T11:41:48Z","title_canon_sha256":"20bfbceed00808e5a6aa51ea2e6c0ee6e4af6c53c5b432cb1ec90f2fdb73cc49"},"schema_version":"1.0","source":{"id":"1609.03777","kind":"arxiv","version":2}},"canonical_sha256":"5f523a7fbd411deb125879235e115fa8324a5fd36e3dfc29b7ac1a6a78e8a1d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f523a7fbd411deb125879235e115fa8324a5fd36e3dfc29b7ac1a6a78e8a1d9","first_computed_at":"2026-05-18T00:51:33.961219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:33.961219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PzLv2n+V9e37zOpn/nBklTMFB3nKU97FtaJpyAge9nMBxKqE3MHYANl0Zgie3hRNyECXXCKh4UdyM3BMQGnzBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:33.961727Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.03777","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d93aa50c6e43c5443776d5c6e6ab8029f57bb8368e4841536c302d405c1e8a72","sha256:081078f9e9182ce1919f7a6a8d54dbca696a5ca8c66cec02fdf92e80388214b7"],"state_sha256":"887a60c22932c0464ea4f459ef61506de835d0180a80a1ecd7bfb502f742804f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+IDms4rYqDeruBgWmdq7bewNsAKn6oKPSiu3eGT0I6zSlhmrxdCiSX8QN83S6q456QiTEtvPr62qkrSXigTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T00:12:52.484454Z","bundle_sha256":"8aebd03578344fbf236ffcfb2857b93f120f6cb650e6b87a6100488b338707ac"}}