{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:H4WPICDWFDCY4E5TD7RMZHIZ3J","short_pith_number":"pith:H4WPICDW","schema_version":"1.0","canonical_sha256":"3f2cf4087628c58e13b31fe2cc9d19da4f0b02947febe8672f7d578f44b4c5db","source":{"kind":"arxiv","id":"1511.06303","version":2},"attestation_state":"computed","paper":{"title":"Alternative structures for character-level RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Armand Joulin, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2015-11-19T18:46:21Z","abstract_excerpt":"Recurrent neural networks are convenient and efficient models for language modeling. However, when applied on the level of characters instead of words, they suffer from several problems. In order to successfully model long-term dependencies, the hidden representation needs to be large. This in turn implies higher computational costs, which can become prohibitive in practice. We propose two alternative structural modifications to the classical RNN model. The first one consists on conditioning the character level representation on the previous word representation. The other one uses the characte"},"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":"1511.06303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:46:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ba71e8a41a646d212a9af0b02dc8114d03ccc3843e07494080eb2c9a6e6252b1","abstract_canon_sha256":"0641c43b40c7d8779e9ca24f414021716c258be8509bfa26e38be69e692b64bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:09.112191Z","signature_b64":"iGXDmh4eQPn/I8NeDLWCAkB+nm/i7b7bjn6IQmglRfZiacLfRPP89H/cCMOVKdZZCgW3vRMXRpgwroDoq74HCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f2cf4087628c58e13b31fe2cc9d19da4f0b02947febe8672f7d578f44b4c5db","last_reissued_at":"2026-05-18T01:26:09.111438Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:09.111438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alternative structures for character-level RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Armand Joulin, Piotr Bojanowski, Tomas Mikolov","submitted_at":"2015-11-19T18:46:21Z","abstract_excerpt":"Recurrent neural networks are convenient and efficient models for language modeling. However, when applied on the level of characters instead of words, they suffer from several problems. In order to successfully model long-term dependencies, the hidden representation needs to be large. This in turn implies higher computational costs, which can become prohibitive in practice. We propose two alternative structural modifications to the classical RNN model. The first one consists on conditioning the character level representation on the previous word representation. The other one uses the characte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06303","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1511.06303","created_at":"2026-05-18T01:26:09.111546+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06303v2","created_at":"2026-05-18T01:26:09.111546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06303","created_at":"2026-05-18T01:26:09.111546+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4WPICDWFDCY","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4WPICDWFDCY4E5T","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4WPICDW","created_at":"2026-05-18T12:29:22.688609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J","json":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J.json","graph_json":"https://pith.science/api/pith-number/H4WPICDWFDCY4E5TD7RMZHIZ3J/graph.json","events_json":"https://pith.science/api/pith-number/H4WPICDWFDCY4E5TD7RMZHIZ3J/events.json","paper":"https://pith.science/paper/H4WPICDW"},"agent_actions":{"view_html":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J","download_json":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J.json","view_paper":"https://pith.science/paper/H4WPICDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06303&json=true","fetch_graph":"https://pith.science/api/pith-number/H4WPICDWFDCY4E5TD7RMZHIZ3J/graph.json","fetch_events":"https://pith.science/api/pith-number/H4WPICDWFDCY4E5TD7RMZHIZ3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J/action/storage_attestation","attest_author":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J/action/author_attestation","sign_citation":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J/action/citation_signature","submit_replication":"https://pith.science/pith/H4WPICDWFDCY4E5TD7RMZHIZ3J/action/replication_record"}},"created_at":"2026-05-18T01:26:09.111546+00:00","updated_at":"2026-05-18T01:26:09.111546+00:00"}