{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:K563AN545NPYA5VN47K5X622YH","short_pith_number":"pith:K563AN54","schema_version":"1.0","canonical_sha256":"577db037bceb5f8076ade7d5dbfb5ac1e5bd33ec36b95ca79993d30acce18b64","source":{"kind":"arxiv","id":"1610.03017","version":3},"attestation_state":"computed","paper":{"title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason Lee, Kyunghyun Cho, Thomas Hofmann","submitted_at":"2016-10-10T18:19:34Z","abstract_excerpt":"Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a s"},"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":"1610.03017","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-10T18:19:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9288b069c032319905dc21bb944832a98860bc2bd25d86fd3937916a44228335","abstract_canon_sha256":"274e3b6937fda414583e3fbcc19dd534cc76391203e96c34ea0f6075eabd5e33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:30.630334Z","signature_b64":"9UYo14Am6ugBze42XDwjxbHmgzs0+bOfeRRtJc/NEigbBlhAcu0Uvrh6S3f1PK4aH7yPzHo1JzIfRjL8LQzFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"577db037bceb5f8076ade7d5dbfb5ac1e5bd33ec36b95ca79993d30acce18b64","last_reissued_at":"2026-05-18T00:42:30.629765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:30.629765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jason Lee, Kyunghyun Cho, Thomas Hofmann","submitted_at":"2016-10-10T18:19:34Z","abstract_excerpt":"Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.03017","kind":"arxiv","version":3},"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":"1610.03017","created_at":"2026-05-18T00:42:30.629861+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.03017v3","created_at":"2026-05-18T00:42:30.629861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.03017","created_at":"2026-05-18T00:42:30.629861+00:00"},{"alias_kind":"pith_short_12","alias_value":"K563AN545NPY","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"K563AN545NPYA5VN","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"K563AN54","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.01300","citing_title":"Learning to Reformulate the Queries on the WEB","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH","json":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH.json","graph_json":"https://pith.science/api/pith-number/K563AN545NPYA5VN47K5X622YH/graph.json","events_json":"https://pith.science/api/pith-number/K563AN545NPYA5VN47K5X622YH/events.json","paper":"https://pith.science/paper/K563AN54"},"agent_actions":{"view_html":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH","download_json":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH.json","view_paper":"https://pith.science/paper/K563AN54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.03017&json=true","fetch_graph":"https://pith.science/api/pith-number/K563AN545NPYA5VN47K5X622YH/graph.json","fetch_events":"https://pith.science/api/pith-number/K563AN545NPYA5VN47K5X622YH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH/action/storage_attestation","attest_author":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH/action/author_attestation","sign_citation":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH/action/citation_signature","submit_replication":"https://pith.science/pith/K563AN545NPYA5VN47K5X622YH/action/replication_record"}},"created_at":"2026-05-18T00:42:30.629861+00:00","updated_at":"2026-05-18T00:42:30.629861+00:00"}