{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QFGRTPDTUUC7CFS4ULUHVOPN4Y","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":"9298227453dbe0445e9afe14d2bb49680910c08a9b9704b78eb1ecc1f7c93a38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-16T21:50:32Z","title_canon_sha256":"3de7bebb0b886283a670fcfc91026a056857e127a73f5b2a50e44701e9c4e326"},"schema_version":"1.0","source":{"id":"1904.07994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.07994","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"arxiv_version","alias_value":"1904.07994v2","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07994","created_at":"2026-05-17T23:47:01Z"},{"alias_kind":"pith_short_12","alias_value":"QFGRTPDTUUC7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QFGRTPDTUUC7CFS4","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QFGRTPDT","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:d0808237b8ab323dc7e7091f00f65f5d396b6e9e21dd79903979faa132e40e6e","target":"graph","created_at":"2026-05-17T23:47:01Z","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":"The use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a large number of rare words. Despite a steadily increasing interest in such subword-informed word representations, their systematic comparative analysis across typologically diverse languages and different tasks is still missing. In this work, we deliver such a study focusing on the variation of two crucial components required for subword-level integration into","authors_text":"Anna Korhonen, Ivan Vuli\\'c, Yi Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-16T21:50:32Z","title":"A Systematic Study of Leveraging Subword Information for Learning Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07994","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":"sha256:1754c0ceb470e5f9dc5b26a36b90f20862aa822932460e21c9b6a1d66d6496bb","target":"record","created_at":"2026-05-17T23:47:01Z","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":"9298227453dbe0445e9afe14d2bb49680910c08a9b9704b78eb1ecc1f7c93a38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-16T21:50:32Z","title_canon_sha256":"3de7bebb0b886283a670fcfc91026a056857e127a73f5b2a50e44701e9c4e326"},"schema_version":"1.0","source":{"id":"1904.07994","kind":"arxiv","version":2}},"canonical_sha256":"814d19bc73a505f1165ca2e87ab9ede62ae06d4456974ca233be6dde9b4357b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814d19bc73a505f1165ca2e87ab9ede62ae06d4456974ca233be6dde9b4357b6","first_computed_at":"2026-05-17T23:47:01.355657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:01.355657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWcDaSAgXJXs88FpvF6ESWSj3jfIIHQefGnSA7L1/KALeXFyt8e0wmKwmqxtWfORZzgGzEzwaa2moIhA86V3Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:01.356476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.07994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1754c0ceb470e5f9dc5b26a36b90f20862aa822932460e21c9b6a1d66d6496bb","sha256:d0808237b8ab323dc7e7091f00f65f5d396b6e9e21dd79903979faa132e40e6e"],"state_sha256":"1c7fe5587c62760be2fbb04806ab5e8422993a636a79985e1ea1783bee3f2259"}