{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2H346KUHCHCGPVSPLFHAT4IBUA","short_pith_number":"pith:2H346KUH","schema_version":"1.0","canonical_sha256":"d1f7cf2a8711c467d64f594e09f101a01ad818058c451653b979ecb2f26a7e30","source":{"kind":"arxiv","id":"1711.01804","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Croatian Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lukas Svoboda, Slobodan Beliga","submitted_at":"2017-11-06T09:40:41Z","abstract_excerpt":"Croatian is poorly resourced and highly inflected language from Slavic language family. Nowadays, research is focusing mostly on English. We created a new word analogy corpus based on the original English Word2vec word analogy corpus and added some of the specific linguistic aspects from Croatian language. Next, we created Croatian WordSim353 and RG65 corpora for a basic evaluation of word similarities. We compared created corpora on two popular word representation models, based on Word2Vec tool and fastText tool. Models has been trained on 1.37B tokens training data corpus and tested on a new"},"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":"1711.01804","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-06T09:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"af6d356ef6f2b21b90d1b4bab8eec27c00484d9c3f407fbc4a59d01a86850394","abstract_canon_sha256":"3dc7966130011fb470cfbd1e5ba1578267da6372897b9a2e34aa26c215ccfc78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:02.156470Z","signature_b64":"gFWU4tEuU3bLbNYCXkPsNMfIuGq8XueENm9FjfJaMTSc6g+nPXqkFJZmdgnkvWvnTQORuXMTCag/3MHFM7wcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1f7cf2a8711c467d64f594e09f101a01ad818058c451653b979ecb2f26a7e30","last_reissued_at":"2026-05-18T00:31:02.155762Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:02.155762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Croatian Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lukas Svoboda, Slobodan Beliga","submitted_at":"2017-11-06T09:40:41Z","abstract_excerpt":"Croatian is poorly resourced and highly inflected language from Slavic language family. Nowadays, research is focusing mostly on English. We created a new word analogy corpus based on the original English Word2vec word analogy corpus and added some of the specific linguistic aspects from Croatian language. Next, we created Croatian WordSim353 and RG65 corpora for a basic evaluation of word similarities. We compared created corpora on two popular word representation models, based on Word2Vec tool and fastText tool. Models has been trained on 1.37B tokens training data corpus and tested on a new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01804","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":"1711.01804","created_at":"2026-05-18T00:31:02.155871+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01804v2","created_at":"2026-05-18T00:31:02.155871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01804","created_at":"2026-05-18T00:31:02.155871+00:00"},{"alias_kind":"pith_short_12","alias_value":"2H346KUHCHCG","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2H346KUHCHCGPVSP","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2H346KUH","created_at":"2026-05-18T12:30:55.937587+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/2H346KUHCHCGPVSPLFHAT4IBUA","json":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA.json","graph_json":"https://pith.science/api/pith-number/2H346KUHCHCGPVSPLFHAT4IBUA/graph.json","events_json":"https://pith.science/api/pith-number/2H346KUHCHCGPVSPLFHAT4IBUA/events.json","paper":"https://pith.science/paper/2H346KUH"},"agent_actions":{"view_html":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA","download_json":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA.json","view_paper":"https://pith.science/paper/2H346KUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01804&json=true","fetch_graph":"https://pith.science/api/pith-number/2H346KUHCHCGPVSPLFHAT4IBUA/graph.json","fetch_events":"https://pith.science/api/pith-number/2H346KUHCHCGPVSPLFHAT4IBUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA/action/storage_attestation","attest_author":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA/action/author_attestation","sign_citation":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA/action/citation_signature","submit_replication":"https://pith.science/pith/2H346KUHCHCGPVSPLFHAT4IBUA/action/replication_record"}},"created_at":"2026-05-18T00:31:02.155871+00:00","updated_at":"2026-05-18T00:31:02.155871+00:00"}