{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HIEOVGAUUIOQA4UJAV4JECTZCG","short_pith_number":"pith:HIEOVGAU","schema_version":"1.0","canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","source":{"kind":"arxiv","id":"1807.03108","version":1},"attestation_state":"computed","paper":{"title":"Discriminating between Indo-Aryan Languages Using SVM Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Santanu Pal, Shervin Malmasi","submitted_at":"2018-07-09T13:26:44Z","abstract_excerpt":"In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual features and combine the output of single classifiers to maximize performance. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88:95% F1 score and it was ranked 3rd out of 8 teams."},"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":"1807.03108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-09T13:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"1217a3e15ee07fcc1989476b4e6e41bc5c0ddbc1da39cac9f08ed76d20b57443","abstract_canon_sha256":"b984b46142ccb49e3cfbcee6f5d478ac1632599ec30a791711525e4d3da25907"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:12.863463Z","signature_b64":"PFMojge6v9ZXj+nYiBNagGtwfAESEubl+J1VeIGEsWwo8RfvSj6OKIowTKM0bYbUSnHPV4xQ76T4cZx+ccKkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","last_reissued_at":"2026-05-18T00:11:12.862669Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:12.862669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discriminating between Indo-Aryan Languages Using SVM Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Santanu Pal, Shervin Malmasi","submitted_at":"2018-07-09T13:26:44Z","abstract_excerpt":"In this paper we present a system based on SVM ensembles trained on characters and words to discriminate between five similar languages of the Indo-Aryan family: Hindi, Braj Bhasha, Awadhi, Bhojpuri, and Magahi. We investigate the performance of individual features and combine the output of single classifiers to maximize performance. The system competed in the Indo-Aryan Language Identification (ILI) shared task organized within the VarDial Evaluation Campaign 2018. Our best entry in the competition, named ILIdentification, scored 88:95% F1 score and it was ranked 3rd out of 8 teams."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03108","kind":"arxiv","version":1},"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":"1807.03108","created_at":"2026-05-18T00:11:12.862814+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03108v1","created_at":"2026-05-18T00:11:12.862814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03108","created_at":"2026-05-18T00:11:12.862814+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIEOVGAUUIOQ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIEOVGAUUIOQA4UJ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIEOVGAU","created_at":"2026-05-18T12:32:28.185984+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/HIEOVGAUUIOQA4UJAV4JECTZCG","json":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG.json","graph_json":"https://pith.science/api/pith-number/HIEOVGAUUIOQA4UJAV4JECTZCG/graph.json","events_json":"https://pith.science/api/pith-number/HIEOVGAUUIOQA4UJAV4JECTZCG/events.json","paper":"https://pith.science/paper/HIEOVGAU"},"agent_actions":{"view_html":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG","download_json":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG.json","view_paper":"https://pith.science/paper/HIEOVGAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03108&json=true","fetch_graph":"https://pith.science/api/pith-number/HIEOVGAUUIOQA4UJAV4JECTZCG/graph.json","fetch_events":"https://pith.science/api/pith-number/HIEOVGAUUIOQA4UJAV4JECTZCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/action/storage_attestation","attest_author":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/action/author_attestation","sign_citation":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/action/citation_signature","submit_replication":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/action/replication_record"}},"created_at":"2026-05-18T00:11:12.862814+00:00","updated_at":"2026-05-18T00:11:12.862814+00:00"}