{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HIEOVGAUUIOQA4UJAV4JECTZCG","short_pith_number":"pith:HIEOVGAU","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"},"canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","source":{"kind":"arxiv","id":"1807.03108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03108","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03108v1","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03108","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"HIEOVGAUUIOQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HIEOVGAUUIOQA4UJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HIEOVGAU","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HIEOVGAUUIOQA4UJAV4JECTZCG","target":"record","payload":{"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"},"canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","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"},"source_kind":"arxiv","source_id":"1807.03108","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVq5ZBktWihsAh1PuEynCMJ5WsFap8Iop9XU9ZwqNTNvGQmMH/ufU6IT7fTGg5PJUrztyMGqQtAAVxn6CadJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:29:06.254249Z"},"content_sha256":"461f840b45eef14b4adb3191d759bd693871d94e738bb8e9a9a2487fa9e59cdb","schema_version":"1.0","event_id":"sha256:461f840b45eef14b4adb3191d759bd693871d94e738bb8e9a9a2487fa9e59cdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HIEOVGAUUIOQA4UJAV4JECTZCG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:11:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5V8bdNirx66mr9mrdjJygR7wDG6jz3nJsqU9hRPWcVyOuf37hA18bMbkKHT4n1tpscgcmph7aquGJP/Pe+bCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:29:06.254926Z"},"content_sha256":"6e43f63166b80f37fdf0e47b5410307b56502771597dadc23c79b1ca83f9e995","schema_version":"1.0","event_id":"sha256:6e43f63166b80f37fdf0e47b5410307b56502771597dadc23c79b1ca83f9e995"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/bundle.json","state_url":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T02:29:06Z","links":{"resolver":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG","bundle":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/bundle.json","state":"https://pith.science/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIEOVGAUUIOQA4UJAV4JECTZCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HIEOVGAUUIOQA4UJAV4JECTZCG","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":"b984b46142ccb49e3cfbcee6f5d478ac1632599ec30a791711525e4d3da25907","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-09T13:26:44Z","title_canon_sha256":"1217a3e15ee07fcc1989476b4e6e41bc5c0ddbc1da39cac9f08ed76d20b57443"},"schema_version":"1.0","source":{"id":"1807.03108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03108","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03108v1","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03108","created_at":"2026-05-18T00:11:12Z"},{"alias_kind":"pith_short_12","alias_value":"HIEOVGAUUIOQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HIEOVGAUUIOQA4UJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HIEOVGAU","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:6e43f63166b80f37fdf0e47b5410307b56502771597dadc23c79b1ca83f9e995","target":"graph","created_at":"2026-05-18T00:11:12Z","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":"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.","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Santanu Pal, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-09T13:26:44Z","title":"Discriminating between Indo-Aryan Languages Using SVM Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03108","kind":"arxiv","version":1},"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":"sha256:461f840b45eef14b4adb3191d759bd693871d94e738bb8e9a9a2487fa9e59cdb","target":"record","created_at":"2026-05-18T00:11:12Z","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":"b984b46142ccb49e3cfbcee6f5d478ac1632599ec30a791711525e4d3da25907","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-09T13:26:44Z","title_canon_sha256":"1217a3e15ee07fcc1989476b4e6e41bc5c0ddbc1da39cac9f08ed76d20b57443"},"schema_version":"1.0","source":{"id":"1807.03108","kind":"arxiv","version":1}},"canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a08ea9814a21d0072890578920a79118ae1af23d0734ab8cef8c5ed615efe46","first_computed_at":"2026-05-18T00:11:12.862669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:12.862669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PFMojge6v9ZXj+nYiBNagGtwfAESEubl+J1VeIGEsWwo8RfvSj6OKIowTKM0bYbUSnHPV4xQ76T4cZx+ccKkCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:12.863463Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:461f840b45eef14b4adb3191d759bd693871d94e738bb8e9a9a2487fa9e59cdb","sha256:6e43f63166b80f37fdf0e47b5410307b56502771597dadc23c79b1ca83f9e995"],"state_sha256":"21e945f66656887fae8d783a2effc1806f8c3294da140f9432bcc12ffe622315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ds/AH6srFp3ggd53M46G2nQPnqmYENLiLAKMkP2RhGixqI3c1SLMHErEQ+RAS+5Lg3Lk/HcXZRDyFAU0dZ24CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:29:06.258038Z","bundle_sha256":"315f6d8c66ce56762541619cac9127e588e3689f68e036cb45f8cb043c72bc9b"}}