{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LLIBEZ7UPIVGYIPYXUIRGODDHI","short_pith_number":"pith:LLIBEZ7U","canonical_record":{"source":{"id":"1701.03682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-13T14:20:06Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"82e15c77cc675d72eb3b03743a18e97a3292956020989417e6ff796829e8e8d2","abstract_canon_sha256":"2fbdae853ddf38e81aefa03b085043dd56d09c252c13573b1cb6dfeeaa3cd0be"},"schema_version":"1.0"},"canonical_sha256":"5ad01267f47a2a6c21f8bd111338633a1d1ab3a6c7fbaf23b32bde10cd7d484c","source":{"kind":"arxiv","id":"1701.03682","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03682","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03682v1","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03682","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"pith_short_12","alias_value":"LLIBEZ7UPIVG","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LLIBEZ7UPIVGYIPY","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LLIBEZ7U","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LLIBEZ7UPIVGYIPYXUIRGODDHI","target":"record","payload":{"canonical_record":{"source":{"id":"1701.03682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-13T14:20:06Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"82e15c77cc675d72eb3b03743a18e97a3292956020989417e6ff796829e8e8d2","abstract_canon_sha256":"2fbdae853ddf38e81aefa03b085043dd56d09c252c13573b1cb6dfeeaa3cd0be"},"schema_version":"1.0"},"canonical_sha256":"5ad01267f47a2a6c21f8bd111338633a1d1ab3a6c7fbaf23b32bde10cd7d484c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:54.156840Z","signature_b64":"b/H403iXUSY4z8hDGYqNEzMcASRKd48qJ/H+hD3kUSWDFWu3xwq/t6mj+x7Opnr/5vig5P2uOuxm/r/LwFagCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad01267f47a2a6c21f8bd111338633a1d1ab3a6c7fbaf23b32bde10cd7d484c","last_reissued_at":"2026-05-18T00:52:54.156116Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:54.156116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.03682","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":"2026-05-18T00:52:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iu09+YEtA8Cbn3hO01eVqbCnnzMS9+HJGqykpw4ZbPp/LcHTNzIzpyZVAH8zHnEf3cwrzLPHrmJZdgHY7GzuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:08:57.073059Z"},"content_sha256":"7a0d4e9a8ac130da4e8eab8384a3c8073ba6f91b3a30c4cb003366eda2978fd2","schema_version":"1.0","event_id":"sha256:7a0d4e9a8ac130da4e8eab8384a3c8073ba6f91b3a30c4cb003366eda2978fd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LLIBEZ7UPIVGYIPYXUIRGODDHI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LIDE: Language Identification from Text Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Arkajyoti Misra, Emrah Budur, Priyank Mathur","submitted_at":"2017-01-13T14:20:06Z","abstract_excerpt":"The increase in the use of microblogging came along with the rapid growth on short linguistic data. On the other hand deep learning is considered to be the new frontier to extract meaningful information out of large amount of raw data in an automated manner. In this study, we engaged these two emerging fields to come up with a robust language identifier on demand, namely Language Identification Engine (LIDE). As a result, we achieved 95.12% accuracy in Discriminating between Similar Languages (DSL) Shared Task 2015 dataset, which is comparable to the maximum reported accuracy of 95.54% achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03682","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":"2026-05-18T00:52:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"18IXZ/yN3R+YBgvzmsg6nkGgGoUKKm+OnifzOFC+TGyAoXOXc9P2N0h6xKmTAwm8jon9DS16UjFcGEDxU58kCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:08:57.073431Z"},"content_sha256":"ad03e82d4564333827299421706f1f08cf8d2460fd46b5cd9e3d09d1c8b3e88e","schema_version":"1.0","event_id":"sha256:ad03e82d4564333827299421706f1f08cf8d2460fd46b5cd9e3d09d1c8b3e88e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/bundle.json","state_url":"https://pith.science/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/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":"2026-06-29T13:08:57Z","links":{"resolver":"https://pith.science/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI","bundle":"https://pith.science/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/bundle.json","state":"https://pith.science/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLIBEZ7UPIVGYIPYXUIRGODDHI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LLIBEZ7UPIVGYIPYXUIRGODDHI","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":"2fbdae853ddf38e81aefa03b085043dd56d09c252c13573b1cb6dfeeaa3cd0be","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-13T14:20:06Z","title_canon_sha256":"82e15c77cc675d72eb3b03743a18e97a3292956020989417e6ff796829e8e8d2"},"schema_version":"1.0","source":{"id":"1701.03682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.03682","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"arxiv_version","alias_value":"1701.03682v1","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03682","created_at":"2026-05-18T00:52:54Z"},{"alias_kind":"pith_short_12","alias_value":"LLIBEZ7UPIVG","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LLIBEZ7UPIVGYIPY","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LLIBEZ7U","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:ad03e82d4564333827299421706f1f08cf8d2460fd46b5cd9e3d09d1c8b3e88e","target":"graph","created_at":"2026-05-18T00:52:54Z","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 increase in the use of microblogging came along with the rapid growth on short linguistic data. On the other hand deep learning is considered to be the new frontier to extract meaningful information out of large amount of raw data in an automated manner. In this study, we engaged these two emerging fields to come up with a robust language identifier on demand, namely Language Identification Engine (LIDE). As a result, we achieved 95.12% accuracy in Discriminating between Similar Languages (DSL) Shared Task 2015 dataset, which is comparable to the maximum reported accuracy of 95.54% achieve","authors_text":"Arkajyoti Misra, Emrah Budur, Priyank Mathur","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-13T14:20:06Z","title":"LIDE: Language Identification from Text Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03682","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":"sha256:7a0d4e9a8ac130da4e8eab8384a3c8073ba6f91b3a30c4cb003366eda2978fd2","target":"record","created_at":"2026-05-18T00:52:54Z","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":"2fbdae853ddf38e81aefa03b085043dd56d09c252c13573b1cb6dfeeaa3cd0be","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-13T14:20:06Z","title_canon_sha256":"82e15c77cc675d72eb3b03743a18e97a3292956020989417e6ff796829e8e8d2"},"schema_version":"1.0","source":{"id":"1701.03682","kind":"arxiv","version":1}},"canonical_sha256":"5ad01267f47a2a6c21f8bd111338633a1d1ab3a6c7fbaf23b32bde10cd7d484c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ad01267f47a2a6c21f8bd111338633a1d1ab3a6c7fbaf23b32bde10cd7d484c","first_computed_at":"2026-05-18T00:52:54.156116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:54.156116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b/H403iXUSY4z8hDGYqNEzMcASRKd48qJ/H+hD3kUSWDFWu3xwq/t6mj+x7Opnr/5vig5P2uOuxm/r/LwFagCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:54.156840Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.03682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a0d4e9a8ac130da4e8eab8384a3c8073ba6f91b3a30c4cb003366eda2978fd2","sha256:ad03e82d4564333827299421706f1f08cf8d2460fd46b5cd9e3d09d1c8b3e88e"],"state_sha256":"3a709aceec24c2c74c7887aa39ca09e8c7907a6ccbbe1669141f72fc964fcbb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nu+Plq8YtRNE1lc6AdChSSlgjWaJIpxYTYgsRxYkjJAc71TimKW2PTV7LzgOevWdmMAyqfRIgPltDZ9q/T0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T13:08:57.075528Z","bundle_sha256":"2d6f6554c5a3cf944da4deadc4a6e6307757b58b4f9fab60b4bcead084d1e182"}}