{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EWNLD2NFSWHBADWJK7IWPEFTJS","short_pith_number":"pith:EWNLD2NF","canonical_record":{"source":{"id":"2211.14459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-26T02:39:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"801799a3a4281a8aa7b836698f9e5291f62dc2a67885809b67ade3c5efd45d19","abstract_canon_sha256":"fd77527b9f07edd32bb484eac3abdc76ef223d3c591c4b6a1d85c95642b44bc4"},"schema_version":"1.0"},"canonical_sha256":"259ab1e9a5958e100ec957d16790b34c99c6beb8646102e17ad8e9f63c0aaf86","source":{"kind":"arxiv","id":"2211.14459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14459","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14459v1","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14459","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"EWNLD2NFSWHB","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"EWNLD2NFSWHBADWJ","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"EWNLD2NF","created_at":"2026-07-05T05:19:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EWNLD2NFSWHBADWJK7IWPEFTJS","target":"record","payload":{"canonical_record":{"source":{"id":"2211.14459","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-26T02:39:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"801799a3a4281a8aa7b836698f9e5291f62dc2a67885809b67ade3c5efd45d19","abstract_canon_sha256":"fd77527b9f07edd32bb484eac3abdc76ef223d3c591c4b6a1d85c95642b44bc4"},"schema_version":"1.0"},"canonical_sha256":"259ab1e9a5958e100ec957d16790b34c99c6beb8646102e17ad8e9f63c0aaf86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:39.925096Z","signature_b64":"0XolmtyZfHldIS6gk+4MYXunmxRsjuR3WbbTq4dLqnxm6+P5ShIDnvmXMnKZFRUjDsQMwbdBxwbTAS7DR6GeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259ab1e9a5958e100ec957d16790b34c99c6beb8646102e17ad8e9f63c0aaf86","last_reissued_at":"2026-07-05T05:19:39.924734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:39.924734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.14459","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":"2026-07-05T05:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymuyi+s5KkN6gHCNu3s5/QzC6uE02iuuEg/kPUFMnr6NAkk9gF+BO8zt7bSnFVQtQlIe1PGReu5tKl0E8olxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:08:10.932428Z"},"content_sha256":"81a7395cc0f290048a8842fa4ca6747c78bb2593a41ad9b1a113225372200000","schema_version":"1.0","event_id":"sha256:81a7395cc0f290048a8842fa4ca6747c78bb2593a41ad9b1a113225372200000"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EWNLD2NFSWHBADWJK7IWPEFTJS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Gelbuk, Atnafu Lambebo Tonja, Grigori Sidorov, Mesay Gemeda Yigezu, Moein Shahiki Tash, Olga Kolesnikova","submitted_at":"2022-11-26T02:39:19Z","abstract_excerpt":"Using code-mixed data in natural language processing (NLP) research currently gets a lot of attention. Language identification of social media code-mixed text has been an interesting problem of study in recent years due to the advancement and influences of social media in communication. This paper presents the Instituto Polit\\'ecnico Nacional, Centro de Investigaci\\'on en Computaci\\'on (CIC) team's system description paper for the CoLI-Kanglish shared task at ICON2022. In this paper, we propose the use of a Transformer based model for word-level language identification in code-mixed Kannada En"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14459","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.14459/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:19:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2NXBtetTR89qILjKISwffE6zUxWfqYwj8fIehDXq7mSn83Z9D/q8GGg9jOfJgclKkY7Ux56kMeDIZsWaX0hCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:08:10.933342Z"},"content_sha256":"5215d6c2e61dccb45431cab2d6716b2edf23549fea8ca2fc193d78cd72449117","schema_version":"1.0","event_id":"sha256:5215d6c2e61dccb45431cab2d6716b2edf23549fea8ca2fc193d78cd72449117"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/bundle.json","state_url":"https://pith.science/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/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":"2026-08-19T04:08:10Z","links":{"resolver":"https://pith.science/pith/EWNLD2NFSWHBADWJK7IWPEFTJS","bundle":"https://pith.science/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/bundle.json","state":"https://pith.science/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWNLD2NFSWHBADWJK7IWPEFTJS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EWNLD2NFSWHBADWJK7IWPEFTJS","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":"fd77527b9f07edd32bb484eac3abdc76ef223d3c591c4b6a1d85c95642b44bc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-26T02:39:19Z","title_canon_sha256":"801799a3a4281a8aa7b836698f9e5291f62dc2a67885809b67ade3c5efd45d19"},"schema_version":"1.0","source":{"id":"2211.14459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14459","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14459v1","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14459","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"EWNLD2NFSWHB","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"EWNLD2NFSWHBADWJ","created_at":"2026-07-05T05:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"EWNLD2NF","created_at":"2026-07-05T05:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:5215d6c2e61dccb45431cab2d6716b2edf23549fea8ca2fc193d78cd72449117","target":"graph","created_at":"2026-07-05T05:19:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.14459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using code-mixed data in natural language processing (NLP) research currently gets a lot of attention. Language identification of social media code-mixed text has been an interesting problem of study in recent years due to the advancement and influences of social media in communication. This paper presents the Instituto Polit\\'ecnico Nacional, Centro de Investigaci\\'on en Computaci\\'on (CIC) team's system description paper for the CoLI-Kanglish shared task at ICON2022. In this paper, we propose the use of a Transformer based model for word-level language identification in code-mixed Kannada En","authors_text":"Alexander Gelbuk, Atnafu Lambebo Tonja, Grigori Sidorov, Mesay Gemeda Yigezu, Moein Shahiki Tash, Olga Kolesnikova","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-26T02:39:19Z","title":"Transformer-based Model for Word Level Language Identification in Code-mixed Kannada-English Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14459","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":"sha256:81a7395cc0f290048a8842fa4ca6747c78bb2593a41ad9b1a113225372200000","target":"record","created_at":"2026-07-05T05:19:39Z","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":"fd77527b9f07edd32bb484eac3abdc76ef223d3c591c4b6a1d85c95642b44bc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-26T02:39:19Z","title_canon_sha256":"801799a3a4281a8aa7b836698f9e5291f62dc2a67885809b67ade3c5efd45d19"},"schema_version":"1.0","source":{"id":"2211.14459","kind":"arxiv","version":1}},"canonical_sha256":"259ab1e9a5958e100ec957d16790b34c99c6beb8646102e17ad8e9f63c0aaf86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"259ab1e9a5958e100ec957d16790b34c99c6beb8646102e17ad8e9f63c0aaf86","first_computed_at":"2026-07-05T05:19:39.924734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:39.924734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0XolmtyZfHldIS6gk+4MYXunmxRsjuR3WbbTq4dLqnxm6+P5ShIDnvmXMnKZFRUjDsQMwbdBxwbTAS7DR6GeBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:39.925096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.14459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81a7395cc0f290048a8842fa4ca6747c78bb2593a41ad9b1a113225372200000","sha256:5215d6c2e61dccb45431cab2d6716b2edf23549fea8ca2fc193d78cd72449117"],"state_sha256":"04e7cbbc9b1614d7665f31dd1b116f1ca734598bfd44944639d010dfafc40d8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SToS3hzpoX4G9cVHr9U0eZy9TqlzNSV+jkms7pcpOdLBD5fXF4tHiCzNM61WM3JlyZpbOsLnLl2z4/u858iWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:08:10.938064Z","bundle_sha256":"4c0b6cfd2aa2a72b71d39c26b7e3101e751db29ee1945094402eada0b2ec602d"}}