{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VS2PFBURVYSQTBFWVHXBCOMO4T","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":"c58b2fa057cec9e0bdffcae640dbe3a19344970925c6ba7aad994c6fe27c2e19","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T16:49:59Z","title_canon_sha256":"c8565783d1b3535c3929322b2dd52e444d207efd663eab23488ad26a38808639"},"schema_version":"1.0","source":{"id":"2204.08398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08398","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08398v1","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08398","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"VS2PFBURVYSQ","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"VS2PFBURVYSQTBFW","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"VS2PFBUR","created_at":"2026-07-05T04:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:e3b1c0bb94f4520a01328f5752e7a8439cf36e0539d08166d6ba0b1ea3444e2e","target":"graph","created_at":"2026-07-05T04:15:25Z","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/2204.08398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching occurs when more than one language is mixed in a given sentence or a conversation. This phenomenon is more prominent on social media platforms and its adoption is increasing over time. Therefore code-mixed NLP has been extensively studied in the literature. As pre-trained transformer-based architectures are gaining popularity, we observe that real code-mixing data are scarce to pre-train large language models. We present L3Cube-HingCorpus, the first large-scale real Hindi-English code mixed data in a Roman script. It consists of 52.93M sentences and 1.04B tokens, scraped from Tw","authors_text":"Ravindra Nayak, Raviraj Joshi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T16:49:59Z","title":"L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08398","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:c9e0316c25757457d1b5765d913272582608a863a2b4e8e424521120c9138b3f","target":"record","created_at":"2026-07-05T04:15:25Z","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":"c58b2fa057cec9e0bdffcae640dbe3a19344970925c6ba7aad994c6fe27c2e19","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-18T16:49:59Z","title_canon_sha256":"c8565783d1b3535c3929322b2dd52e444d207efd663eab23488ad26a38808639"},"schema_version":"1.0","source":{"id":"2204.08398","kind":"arxiv","version":1}},"canonical_sha256":"acb4f28691ae250984b6a9ee11398ee4d034cf9330f43e10d6edb7541bfeaa80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acb4f28691ae250984b6a9ee11398ee4d034cf9330f43e10d6edb7541bfeaa80","first_computed_at":"2026-07-05T04:15:25.507917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:25.507917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vWoYIBjAyd7EfjK5JD2Gy5MeRdQzECmbzwNXP4TQHfy/xG/67cqZ2PVqt/iD2vBIrP0pjgmpFV25TVEFMOsNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:25.508465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9e0316c25757457d1b5765d913272582608a863a2b4e8e424521120c9138b3f","sha256:e3b1c0bb94f4520a01328f5752e7a8439cf36e0539d08166d6ba0b1ea3444e2e"],"state_sha256":"4348f5d070f4eaad1d167e041b998c786ae3628fdce24b8ca787f0b1746ab130"}