{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BTREPEONLREGPKUXZOTDOOFI7K","short_pith_number":"pith:BTREPEON","schema_version":"1.0","canonical_sha256":"0ce24791cd5c4867aa97cba63738a8fa9684e90c0a93ed36ed167ed08291c55b","source":{"kind":"arxiv","id":"2206.07988","version":1},"attestation_state":"computed","paper":{"title":"PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Goindani, Anmol Goel, Manish Shrivastava, Naman Ahuja, Ponnurangam Kumaraguru, Prashant Kodali, Tanmay Sachan","submitted_at":"2022-06-16T08:00:42Z","abstract_excerpt":"Code-Mixing is a phenomenon of mixing two or more languages in a speech event and is prevalent in multilingual societies. Given the low-resource nature of Code-Mixing, machine generation of code-mixed text is a prevalent approach for data augmentation. However, evaluating the quality of such machine generated code-mixed text is an open problem. In our submission to HinglishEval, a shared-task collocated with INLG2022, we attempt to build models factors that impact the quality of synthetically generated code-mix text by predicting ratings for code-mix quality."},"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":"2206.07988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-06-16T08:00:42Z","cross_cats_sorted":[],"title_canon_sha256":"86c111df8726cd10cbd311e243dd7e603f860509d7540ba3ada9fc2d09059068","abstract_canon_sha256":"702207ecee17979283abe23d0343053daf29d14bde5b9c7ff2df47aa32ed2071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:20.953855Z","signature_b64":"fb04vKLkShoQ0OzD24oGkxPWOjSOk3ysEXX/L0GqwQQ7TPswN9W+jj9Vv723goUegL+Jsc28ePTeSv7OHTyvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ce24791cd5c4867aa97cba63738a8fa9684e90c0a93ed36ed167ed08291c55b","last_reissued_at":"2026-07-05T04:32:20.953365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:20.953365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akshay Goindani, Anmol Goel, Manish Shrivastava, Naman Ahuja, Ponnurangam Kumaraguru, Prashant Kodali, Tanmay Sachan","submitted_at":"2022-06-16T08:00:42Z","abstract_excerpt":"Code-Mixing is a phenomenon of mixing two or more languages in a speech event and is prevalent in multilingual societies. Given the low-resource nature of Code-Mixing, machine generation of code-mixed text is a prevalent approach for data augmentation. However, evaluating the quality of such machine generated code-mixed text is an open problem. In our submission to HinglishEval, a shared-task collocated with INLG2022, we attempt to build models factors that impact the quality of synthetically generated code-mix text by predicting ratings for code-mix quality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07988","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/2206.07988/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.07988","created_at":"2026-07-05T04:32:20.953428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07988v1","created_at":"2026-07-05T04:32:20.953428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07988","created_at":"2026-07-05T04:32:20.953428+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTREPEONLREG","created_at":"2026-07-05T04:32:20.953428+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTREPEONLREGPKUX","created_at":"2026-07-05T04:32:20.953428+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTREPEON","created_at":"2026-07-05T04:32:20.953428+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/BTREPEONLREGPKUXZOTDOOFI7K","json":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K.json","graph_json":"https://pith.science/api/pith-number/BTREPEONLREGPKUXZOTDOOFI7K/graph.json","events_json":"https://pith.science/api/pith-number/BTREPEONLREGPKUXZOTDOOFI7K/events.json","paper":"https://pith.science/paper/BTREPEON"},"agent_actions":{"view_html":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K","download_json":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K.json","view_paper":"https://pith.science/paper/BTREPEON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07988&json=true","fetch_graph":"https://pith.science/api/pith-number/BTREPEONLREGPKUXZOTDOOFI7K/graph.json","fetch_events":"https://pith.science/api/pith-number/BTREPEONLREGPKUXZOTDOOFI7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K/action/storage_attestation","attest_author":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K/action/author_attestation","sign_citation":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K/action/citation_signature","submit_replication":"https://pith.science/pith/BTREPEONLREGPKUXZOTDOOFI7K/action/replication_record"}},"created_at":"2026-07-05T04:32:20.953428+00:00","updated_at":"2026-07-05T04:32:20.953428+00:00"}