{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DQQDFZABMCU5FFDYDEHZNZE4WB","short_pith_number":"pith:DQQDFZAB","schema_version":"1.0","canonical_sha256":"1c2032e40160a9d29478190f96e49cb079f1f480228004bd29a08e5b4aa6d6a6","source":{"kind":"arxiv","id":"2004.05051","version":2},"attestation_state":"computed","paper":{"title":"A New Dataset for Natural Language Inference from Code-mixed Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Monojit Choudhury, Sandipan Dandapat, Simran Khanuja, Sunayana Sitaram","submitted_at":"2020-04-10T14:32:01Z","abstract_excerpt":"Natural Language Inference (NLI) is the task of inferring the logical relationship, typically entailment or contradiction, between a premise and hypothesis. Code-mixing is the use of more than one language in the same conversation or utterance, and is prevalent in multilingual communities all over the world. In this paper, we present the first dataset for code-mixed NLI, in which both the premises and hypotheses are in code-mixed Hindi-English. We use data from Hindi movies (Bollywood) as premises, and crowd-source hypotheses from Hindi-English bilinguals. We conduct a pilot annotation study a"},"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":"2004.05051","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T14:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"bf8d498c8bd6716d4a5419a4c6b8fa1071e04667d01c388658bea39eb61a9b51","abstract_canon_sha256":"9e098e0bd80022fee1ab151e7f059dd943239a1d1b9447913230388340f8a1ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:34.423664Z","signature_b64":"A9QdEguNHzEsoR/tmqjPII6PXESIWrDAJ1VjCBiPiozvuNJYLt6Td71UJGf9A/ZVCuTFGqrZim/usaIYHjKwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c2032e40160a9d29478190f96e49cb079f1f480228004bd29a08e5b4aa6d6a6","last_reissued_at":"2026-07-05T00:54:34.423193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:34.423193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Dataset for Natural Language Inference from Code-mixed Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Monojit Choudhury, Sandipan Dandapat, Simran Khanuja, Sunayana Sitaram","submitted_at":"2020-04-10T14:32:01Z","abstract_excerpt":"Natural Language Inference (NLI) is the task of inferring the logical relationship, typically entailment or contradiction, between a premise and hypothesis. Code-mixing is the use of more than one language in the same conversation or utterance, and is prevalent in multilingual communities all over the world. In this paper, we present the first dataset for code-mixed NLI, in which both the premises and hypotheses are in code-mixed Hindi-English. We use data from Hindi movies (Bollywood) as premises, and crowd-source hypotheses from Hindi-English bilinguals. We conduct a pilot annotation study a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05051","kind":"arxiv","version":2},"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/2004.05051/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":"2004.05051","created_at":"2026-07-05T00:54:34.423251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05051v2","created_at":"2026-07-05T00:54:34.423251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05051","created_at":"2026-07-05T00:54:34.423251+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQQDFZABMCU5","created_at":"2026-07-05T00:54:34.423251+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQQDFZABMCU5FFDY","created_at":"2026-07-05T00:54:34.423251+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQQDFZAB","created_at":"2026-07-05T00:54:34.423251+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/DQQDFZABMCU5FFDYDEHZNZE4WB","json":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB.json","graph_json":"https://pith.science/api/pith-number/DQQDFZABMCU5FFDYDEHZNZE4WB/graph.json","events_json":"https://pith.science/api/pith-number/DQQDFZABMCU5FFDYDEHZNZE4WB/events.json","paper":"https://pith.science/paper/DQQDFZAB"},"agent_actions":{"view_html":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB","download_json":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB.json","view_paper":"https://pith.science/paper/DQQDFZAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05051&json=true","fetch_graph":"https://pith.science/api/pith-number/DQQDFZABMCU5FFDYDEHZNZE4WB/graph.json","fetch_events":"https://pith.science/api/pith-number/DQQDFZABMCU5FFDYDEHZNZE4WB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB/action/storage_attestation","attest_author":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB/action/author_attestation","sign_citation":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB/action/citation_signature","submit_replication":"https://pith.science/pith/DQQDFZABMCU5FFDYDEHZNZE4WB/action/replication_record"}},"created_at":"2026-07-05T00:54:34.423251+00:00","updated_at":"2026-07-05T00:54:34.423251+00:00"}