{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LVOQXJYGMCLK2YAFI6THAJAHH7","short_pith_number":"pith:LVOQXJYG","schema_version":"1.0","canonical_sha256":"5d5d0ba7066096ad600547a67024073fd82b017642010672eb89a9eb20f78cd2","source":{"kind":"arxiv","id":"2302.09685","version":1},"attestation_state":"computed","paper":{"title":"Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ankan Mullick, G Sai Chaitanya, Ishani Mondal, Pawan Goyal, R Raghav, Sourjyadip Ray","submitted_at":"2023-02-19T22:53:03Z","abstract_excerpt":"Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare. To assess the current status of various state-of-the-art language models in healthcare, this paper studies the problem by initially proposing two different Healthcare datasets, Indian Healthcare Query Intent-WebMD and 1mg (IHQID-WebMD and IHQID-1mg) and one real world Indian hospital query data in English and multiple Indic languages (Hindi, Bengali, Tamil, Telugu, Marathi and Gujarati) which are annotated w"},"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":"2302.09685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-02-19T22:53:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"96c6dfd91349a25cee7fd1eb7abfe656883943003c3a5bf0242c4f5a67374583","abstract_canon_sha256":"22611890d92e9136bb44a1b4a8973d98ed09c6d331fd5026b507064e1c1871e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:56.982262Z","signature_b64":"KX1JIzuVukMlNwXNOtFWLS947sEsTcDk6STNo1U8HB5/D4sRGaSY62N3csPp4/PsCfyCcVrqp2mKZtgZcFstBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d5d0ba7066096ad600547a67024073fd82b017642010672eb89a9eb20f78cd2","last_reissued_at":"2026-07-05T05:54:56.981874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:56.981874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ankan Mullick, G Sai Chaitanya, Ishani Mondal, Pawan Goyal, R Raghav, Sourjyadip Ray","submitted_at":"2023-02-19T22:53:03Z","abstract_excerpt":"Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare. To assess the current status of various state-of-the-art language models in healthcare, this paper studies the problem by initially proposing two different Healthcare datasets, Indian Healthcare Query Intent-WebMD and 1mg (IHQID-WebMD and IHQID-1mg) and one real world Indian hospital query data in English and multiple Indic languages (Hindi, Bengali, Tamil, Telugu, Marathi and Gujarati) which are annotated w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09685","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/2302.09685/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":"2302.09685","created_at":"2026-07-05T05:54:56.981923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09685v1","created_at":"2026-07-05T05:54:56.981923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09685","created_at":"2026-07-05T05:54:56.981923+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVOQXJYGMCLK","created_at":"2026-07-05T05:54:56.981923+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVOQXJYGMCLK2YAF","created_at":"2026-07-05T05:54:56.981923+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVOQXJYG","created_at":"2026-07-05T05:54:56.981923+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/LVOQXJYGMCLK2YAFI6THAJAHH7","json":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7.json","graph_json":"https://pith.science/api/pith-number/LVOQXJYGMCLK2YAFI6THAJAHH7/graph.json","events_json":"https://pith.science/api/pith-number/LVOQXJYGMCLK2YAFI6THAJAHH7/events.json","paper":"https://pith.science/paper/LVOQXJYG"},"agent_actions":{"view_html":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7","download_json":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7.json","view_paper":"https://pith.science/paper/LVOQXJYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09685&json=true","fetch_graph":"https://pith.science/api/pith-number/LVOQXJYGMCLK2YAFI6THAJAHH7/graph.json","fetch_events":"https://pith.science/api/pith-number/LVOQXJYGMCLK2YAFI6THAJAHH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7/action/storage_attestation","attest_author":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7/action/author_attestation","sign_citation":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7/action/citation_signature","submit_replication":"https://pith.science/pith/LVOQXJYGMCLK2YAFI6THAJAHH7/action/replication_record"}},"created_at":"2026-07-05T05:54:56.981923+00:00","updated_at":"2026-07-05T05:54:56.981923+00:00"}