{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6RNBS22K7HJKXNHGWTZFOG65PJ","short_pith_number":"pith:6RNBS22K","schema_version":"1.0","canonical_sha256":"f45a196b4af9d2abb4e6b4f2571bdd7a6a2ee0d0fb54afa7c1a6d56c49bee460","source":{"kind":"arxiv","id":"2606.26112","version":1},"attestation_state":"computed","paper":{"title":"From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhara Gorasiya, Malhar Kulkarni, Pushpak Bhattacharya, Siddhant Hitesh Mantri","submitted_at":"2026-05-21T03:16:27Z","abstract_excerpt":"Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through 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":"2606.26112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T03:16:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3681be983c63515b4a49c5d1c16aa01a7eeb8ad8bcb13657092a5d32db6ffb0","abstract_canon_sha256":"2aa6cbe6acf7989cb69c18d33a788f9bd1b8c166fb27b3bf622ce0a15167359c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:26.526710Z","signature_b64":"nUXFUJiSpHyRzrlId+FjZ0yKIRZc9JgfU67B26aI0PoGdpps47S5ABsNtP8MXQYg+Vmj4EPG+UQpS7d4RwxDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f45a196b4af9d2abb4e6b4f2571bdd7a6a2ee0d0fb54afa7c1a6d56c49bee460","last_reissued_at":"2026-06-26T00:15:26.526228Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:26.526228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Lexicon to AI: A Structured-Data Pipeline for Specialized Conversational Systems in Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dhara Gorasiya, Malhar Kulkarni, Pushpak Bhattacharya, Siddhant Hitesh Mantri","submitted_at":"2026-05-21T03:16:27Z","abstract_excerpt":"Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26112","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/2606.26112/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":"2606.26112","created_at":"2026-06-26T00:15:26.526288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26112v1","created_at":"2026-06-26T00:15:26.526288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26112","created_at":"2026-06-26T00:15:26.526288+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RNBS22K7HJK","created_at":"2026-06-26T00:15:26.526288+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RNBS22K7HJKXNHG","created_at":"2026-06-26T00:15:26.526288+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RNBS22K","created_at":"2026-06-26T00:15:26.526288+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/6RNBS22K7HJKXNHGWTZFOG65PJ","json":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ.json","graph_json":"https://pith.science/api/pith-number/6RNBS22K7HJKXNHGWTZFOG65PJ/graph.json","events_json":"https://pith.science/api/pith-number/6RNBS22K7HJKXNHGWTZFOG65PJ/events.json","paper":"https://pith.science/paper/6RNBS22K"},"agent_actions":{"view_html":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ","download_json":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ.json","view_paper":"https://pith.science/paper/6RNBS22K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26112&json=true","fetch_graph":"https://pith.science/api/pith-number/6RNBS22K7HJKXNHGWTZFOG65PJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6RNBS22K7HJKXNHGWTZFOG65PJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ/action/storage_attestation","attest_author":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ/action/author_attestation","sign_citation":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ/action/citation_signature","submit_replication":"https://pith.science/pith/6RNBS22K7HJKXNHGWTZFOG65PJ/action/replication_record"}},"created_at":"2026-06-26T00:15:26.526288+00:00","updated_at":"2026-06-26T00:15:26.526288+00:00"}