{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K3LMJOBYALVA2QDQMEFN5RZAMK","short_pith_number":"pith:K3LMJOBY","schema_version":"1.0","canonical_sha256":"56d6c4b83802ea0d4070610adec72062913d3ed9de2a5bf60972788748f2ab38","source":{"kind":"arxiv","id":"2407.09855","version":1},"attestation_state":"computed","paper":{"title":"Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kusum Lata, Sambit Sekhar, Sanskruti Mishra, Shakshi Panwar, Shantipriya Parida","submitted_at":"2024-07-13T11:29:20Z","abstract_excerpt":"Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic languages, is the availability of high-quality data for building foundation LLMs. In this paper, we are proposing a large pre-train dataset in Hindi useful for the Indic language Hindi. We have collected the data span across several domains including major dialects in Hindi. The dataset contains 1.28 billion Hindi tokens. We have explained our pipeline includin"},"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":"2407.09855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T11:29:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7c2a18e2324be9b242fee14b1786dcf6866d1aea58e8816fb1bcbf0ab2a3297","abstract_canon_sha256":"f7135d1255fa139ef3bffd92145ea6a753d07ecce9734540a6110094ad6974a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:35.747986Z","signature_b64":"g8+8PMBC7/xQGlp6JKmPQyKQHCgnt58QLzd7KkrjzNvVcAqTZxVihhOZzhaKMqUnMKdpCYCys9K43gM11TVEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d6c4b83802ea0d4070610adec72062913d3ed9de2a5bf60972788748f2ab38","last_reissued_at":"2026-07-05T08:43:35.747489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:35.747489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building pre-train LLM Dataset for the INDIC Languages: a case study on Hindi","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kusum Lata, Sambit Sekhar, Sanskruti Mishra, Shakshi Panwar, Shantipriya Parida","submitted_at":"2024-07-13T11:29:20Z","abstract_excerpt":"Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic languages, is the availability of high-quality data for building foundation LLMs. In this paper, we are proposing a large pre-train dataset in Hindi useful for the Indic language Hindi. We have collected the data span across several domains including major dialects in Hindi. The dataset contains 1.28 billion Hindi tokens. We have explained our pipeline includin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09855","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/2407.09855/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":"2407.09855","created_at":"2026-07-05T08:43:35.747545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09855v1","created_at":"2026-07-05T08:43:35.747545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09855","created_at":"2026-07-05T08:43:35.747545+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3LMJOBYALVA","created_at":"2026-07-05T08:43:35.747545+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3LMJOBYALVA2QDQ","created_at":"2026-07-05T08:43:35.747545+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3LMJOBY","created_at":"2026-07-05T08:43:35.747545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.04497","citing_title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK","json":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK.json","graph_json":"https://pith.science/api/pith-number/K3LMJOBYALVA2QDQMEFN5RZAMK/graph.json","events_json":"https://pith.science/api/pith-number/K3LMJOBYALVA2QDQMEFN5RZAMK/events.json","paper":"https://pith.science/paper/K3LMJOBY"},"agent_actions":{"view_html":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK","download_json":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK.json","view_paper":"https://pith.science/paper/K3LMJOBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09855&json=true","fetch_graph":"https://pith.science/api/pith-number/K3LMJOBYALVA2QDQMEFN5RZAMK/graph.json","fetch_events":"https://pith.science/api/pith-number/K3LMJOBYALVA2QDQMEFN5RZAMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK/action/storage_attestation","attest_author":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK/action/author_attestation","sign_citation":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK/action/citation_signature","submit_replication":"https://pith.science/pith/K3LMJOBYALVA2QDQMEFN5RZAMK/action/replication_record"}},"created_at":"2026-07-05T08:43:35.747545+00:00","updated_at":"2026-07-05T08:43:35.747545+00:00"}