{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DO2XBQFGOQ2T7G2TOOUHFTR45I","short_pith_number":"pith:DO2XBQFG","schema_version":"1.0","canonical_sha256":"1bb570c0a674353f9b5373a872ce3cea19675aa1b5c26745fb19cd1bb3293ea9","source":{"kind":"arxiv","id":"2506.01615","version":2},"attestation_state":"computed","paper":{"title":"IndicRAGSuite: Large-Scale Datasets and a Benchmark for Indian Language RAG Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Pasunuti Prasanjith, Prathmesh B More, Raj Dabre","submitted_at":"2025-06-02T12:55:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems enable language models to access relevant information and generate accurate, well-grounded, and contextually informed responses. However, for Indian languages, the development of high-quality RAG systems is hindered by the lack of two critical resources: (1) evaluation benchmarks for retrieval and generation tasks, and (2) large-scale training datasets for multilingual retrieval. Most existing benchmarks and datasets are centered around English or high-resource languages, making it difficult to extend RAG capabilities to the diverse linguistic lands"},"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":"2506.01615","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T12:55:51Z","cross_cats_sorted":[],"title_canon_sha256":"ff4459995a98fec513de5866f57f8bc8724a629325b639f4ef9d2141c950c097","abstract_canon_sha256":"3139a466dce2fd44693ad5dd5743096571edabeebedb7f53a1a628979453e440"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:01.610347Z","signature_b64":"G+4wB61VWa8/zO7TSqlKSm7u2PxXI34zpedQbYAc6DqN+h+t+af97ID/9rp3dlU1FPFRphmmfzGa4haAFHtNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bb570c0a674353f9b5373a872ce3cea19675aa1b5c26745fb19cd1bb3293ea9","last_reissued_at":"2026-07-05T11:15:01.609825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:01.609825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IndicRAGSuite: Large-Scale Datasets and a Benchmark for Indian Language RAG Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Pasunuti Prasanjith, Prathmesh B More, Raj Dabre","submitted_at":"2025-06-02T12:55:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems enable language models to access relevant information and generate accurate, well-grounded, and contextually informed responses. However, for Indian languages, the development of high-quality RAG systems is hindered by the lack of two critical resources: (1) evaluation benchmarks for retrieval and generation tasks, and (2) large-scale training datasets for multilingual retrieval. Most existing benchmarks and datasets are centered around English or high-resource languages, making it difficult to extend RAG capabilities to the diverse linguistic lands"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01615","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/2506.01615/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":"2506.01615","created_at":"2026-07-05T11:15:01.609891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01615v2","created_at":"2026-07-05T11:15:01.609891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01615","created_at":"2026-07-05T11:15:01.609891+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO2XBQFGOQ2T","created_at":"2026-07-05T11:15:01.609891+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO2XBQFGOQ2T7G2T","created_at":"2026-07-05T11:15:01.609891+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO2XBQFG","created_at":"2026-07-05T11:15:01.609891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05785","citing_title":"Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I","json":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I.json","graph_json":"https://pith.science/api/pith-number/DO2XBQFGOQ2T7G2TOOUHFTR45I/graph.json","events_json":"https://pith.science/api/pith-number/DO2XBQFGOQ2T7G2TOOUHFTR45I/events.json","paper":"https://pith.science/paper/DO2XBQFG"},"agent_actions":{"view_html":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I","download_json":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I.json","view_paper":"https://pith.science/paper/DO2XBQFG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01615&json=true","fetch_graph":"https://pith.science/api/pith-number/DO2XBQFGOQ2T7G2TOOUHFTR45I/graph.json","fetch_events":"https://pith.science/api/pith-number/DO2XBQFGOQ2T7G2TOOUHFTR45I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I/action/storage_attestation","attest_author":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I/action/author_attestation","sign_citation":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I/action/citation_signature","submit_replication":"https://pith.science/pith/DO2XBQFGOQ2T7G2TOOUHFTR45I/action/replication_record"}},"created_at":"2026-07-05T11:15:01.609891+00:00","updated_at":"2026-07-05T11:15:01.609891+00:00"}