{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y56QGN7TCWC2SP7US3GYDSPDJ3","short_pith_number":"pith:Y56QGN7T","schema_version":"1.0","canonical_sha256":"c77d0337f31585a93ff496cd81c9e34ee515aa0dc1e4dbf8cb3f3e63bab020e0","source":{"kind":"arxiv","id":"2505.19494","version":1},"attestation_state":"computed","paper":{"title":"Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Manoj Balaji Jagadeeshan, Pawan Goyal, Prince Raj","submitted_at":"2025-05-26T04:23:21Z","abstract_excerpt":"The study presents a comprehensive benchmark for retrieving Sanskrit documents using English queries, focusing on the chapters of the Srimadbhagavatam. It employs a tripartite approach: Direct Retrieval (DR), Translation-based Retrieval (DT), and Query Translation (QT), utilizing shared embedding spaces and advanced translation methods to enhance retrieval systems in a RAG framework. The study fine-tunes state-of-the-art models for Sanskrit's linguistic nuances, evaluating models such as BM25, REPLUG, mDPR, ColBERT, Contriever, and GPT-2. It adapts summarization techniques for Sanskrit documen"},"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":"2505.19494","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T04:23:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"cb380cc998f2599de3549ed0e00bac54eda86d0ef354d8aeda857a1a3cb1a276","abstract_canon_sha256":"80e245b69b152ecec81dedd56daa4484a0a3a2f337cd6860c636bd2febe08a95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:31.214904Z","signature_b64":"4mwYkCzS/ihw3lVgDzV+VD4jPZ/Uv62wbUW91jaBHiCBujVm/bfUsgv5wfvxkI5YmyXs/q/WiRQgBTZkZEHfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c77d0337f31585a93ff496cd81c9e34ee515aa0dc1e4dbf8cb3f3e63bab020e0","last_reissued_at":"2026-07-05T11:09:31.214385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:31.214385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anveshana: A New Benchmark Dataset for Cross-Lingual Information Retrieval On English Queries and Sanskrit Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Manoj Balaji Jagadeeshan, Pawan Goyal, Prince Raj","submitted_at":"2025-05-26T04:23:21Z","abstract_excerpt":"The study presents a comprehensive benchmark for retrieving Sanskrit documents using English queries, focusing on the chapters of the Srimadbhagavatam. It employs a tripartite approach: Direct Retrieval (DR), Translation-based Retrieval (DT), and Query Translation (QT), utilizing shared embedding spaces and advanced translation methods to enhance retrieval systems in a RAG framework. The study fine-tunes state-of-the-art models for Sanskrit's linguistic nuances, evaluating models such as BM25, REPLUG, mDPR, ColBERT, Contriever, and GPT-2. It adapts summarization techniques for Sanskrit documen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19494","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/2505.19494/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":"2505.19494","created_at":"2026-07-05T11:09:31.214442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19494v1","created_at":"2026-07-05T11:09:31.214442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19494","created_at":"2026-07-05T11:09:31.214442+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y56QGN7TCWC2","created_at":"2026-07-05T11:09:31.214442+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y56QGN7TCWC2SP7U","created_at":"2026-07-05T11:09:31.214442+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y56QGN7T","created_at":"2026-07-05T11:09:31.214442+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/Y56QGN7TCWC2SP7US3GYDSPDJ3","json":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3.json","graph_json":"https://pith.science/api/pith-number/Y56QGN7TCWC2SP7US3GYDSPDJ3/graph.json","events_json":"https://pith.science/api/pith-number/Y56QGN7TCWC2SP7US3GYDSPDJ3/events.json","paper":"https://pith.science/paper/Y56QGN7T"},"agent_actions":{"view_html":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3","download_json":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3.json","view_paper":"https://pith.science/paper/Y56QGN7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19494&json=true","fetch_graph":"https://pith.science/api/pith-number/Y56QGN7TCWC2SP7US3GYDSPDJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/Y56QGN7TCWC2SP7US3GYDSPDJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3/action/storage_attestation","attest_author":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3/action/author_attestation","sign_citation":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3/action/citation_signature","submit_replication":"https://pith.science/pith/Y56QGN7TCWC2SP7US3GYDSPDJ3/action/replication_record"}},"created_at":"2026-07-05T11:09:31.214442+00:00","updated_at":"2026-07-05T11:09:31.214442+00:00"}