{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KSWLOS5ZBYBMMASLGVSCG6YB4Y","short_pith_number":"pith:KSWLOS5Z","canonical_record":{"source":{"id":"2505.03688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T16:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab5fb40249181c4a49f612601532f374b6360dc5c735794833c729d728ef9350","abstract_canon_sha256":"c1f8cd1f9cfad115068f6079bbe331c6dd7591b022365ba2c551b6bb409660ee"},"schema_version":"1.0"},"canonical_sha256":"54acb74bb90e02c6024b3564237b01e63ed973d7de55e11afa62c7385c34305b","source":{"kind":"arxiv","id":"2505.03688","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03688","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03688v2","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03688","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"KSWLOS5ZBYBM","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"KSWLOS5ZBYBMMASL","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"KSWLOS5Z","created_at":"2026-07-05T11:02:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KSWLOS5ZBYBMMASLGVSCG6YB4Y","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03688","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T16:42:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ab5fb40249181c4a49f612601532f374b6360dc5c735794833c729d728ef9350","abstract_canon_sha256":"c1f8cd1f9cfad115068f6079bbe331c6dd7591b022365ba2c551b6bb409660ee"},"schema_version":"1.0"},"canonical_sha256":"54acb74bb90e02c6024b3564237b01e63ed973d7de55e11afa62c7385c34305b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:24.364389Z","signature_b64":"WfzAmLKwy3yx6oEqqvzMjaQHYg+ZqvZ20LSwatiS/EOP/rKMZXzqJTz9vVD3Oo8IcAZmFX+Nrb1DrOIHDu1QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54acb74bb90e02c6024b3564237b01e63ed973d7de55e11afa62c7385c34305b","last_reissued_at":"2026-07-05T11:02:24.363917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:24.363917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03688","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"epU/Enqe/GHkTHi3wCd20n8IKmVFGA7LFrPmydVtdWwiMmeAx1zd4zkiiEOV6kgzi3ux0000Ke6qzsTV6dhMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:37.420873Z"},"content_sha256":"a13040d0fce478424eb484e66eb3adbb77f14bb4b744569ca89455c1402cded1","schema_version":"1.0","event_id":"sha256:a13040d0fce478424eb484e66eb3adbb77f14bb4b744569ca89455c1402cded1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KSWLOS5ZBYBMMASLGVSCG6YB4Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Kulkarni, Rajlaxmi Patil, Raviraj Joshi, Ruturaj Ghatage, Sharvi Endait","submitted_at":"2025-05-06T16:42:54Z","abstract_excerpt":"The rapid progress in question-answering (QA) systems has predominantly benefited high-resource languages, leaving Indic languages largely underrepresented despite their vast native speaker base. In this paper, we present IndicSQuAD, a comprehensive multi-lingual extractive QA dataset covering nine major Indic languages, systematically derived from the SQuAD dataset. Building on previous work with MahaSQuAD for Marathi, our approach adapts and extends translation techniques to maintain high linguistic fidelity and accurate answer-span alignment across diverse languages. IndicSQuAD comprises ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03688","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/2505.03688/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:02:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38rinPiDEhX3XlaQeo6dE8oY6KOEO7wGSSDXF9fO/P7kI6SDAXI/ufEjjyBP77gUBmGw/7rwEOR1LhTAHvxQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:37.421247Z"},"content_sha256":"4d4bd6b0a8da4fd8067a05c539df93ae452227a446543ca292015b505f577fdf","schema_version":"1.0","event_id":"sha256:4d4bd6b0a8da4fd8067a05c539df93ae452227a446543ca292015b505f577fdf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/bundle.json","state_url":"https://pith.science/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T15:49:37Z","links":{"resolver":"https://pith.science/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y","bundle":"https://pith.science/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/bundle.json","state":"https://pith.science/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSWLOS5ZBYBMMASLGVSCG6YB4Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KSWLOS5ZBYBMMASLGVSCG6YB4Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1f8cd1f9cfad115068f6079bbe331c6dd7591b022365ba2c551b6bb409660ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T16:42:54Z","title_canon_sha256":"ab5fb40249181c4a49f612601532f374b6360dc5c735794833c729d728ef9350"},"schema_version":"1.0","source":{"id":"2505.03688","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03688","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03688v2","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03688","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_12","alias_value":"KSWLOS5ZBYBM","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_16","alias_value":"KSWLOS5ZBYBMMASL","created_at":"2026-07-05T11:02:24Z"},{"alias_kind":"pith_short_8","alias_value":"KSWLOS5Z","created_at":"2026-07-05T11:02:24Z"}],"graph_snapshots":[{"event_id":"sha256:4d4bd6b0a8da4fd8067a05c539df93ae452227a446543ca292015b505f577fdf","target":"graph","created_at":"2026-07-05T11:02:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.03688/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress in question-answering (QA) systems has predominantly benefited high-resource languages, leaving Indic languages largely underrepresented despite their vast native speaker base. In this paper, we present IndicSQuAD, a comprehensive multi-lingual extractive QA dataset covering nine major Indic languages, systematically derived from the SQuAD dataset. Building on previous work with MahaSQuAD for Marathi, our approach adapts and extends translation techniques to maintain high linguistic fidelity and accurate answer-span alignment across diverse languages. IndicSQuAD comprises ex","authors_text":"Aditya Kulkarni, Rajlaxmi Patil, Raviraj Joshi, Ruturaj Ghatage, Sharvi Endait","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T16:42:54Z","title":"IndicSQuAD: A Comprehensive Multilingual Question Answering Dataset for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03688","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a13040d0fce478424eb484e66eb3adbb77f14bb4b744569ca89455c1402cded1","target":"record","created_at":"2026-07-05T11:02:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1f8cd1f9cfad115068f6079bbe331c6dd7591b022365ba2c551b6bb409660ee","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T16:42:54Z","title_canon_sha256":"ab5fb40249181c4a49f612601532f374b6360dc5c735794833c729d728ef9350"},"schema_version":"1.0","source":{"id":"2505.03688","kind":"arxiv","version":2}},"canonical_sha256":"54acb74bb90e02c6024b3564237b01e63ed973d7de55e11afa62c7385c34305b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54acb74bb90e02c6024b3564237b01e63ed973d7de55e11afa62c7385c34305b","first_computed_at":"2026-07-05T11:02:24.363917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:24.363917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WfzAmLKwy3yx6oEqqvzMjaQHYg+ZqvZ20LSwatiS/EOP/rKMZXzqJTz9vVD3Oo8IcAZmFX+Nrb1DrOIHDu1QCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:24.364389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03688","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a13040d0fce478424eb484e66eb3adbb77f14bb4b744569ca89455c1402cded1","sha256:4d4bd6b0a8da4fd8067a05c539df93ae452227a446543ca292015b505f577fdf"],"state_sha256":"1a7c32d0f875eb60358140e87b8f63644f388858a44691ef6750c1bae145953f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wGf1O/hIzyhJjLwBKSnfVNxvWpORPOjx7iFkEC5sgYWX8ytFkDdowcZC7xBsftL+kq1VD+xYFklQt+DlP+WHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:49:37.423197Z","bundle_sha256":"516177ecaff8818a73dd4bc1498e266c5e5e7052dcaaad90369bacd6e9c7bcdf"}}