{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4VQC3MIYN546RIPXEV67VY7KJ7","short_pith_number":"pith:4VQC3MIY","canonical_record":{"source":{"id":"2404.13364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T12:16:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a87f8addf24408fbcd9d2613a036c34ebacd3c0538d25b305503b1a075a2c72d","abstract_canon_sha256":"b1599e2a27db1688a17ec1079d59fb85e484a83befeae8c7a17ca34281912e5f"},"schema_version":"1.0"},"canonical_sha256":"e5602db1186f79e8a1f7257dfae3ea4fffbae299502da4b314069a2047f7522c","source":{"kind":"arxiv","id":"2404.13364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13364","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13364v1","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13364","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_12","alias_value":"4VQC3MIYN546","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_16","alias_value":"4VQC3MIYN546RIPX","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_8","alias_value":"4VQC3MIY","created_at":"2026-07-05T08:10:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4VQC3MIYN546RIPXEV67VY7KJ7","target":"record","payload":{"canonical_record":{"source":{"id":"2404.13364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T12:16:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a87f8addf24408fbcd9d2613a036c34ebacd3c0538d25b305503b1a075a2c72d","abstract_canon_sha256":"b1599e2a27db1688a17ec1079d59fb85e484a83befeae8c7a17ca34281912e5f"},"schema_version":"1.0"},"canonical_sha256":"e5602db1186f79e8a1f7257dfae3ea4fffbae299502da4b314069a2047f7522c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:31.090300Z","signature_b64":"9cmraEb/HFE3ZVJbDsa3sn+003Lvj464Kw+7a8fK6hVDVwL1YwOZ08wcO/k3TtZGuRlx7TbHsA5efCjMxqj7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5602db1186f79e8a1f7257dfae3ea4fffbae299502da4b314069a2047f7522c","last_reissued_at":"2026-07-05T08:10:31.089838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:31.089838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.13364","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F7bBljvvdiNj4q9ELcPqpYN6oHE0IrWegZM6Iur4s3AaEsKUyQA6rDASRlULdw1f7anggoazNum25wwQigNTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:05.441236Z"},"content_sha256":"f61f1176cc8c2090420c4bf68ff6c1b2a1b15ae0c5f7e9a5472ae8e03e663ba1","schema_version":"1.0","event_id":"sha256:f61f1176cc8c2090420c4bf68ff6c1b2a1b15ae0c5f7e9a5472ae8e03e663ba1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4VQC3MIYN546RIPXEV67VY7KJ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MahaSQuAD: Bridging Linguistic Divides in Marathi Question-Answering","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":"2024-04-20T12:16:35Z","abstract_excerpt":"Question-answering systems have revolutionized information retrieval, but linguistic and cultural boundaries limit their widespread accessibility. This research endeavors to bridge the gap of the absence of efficient QnA datasets in low-resource languages by translating the English Question Answering Dataset (SQuAD) using a robust data curation approach. We introduce MahaSQuAD, the first-ever full SQuAD dataset for the Indic language Marathi, consisting of 118,516 training, 11,873 validation, and 11,803 test samples. We also present a gold test set of manually verified 500 examples. Challenges"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13364","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/2404.13364/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":"2026-07-05T08:10:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sf8cxdmn3y577r1Vt3c0pK8Sb06brUICO8d9ck4Bfb0La/zwTmtDOZMm3KIeRzR2sO0VK754SXRUnnOCLbiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:05.441623Z"},"content_sha256":"6841a87bb73d03c232df5ece581d91bc97fec4f536cdaba73de8df43794b4c10","schema_version":"1.0","event_id":"sha256:6841a87bb73d03c232df5ece581d91bc97fec4f536cdaba73de8df43794b4c10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VQC3MIYN546RIPXEV67VY7KJ7/bundle.json","state_url":"https://pith.science/pith/4VQC3MIYN546RIPXEV67VY7KJ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VQC3MIYN546RIPXEV67VY7KJ7/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":"2026-07-06T18:46:05Z","links":{"resolver":"https://pith.science/pith/4VQC3MIYN546RIPXEV67VY7KJ7","bundle":"https://pith.science/pith/4VQC3MIYN546RIPXEV67VY7KJ7/bundle.json","state":"https://pith.science/pith/4VQC3MIYN546RIPXEV67VY7KJ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VQC3MIYN546RIPXEV67VY7KJ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VQC3MIYN546RIPXEV67VY7KJ7","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":"b1599e2a27db1688a17ec1079d59fb85e484a83befeae8c7a17ca34281912e5f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T12:16:35Z","title_canon_sha256":"a87f8addf24408fbcd9d2613a036c34ebacd3c0538d25b305503b1a075a2c72d"},"schema_version":"1.0","source":{"id":"2404.13364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13364","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13364v1","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13364","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_12","alias_value":"4VQC3MIYN546","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_16","alias_value":"4VQC3MIYN546RIPX","created_at":"2026-07-05T08:10:31Z"},{"alias_kind":"pith_short_8","alias_value":"4VQC3MIY","created_at":"2026-07-05T08:10:31Z"}],"graph_snapshots":[{"event_id":"sha256:6841a87bb73d03c232df5ece581d91bc97fec4f536cdaba73de8df43794b4c10","target":"graph","created_at":"2026-07-05T08:10:31Z","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/2404.13364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Question-answering systems have revolutionized information retrieval, but linguistic and cultural boundaries limit their widespread accessibility. This research endeavors to bridge the gap of the absence of efficient QnA datasets in low-resource languages by translating the English Question Answering Dataset (SQuAD) using a robust data curation approach. We introduce MahaSQuAD, the first-ever full SQuAD dataset for the Indic language Marathi, consisting of 118,516 training, 11,873 validation, and 11,803 test samples. We also present a gold test set of manually verified 500 examples. Challenges","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":"2024-04-20T12:16:35Z","title":"MahaSQuAD: Bridging Linguistic Divides in Marathi Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13364","kind":"arxiv","version":1},"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:f61f1176cc8c2090420c4bf68ff6c1b2a1b15ae0c5f7e9a5472ae8e03e663ba1","target":"record","created_at":"2026-07-05T08:10:31Z","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":"b1599e2a27db1688a17ec1079d59fb85e484a83befeae8c7a17ca34281912e5f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-20T12:16:35Z","title_canon_sha256":"a87f8addf24408fbcd9d2613a036c34ebacd3c0538d25b305503b1a075a2c72d"},"schema_version":"1.0","source":{"id":"2404.13364","kind":"arxiv","version":1}},"canonical_sha256":"e5602db1186f79e8a1f7257dfae3ea4fffbae299502da4b314069a2047f7522c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5602db1186f79e8a1f7257dfae3ea4fffbae299502da4b314069a2047f7522c","first_computed_at":"2026-07-05T08:10:31.089838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:31.089838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9cmraEb/HFE3ZVJbDsa3sn+003Lvj464Kw+7a8fK6hVDVwL1YwOZ08wcO/k3TtZGuRlx7TbHsA5efCjMxqj7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:31.090300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f61f1176cc8c2090420c4bf68ff6c1b2a1b15ae0c5f7e9a5472ae8e03e663ba1","sha256:6841a87bb73d03c232df5ece581d91bc97fec4f536cdaba73de8df43794b4c10"],"state_sha256":"50fe839089fee0da9478e487b12f1d7f37934108a2f5fe176d28c875a90b6e4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FSglQie/IT2pE2GV842OCP1v8a+NDVStUbHp8w0A7dwW+Rie5iwkrtelCVzjTWgoRGhj7rEM+TLEp1ZKsvNuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:46:05.443546Z","bundle_sha256":"89a53a3a6309bcde28d7046b1d272cc9387e1776bb7c6ccdf7e431e66b06318a"}}