{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZMOLZX3TRNGVS2B7PJ4XJ5DZHV","short_pith_number":"pith:ZMOLZX3T","canonical_record":{"source":{"id":"2508.17444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-24T16:48:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7977e086f6ef47f4f0028ddf1497ec9843a57005e1f4a966e09a045feb5411d6","abstract_canon_sha256":"bab7b8d8f8adb7043d668b2b12f2209ba87a22b6d29888c318f9842b6edc46b9"},"schema_version":"1.0"},"canonical_sha256":"cb1cbcdf738b4d59683f7a7974f4793d67d74b0e6f08284466d8bf323defde16","source":{"kind":"arxiv","id":"2508.17444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17444","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17444v1","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17444","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZMOLZX3TRNGV","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZMOLZX3TRNGVS2B7","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZMOLZX3T","created_at":"2026-07-05T11:58:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZMOLZX3TRNGVS2B7PJ4XJ5DZHV","target":"record","payload":{"canonical_record":{"source":{"id":"2508.17444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-24T16:48:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7977e086f6ef47f4f0028ddf1497ec9843a57005e1f4a966e09a045feb5411d6","abstract_canon_sha256":"bab7b8d8f8adb7043d668b2b12f2209ba87a22b6d29888c318f9842b6edc46b9"},"schema_version":"1.0"},"canonical_sha256":"cb1cbcdf738b4d59683f7a7974f4793d67d74b0e6f08284466d8bf323defde16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:41.576208Z","signature_b64":"veeB8A9Dw0l7LlLOavrX6/c8jCExpaJsmQ4MUWCysQe3/7DEKGQ7hqf6IsP0SWhpNf97bPMNBfXPvpajiHgyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb1cbcdf738b4d59683f7a7974f4793d67d74b0e6f08284466d8bf323defde16","last_reissued_at":"2026-07-05T11:58:41.575779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:41.575779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.17444","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":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/2bTQUKv606QjO2+4c3yQMjZYjImn7tQFs/c2xer5YkLF/Jir9wBOgxDx5xcvXyUoQays94srqNJT0Gn58sDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:08:01.405495Z"},"content_sha256":"4c74ff6c4fea766982762d28e918ec90b4b1843ffd854fd4206afbd74f730122","schema_version":"1.0","event_id":"sha256:4c74ff6c4fea766982762d28e918ec90b4b1843ffd854fd4206afbd74f730122"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZMOLZX3TRNGVS2B7PJ4XJ5DZHV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhay Shanbhag, Amogh Thakurdesai, Ananya Joshi, Raviraj Joshi, Ridhima Sinare, Suramya Jadhav","submitted_at":"2025-08-24T16:48:58Z","abstract_excerpt":"Paraphrases are a vital tool to assist language understanding tasks such as question answering, style transfer, semantic parsing, and data augmentation tasks. Indic languages are complex in natural language processing (NLP) due to their rich morphological and syntactic variations, diverse scripts, and limited availability of annotated data. In this work, we present the L3Cube-MahaParaphrase Dataset, a high-quality paraphrase corpus for Marathi, a low resource Indic language, consisting of 8,000 sentence pairs, each annotated by human experts as either Paraphrase (P) or Non-paraphrase (NP). We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17444","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/2508.17444/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":"2026-07-05T11:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hh2d4eDUXhgMwNqZzNjdJATmdfGk09UBUZGchnz0VIx5wCpN+eGagyYUf/gTo9imFCeh9CCzgenz8GBAuLxzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:08:01.405866Z"},"content_sha256":"c2e0913bfb4b5690fc20e263ae286b8ac3448057a83c33cfa5c2809e80d145ef","schema_version":"1.0","event_id":"sha256:c2e0913bfb4b5690fc20e263ae286b8ac3448057a83c33cfa5c2809e80d145ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/bundle.json","state_url":"https://pith.science/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/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":"2026-07-07T10:08:01Z","links":{"resolver":"https://pith.science/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV","bundle":"https://pith.science/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/bundle.json","state":"https://pith.science/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMOLZX3TRNGVS2B7PJ4XJ5DZHV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZMOLZX3TRNGVS2B7PJ4XJ5DZHV","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":"bab7b8d8f8adb7043d668b2b12f2209ba87a22b6d29888c318f9842b6edc46b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-24T16:48:58Z","title_canon_sha256":"7977e086f6ef47f4f0028ddf1497ec9843a57005e1f4a966e09a045feb5411d6"},"schema_version":"1.0","source":{"id":"2508.17444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17444","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17444v1","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17444","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZMOLZX3TRNGV","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"ZMOLZX3TRNGVS2B7","created_at":"2026-07-05T11:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"ZMOLZX3T","created_at":"2026-07-05T11:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:c2e0913bfb4b5690fc20e263ae286b8ac3448057a83c33cfa5c2809e80d145ef","target":"graph","created_at":"2026-07-05T11:58:41Z","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/2508.17444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Paraphrases are a vital tool to assist language understanding tasks such as question answering, style transfer, semantic parsing, and data augmentation tasks. Indic languages are complex in natural language processing (NLP) due to their rich morphological and syntactic variations, diverse scripts, and limited availability of annotated data. In this work, we present the L3Cube-MahaParaphrase Dataset, a high-quality paraphrase corpus for Marathi, a low resource Indic language, consisting of 8,000 sentence pairs, each annotated by human experts as either Paraphrase (P) or Non-paraphrase (NP). We ","authors_text":"Abhay Shanbhag, Amogh Thakurdesai, Ananya Joshi, Raviraj Joshi, Ridhima Sinare, Suramya Jadhav","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-24T16:48:58Z","title":"MahaParaphrase: A Marathi Paraphrase Detection Corpus and BERT-based Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17444","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":"sha256:4c74ff6c4fea766982762d28e918ec90b4b1843ffd854fd4206afbd74f730122","target":"record","created_at":"2026-07-05T11:58:41Z","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":"bab7b8d8f8adb7043d668b2b12f2209ba87a22b6d29888c318f9842b6edc46b9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-24T16:48:58Z","title_canon_sha256":"7977e086f6ef47f4f0028ddf1497ec9843a57005e1f4a966e09a045feb5411d6"},"schema_version":"1.0","source":{"id":"2508.17444","kind":"arxiv","version":1}},"canonical_sha256":"cb1cbcdf738b4d59683f7a7974f4793d67d74b0e6f08284466d8bf323defde16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb1cbcdf738b4d59683f7a7974f4793d67d74b0e6f08284466d8bf323defde16","first_computed_at":"2026-07-05T11:58:41.575779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:41.575779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"veeB8A9Dw0l7LlLOavrX6/c8jCExpaJsmQ4MUWCysQe3/7DEKGQ7hqf6IsP0SWhpNf97bPMNBfXPvpajiHgyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:41.576208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c74ff6c4fea766982762d28e918ec90b4b1843ffd854fd4206afbd74f730122","sha256:c2e0913bfb4b5690fc20e263ae286b8ac3448057a83c33cfa5c2809e80d145ef"],"state_sha256":"c8b30725e999045c8dcc94f313b02157b24c1cd7a5330539678d6d34151b35c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8wSzhxDaJoBsyxV8IFadXCw4/36txeKyoqCp35MCnp2oHa6dZpRFFzCg5lWGfkBEyYtTdV/OrnK9qUz6t6zCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:08:01.407837Z","bundle_sha256":"7bc28cec3fadeb71743407407a99b341c7c7ec71a616ac03f26473f25e9852e2"}}