{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VPPAMEEAAYFRE62YLNUHGTYT3N","short_pith_number":"pith:VPPAMEEA","schema_version":"1.0","canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","source":{"kind":"arxiv","id":"2508.21569","version":1},"attestation_state":"computed","paper":{"title":"L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aishwarya Mirashi, Ananya Joshi, Raviraj Joshi","submitted_at":"2025-08-29T12:24:31Z","abstract_excerpt":"We present MahaSTS, a human-annotated Sentence Textual Similarity (STS) dataset for Marathi, along with MahaSBERT-STS-v2, a fine-tuned Sentence-BERT model optimized for regression-based similarity scoring. The MahaSTS dataset consists of 16,860 Marathi sentence pairs labeled with continuous similarity scores in the range of 0-5. To ensure balanced supervision, the dataset is uniformly distributed across six score-based buckets spanning the full 0-5 range, thus reducing label bias and enhancing model stability. We fine-tune the MahaSBERT model on this dataset and benchmark its performance again"},"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":"2508.21569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T12:24:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"99a358df992d925810fdf7abe6b05aaac63981db86f5ecf8088098b38b3fcafe","abstract_canon_sha256":"1f23357c1a47ca48c0930b6ea8b5b8aa2f9c18bac8ce86cf97fbdce713fee018"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:36.943758Z","signature_b64":"fszit9ZRId+55DDxwelswInKOCxEFy4ztRcQUj1jdmUr3yNsZqGNa35OPLXDz3UM6ClTyL6kkbC8/8FZhpETAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","last_reissued_at":"2026-07-05T12:01:36.943337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:36.943337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aishwarya Mirashi, Ananya Joshi, Raviraj Joshi","submitted_at":"2025-08-29T12:24:31Z","abstract_excerpt":"We present MahaSTS, a human-annotated Sentence Textual Similarity (STS) dataset for Marathi, along with MahaSBERT-STS-v2, a fine-tuned Sentence-BERT model optimized for regression-based similarity scoring. The MahaSTS dataset consists of 16,860 Marathi sentence pairs labeled with continuous similarity scores in the range of 0-5. To ensure balanced supervision, the dataset is uniformly distributed across six score-based buckets spanning the full 0-5 range, thus reducing label bias and enhancing model stability. We fine-tune the MahaSBERT model on this dataset and benchmark its performance again"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21569","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/2508.21569/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":"2508.21569","created_at":"2026-07-05T12:01:36.943391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21569v1","created_at":"2026-07-05T12:01:36.943391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21569","created_at":"2026-07-05T12:01:36.943391+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPPAMEEAAYFR","created_at":"2026-07-05T12:01:36.943391+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPPAMEEAAYFRE62Y","created_at":"2026-07-05T12:01:36.943391+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPPAMEEA","created_at":"2026-07-05T12:01:36.943391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18423","citing_title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N","json":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N.json","graph_json":"https://pith.science/api/pith-number/VPPAMEEAAYFRE62YLNUHGTYT3N/graph.json","events_json":"https://pith.science/api/pith-number/VPPAMEEAAYFRE62YLNUHGTYT3N/events.json","paper":"https://pith.science/paper/VPPAMEEA"},"agent_actions":{"view_html":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N","download_json":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N.json","view_paper":"https://pith.science/paper/VPPAMEEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21569&json=true","fetch_graph":"https://pith.science/api/pith-number/VPPAMEEAAYFRE62YLNUHGTYT3N/graph.json","fetch_events":"https://pith.science/api/pith-number/VPPAMEEAAYFRE62YLNUHGTYT3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/action/storage_attestation","attest_author":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/action/author_attestation","sign_citation":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/action/citation_signature","submit_replication":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/action/replication_record"}},"created_at":"2026-07-05T12:01:36.943391+00:00","updated_at":"2026-07-05T12:01:36.943391+00:00"}