{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VPPAMEEAAYFRE62YLNUHGTYT3N","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":"1f23357c1a47ca48c0930b6ea8b5b8aa2f9c18bac8ce86cf97fbdce713fee018","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T12:24:31Z","title_canon_sha256":"99a358df992d925810fdf7abe6b05aaac63981db86f5ecf8088098b38b3fcafe"},"schema_version":"1.0","source":{"id":"2508.21569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21569","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21569v1","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21569","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_12","alias_value":"VPPAMEEAAYFR","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_16","alias_value":"VPPAMEEAAYFRE62Y","created_at":"2026-07-05T12:01:36Z"},{"alias_kind":"pith_short_8","alias_value":"VPPAMEEA","created_at":"2026-07-05T12:01:36Z"}],"graph_snapshots":[{"event_id":"sha256:99e60c79fbef8507affc87c9c46501ac9d68965fa983b1666003a28970a6277a","target":"graph","created_at":"2026-07-05T12:01:36Z","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/2508.21569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aishwarya Mirashi, Ananya Joshi, Raviraj Joshi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T12:24:31Z","title":"L3Cube-MahaSTS: A Marathi Sentence Similarity Dataset and Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21569","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:cd73796c740d34246467c97b38358285d732633ffdf5014302e04da16db23f9c","target":"record","created_at":"2026-07-05T12:01:36Z","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":"1f23357c1a47ca48c0930b6ea8b5b8aa2f9c18bac8ce86cf97fbdce713fee018","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T12:24:31Z","title_canon_sha256":"99a358df992d925810fdf7abe6b05aaac63981db86f5ecf8088098b38b3fcafe"},"schema_version":"1.0","source":{"id":"2508.21569","kind":"arxiv","version":1}},"canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","first_computed_at":"2026-07-05T12:01:36.943337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:36.943337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fszit9ZRId+55DDxwelswInKOCxEFy4ztRcQUj1jdmUr3yNsZqGNa35OPLXDz3UM6ClTyL6kkbC8/8FZhpETAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:36.943758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd73796c740d34246467c97b38358285d732633ffdf5014302e04da16db23f9c","sha256:99e60c79fbef8507affc87c9c46501ac9d68965fa983b1666003a28970a6277a"],"state_sha256":"b7656ec5f6fd7ff3acd05855e335c0584eb8dcaeaf1fb868e6909ce81795c04c"}