{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VPPAMEEAAYFRE62YLNUHGTYT3N","short_pith_number":"pith:VPPAMEEA","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"},"canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","source":{"kind":"arxiv","id":"2508.21569","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VPPAMEEAAYFRE62YLNUHGTYT3N","target":"record","payload":{"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"},"canonical_sha256":"abde061080060b127b585b68734f13db4c7a4e665924aa2b47b36294daa8c908","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"},"source_kind":"arxiv","source_id":"2508.21569","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":"2026-07-05T12:01:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zj/OF1RfJD6ubBMOS9OOzsx5q7BDwYjkBy/HYppO7HyZ94vgq/AkeYmLtclZOQd9IcmGi6dw0zw3JqysfxZMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:07:45.321639Z"},"content_sha256":"cd73796c740d34246467c97b38358285d732633ffdf5014302e04da16db23f9c","schema_version":"1.0","event_id":"sha256:cd73796c740d34246467c97b38358285d732633ffdf5014302e04da16db23f9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VPPAMEEAAYFRE62YLNUHGTYT3N","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uS/h9bQOqmp/MfuH7LPJHc7SymGgVpJJllynBli5kacVLJDLQPdSK1nzPdQAWkDMMye6wXzVFyqEdoo20o/yCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:07:45.322011Z"},"content_sha256":"99e60c79fbef8507affc87c9c46501ac9d68965fa983b1666003a28970a6277a","schema_version":"1.0","event_id":"sha256:99e60c79fbef8507affc87c9c46501ac9d68965fa983b1666003a28970a6277a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/bundle.json","state_url":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/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":"2026-07-06T18:07:45Z","links":{"resolver":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N","bundle":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/bundle.json","state":"https://pith.science/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPPAMEEAAYFRE62YLNUHGTYT3N/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xaj3EhKSGu95ZsK3bmu0zN9yYa7XYKChuUixuyUXDInnda9apLuWuLpnfcMdlayMfMeZuJR0z3KagRPQ6AuSDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:07:45.324003Z","bundle_sha256":"27812b36492507b35739a18f9c4d342f703683fa66bac2ac0300a70283870ac4"}}