{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RQXTWJAPFTT6UNPHFTVZPK3IL7","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":"595d08e76b8b3d2a88b957272af68b1d5f1cf15e1c9b3c5d310d74d589fe73f8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T09:02:45Z","title_canon_sha256":"f11a96cf12622c25ee44c4564ba5fe1b12876a74a6d66da0695b1cda5ce1cbec"},"schema_version":"1.0","source":{"id":"2404.12010","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12010","created_at":"2026-07-05T08:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12010v1","created_at":"2026-07-05T08:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12010","created_at":"2026-07-05T08:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"RQXTWJAPFTT6","created_at":"2026-07-05T08:09:33Z"},{"alias_kind":"pith_short_16","alias_value":"RQXTWJAPFTT6UNPH","created_at":"2026-07-05T08:09:33Z"},{"alias_kind":"pith_short_8","alias_value":"RQXTWJAP","created_at":"2026-07-05T08:09:33Z"}],"graph_snapshots":[{"event_id":"sha256:0019408701aaa556029bcbcc50f9c1426e9d388f3cefd0356ce6b763bf92cd68","target":"graph","created_at":"2026-07-05T08:09:33Z","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/2404.12010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Paraphrase generation is a pivotal task in natural language processing (NLP). Existing datasets in the domain lack syntactic and lexical diversity, resulting in paraphrases that closely resemble the source sentences. Moreover, these datasets often contain hate speech and noise, and may unintentionally include non-English language sentences. This research introduces ParaFusion, a large-scale, high-quality English paraphrase dataset developed using Large Language Models (LLM) to address these challenges. ParaFusion augments existing datasets with high-quality data, significantly enhancing both l","authors_text":"Lasal Jayawardena, Prasan Yapa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T09:02:45Z","title":"ParaFusion: A Large-Scale LLM-Driven English Paraphrase Dataset Infused with High-Quality Lexical and Syntactic Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12010","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":"sha256:1d5ec00f6489a70bcd1582a248befcfcbf7318f8411e143c1405f10b7327443c","target":"record","created_at":"2026-07-05T08:09:33Z","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":"595d08e76b8b3d2a88b957272af68b1d5f1cf15e1c9b3c5d310d74d589fe73f8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-18T09:02:45Z","title_canon_sha256":"f11a96cf12622c25ee44c4564ba5fe1b12876a74a6d66da0695b1cda5ce1cbec"},"schema_version":"1.0","source":{"id":"2404.12010","kind":"arxiv","version":1}},"canonical_sha256":"8c2f3b240f2ce7ea35e72ceb97ab685fcbb1c162e0cc35725b88351eda7b9a8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c2f3b240f2ce7ea35e72ceb97ab685fcbb1c162e0cc35725b88351eda7b9a8e","first_computed_at":"2026-07-05T08:09:33.873790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:33.873790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v6zDP6rZmaTMWqealsBe2zpxUMnH4eEfJi9Is184MLTNr7KR/ugDCW3iMjWd1vwc2FsvKuD429efCkqd+mOfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:33.874260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12010","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d5ec00f6489a70bcd1582a248befcfcbf7318f8411e143c1405f10b7327443c","sha256:0019408701aaa556029bcbcc50f9c1426e9d388f3cefd0356ce6b763bf92cd68"],"state_sha256":"7747e3d32d336de2063bd219b170ae97ac3014b8bce2c5edcdb9218f5ace198e"}