{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LFRDSYMPWVUZ5YV6HN6S5ERM7Q","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":"9791bb56803b026f292df9c41a31043e2f7589d2a3d3526993e84c0507354d06","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T09:58:11Z","title_canon_sha256":"ecb7e3c21dbbd88b145b290ccc41f3e4904f630162e0eabf7203dc1720796b10"},"schema_version":"1.0","source":{"id":"2509.10108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10108","created_at":"2026-07-05T12:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10108v1","created_at":"2026-07-05T12:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10108","created_at":"2026-07-05T12:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"LFRDSYMPWVUZ","created_at":"2026-07-05T12:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"LFRDSYMPWVUZ5YV6","created_at":"2026-07-05T12:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"LFRDSYMP","created_at":"2026-07-05T12:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:28a0b32c43d6ba2cca75d93bc0bb59857ccb9a17c2b954813d1aa4388bba07a9","target":"graph","created_at":"2026-07-05T12:11:02Z","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/2509.10108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of medical chatbots in Arabic is significantly constrained by the scarcity of large-scale, high-quality annotated datasets. While prior efforts compiled a dataset of 20,000 Arabic patient-doctor interactions from social media to fine-tune large language models (LLMs), model scalability and generalization remained limited. In this study, we propose a scalable synthetic data augmentation strategy to expand the training corpus to 100,000 records. Using advanced generative AI systems ChatGPT-4o and Gemini 2.5 Pro we generated 80,000 contextually relevant and medically coherent synt","authors_text":"Abdulrahman Allam, Ali Hamdi, Khaled Shaban, Seif Ahmed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T09:58:11Z","title":"Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10108","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:de2602afeb8b54a3560d23e16d360c437a34c09aa9b42f67be2111e2fd685080","target":"record","created_at":"2026-07-05T12:11:02Z","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":"9791bb56803b026f292df9c41a31043e2f7589d2a3d3526993e84c0507354d06","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T09:58:11Z","title_canon_sha256":"ecb7e3c21dbbd88b145b290ccc41f3e4904f630162e0eabf7203dc1720796b10"},"schema_version":"1.0","source":{"id":"2509.10108","kind":"arxiv","version":1}},"canonical_sha256":"596239618fb5699ee2be3b7d2e922cfc0c7faabc4d753e3f67eb77ac32e08ba0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"596239618fb5699ee2be3b7d2e922cfc0c7faabc4d753e3f67eb77ac32e08ba0","first_computed_at":"2026-07-05T12:11:02.564607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:02.564607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ebaQpBHBHRMjIcTBR2r4SjD8+0zejG5awlEuVEV8Z0aKRSxFIV1pWZLWuxTlZjPjTYlloSDGOvbexNSJ2dx9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:02.565091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de2602afeb8b54a3560d23e16d360c437a34c09aa9b42f67be2111e2fd685080","sha256:28a0b32c43d6ba2cca75d93bc0bb59857ccb9a17c2b954813d1aa4388bba07a9"],"state_sha256":"cb75215858076deaf6571b4efc35c5ebaae94dd5ee78b27fc69468c362fb1680"}