{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:32UMWY7EWOUMSE4OF52IKPWPFR","short_pith_number":"pith:32UMWY7E","canonical_record":{"source":{"id":"2506.08750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T12:45:12Z","cross_cats_sorted":[],"title_canon_sha256":"70b3cbdbe74cc7bdd20fd63a60c86dbd83eb16ab5b1bcaf0eb6233bd2839e074","abstract_canon_sha256":"9fc80356c170e1a63c068e72b776721970730ea5f443aa169a752aa74aa6a555"},"schema_version":"1.0"},"canonical_sha256":"dea8cb63e4b3a8c9138e2f74853ecf2c5ea23a6cedf3211edac8c43e50f4a97b","source":{"kind":"arxiv","id":"2506.08750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08750","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08750v1","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08750","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"32UMWY7EWOUM","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"32UMWY7EWOUMSE4O","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"32UMWY7E","created_at":"2026-07-05T11:19:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:32UMWY7EWOUMSE4OF52IKPWPFR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T12:45:12Z","cross_cats_sorted":[],"title_canon_sha256":"70b3cbdbe74cc7bdd20fd63a60c86dbd83eb16ab5b1bcaf0eb6233bd2839e074","abstract_canon_sha256":"9fc80356c170e1a63c068e72b776721970730ea5f443aa169a752aa74aa6a555"},"schema_version":"1.0"},"canonical_sha256":"dea8cb63e4b3a8c9138e2f74853ecf2c5ea23a6cedf3211edac8c43e50f4a97b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:12.687300Z","signature_b64":"GymP//Ga/UwuVvrPQhBoGKQErKAkwJGXWMmC/RnbYZ4Lmy+m6Cmg9HczfguupG5UCLWaHl4y1JDb03wCSwfiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea8cb63e4b3a8c9138e2f74853ecf2c5ea23a6cedf3211edac8c43e50f4a97b","last_reissued_at":"2026-07-05T11:19:12.686671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:12.686671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08750","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":"2026-07-05T11:19:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bzBMb/61RxGfEsG7d2ZZWYctSS0cx2EjzssQoAki1gpAwtTKqJ//gAQFAQQT0kEzMxt3rHbc3ngCAMLvzvI5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:19.054102Z"},"content_sha256":"3f2cb15ec6f64eb213fec8cd3d1d690a15686dd4c83854a0463d9014dda999a1","schema_version":"1.0","event_id":"sha256:3f2cb15ec6f64eb213fec8cd3d1d690a15686dd4c83854a0463d9014dda999a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:32UMWY7EWOUMSE4OF52IKPWPFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Lau, Issam Hammad, Mishca de Costa, Muhammad Anwar","submitted_at":"2025-06-10T12:45:12Z","abstract_excerpt":"The nuclear industry possesses a wealth of valuable information locked away in unstructured text data. This data, however, is not readily usable for advanced Large Language Model (LLM) applications that require clean, structured question-answer pairs for tasks like model training, fine-tuning, and evaluation. This paper explores how synthetic data generation can bridge this gap, enabling the development of robust LLMs for the nuclear domain. We discuss the challenges of data scarcity and privacy concerns inherent in the nuclear industry and how synthetic data provides a solution by transformin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08750","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/2506.08750/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":"2026-07-05T11:19:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vQ88rty06bSGvjmXgrKtc6+KyIs9hqAj9IPcT4yDsdYettLnkzKT5t0elPTE1K/EgyF8LaDExuz2+ZZ5UIpbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:09:19.054613Z"},"content_sha256":"e5769c1d7faf3916576fc2ddac73351b64fdec8bb55c23d20fa555220c30ba15","schema_version":"1.0","event_id":"sha256:e5769c1d7faf3916576fc2ddac73351b64fdec8bb55c23d20fa555220c30ba15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/32UMWY7EWOUMSE4OF52IKPWPFR/bundle.json","state_url":"https://pith.science/pith/32UMWY7EWOUMSE4OF52IKPWPFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/32UMWY7EWOUMSE4OF52IKPWPFR/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":"2026-08-14T09:09:19Z","links":{"resolver":"https://pith.science/pith/32UMWY7EWOUMSE4OF52IKPWPFR","bundle":"https://pith.science/pith/32UMWY7EWOUMSE4OF52IKPWPFR/bundle.json","state":"https://pith.science/pith/32UMWY7EWOUMSE4OF52IKPWPFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/32UMWY7EWOUMSE4OF52IKPWPFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:32UMWY7EWOUMSE4OF52IKPWPFR","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":"9fc80356c170e1a63c068e72b776721970730ea5f443aa169a752aa74aa6a555","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T12:45:12Z","title_canon_sha256":"70b3cbdbe74cc7bdd20fd63a60c86dbd83eb16ab5b1bcaf0eb6233bd2839e074"},"schema_version":"1.0","source":{"id":"2506.08750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08750","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08750v1","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08750","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"32UMWY7EWOUM","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"32UMWY7EWOUMSE4O","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"32UMWY7E","created_at":"2026-07-05T11:19:12Z"}],"graph_snapshots":[{"event_id":"sha256:e5769c1d7faf3916576fc2ddac73351b64fdec8bb55c23d20fa555220c30ba15","target":"graph","created_at":"2026-07-05T11:19:12Z","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/2506.08750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The nuclear industry possesses a wealth of valuable information locked away in unstructured text data. This data, however, is not readily usable for advanced Large Language Model (LLM) applications that require clean, structured question-answer pairs for tasks like model training, fine-tuning, and evaluation. This paper explores how synthetic data generation can bridge this gap, enabling the development of robust LLMs for the nuclear domain. We discuss the challenges of data scarcity and privacy concerns inherent in the nuclear industry and how synthetic data provides a solution by transformin","authors_text":"Daniel Lau, Issam Hammad, Mishca de Costa, Muhammad Anwar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T12:45:12Z","title":"Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08750","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":"sha256:3f2cb15ec6f64eb213fec8cd3d1d690a15686dd4c83854a0463d9014dda999a1","target":"record","created_at":"2026-07-05T11:19:12Z","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":"9fc80356c170e1a63c068e72b776721970730ea5f443aa169a752aa74aa6a555","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T12:45:12Z","title_canon_sha256":"70b3cbdbe74cc7bdd20fd63a60c86dbd83eb16ab5b1bcaf0eb6233bd2839e074"},"schema_version":"1.0","source":{"id":"2506.08750","kind":"arxiv","version":1}},"canonical_sha256":"dea8cb63e4b3a8c9138e2f74853ecf2c5ea23a6cedf3211edac8c43e50f4a97b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dea8cb63e4b3a8c9138e2f74853ecf2c5ea23a6cedf3211edac8c43e50f4a97b","first_computed_at":"2026-07-05T11:19:12.686671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:12.686671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GymP//Ga/UwuVvrPQhBoGKQErKAkwJGXWMmC/RnbYZ4Lmy+m6Cmg9HczfguupG5UCLWaHl4y1JDb03wCSwfiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:12.687300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f2cb15ec6f64eb213fec8cd3d1d690a15686dd4c83854a0463d9014dda999a1","sha256:e5769c1d7faf3916576fc2ddac73351b64fdec8bb55c23d20fa555220c30ba15"],"state_sha256":"7d91dc33e661d94f471839b977a3367d26100ab378b419f9263821f10a7ef8e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khLwQDO0pClWPbwuk8NFrfbXOqlzkiMBvgw/vHvuSbOb2EoEJDZW+7/4gjgiqYkxYhTaR6+JSkGFfTukuf3KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:09:19.060458Z","bundle_sha256":"16770ce0d1aca350aec299eb8471a8381f8d0a43f3d5de61837050cfc3c94609"}}