{"as_of":"2026-08-09T07:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9ba1826d718da00ac41fa0e64a46556b60e0a9b96d393383f2b4c8eda372370e","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:39:26.907123Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T18:26:05.809159Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05615","snapshot_observed_at":"2026-08-01T18:26:05.809159Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22704","last_updated":"2026-07-19T16:06:32Z","snapshot_observed_at":"2026-08-08T23:31:57.884290Z","submitted_at":"2026-07-19T16:06:32Z","title":"Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T18:26:05.809159Z"},"links":{"cited_paper":"/paper/2502.05615","citing_paper":"/paper/2607.22704"},"observation_digest":"sha256:2c18a2ab7dc036b6960f74f3f9e5769ce53ac4997160deb83d3cbac993884537","observation_id":"6ac25969-d737-4ae1-9ee8-2900a1a22cc7","resolution":{"observed_at":"2026-08-01T18:26:05.809159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.05615/citation-record","integrity":"/paper/2502.05615/integrity","json":"/paper/2502.05615/citation-record.json","paper":"/paper/2502.05615"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.681471Z","title":"Deepseek-v3 technical report,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.681471Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:1fa53f7d79638cfb98a152f950430f1ccfdecce6db5feffd5914beb012142ce9","observation_id":"206c3d20-061b-451b-8560-265b779217dc","resolution":{"observed_at":"2026-08-08T18:39:26.681471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-08T18:39:26.689538Z","title":"Qwen2.5 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.689538Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:a40509695f4cde90665098cf1262d2788f4e8f102e39b3c8437c15828d652928","observation_id":"f8e286c2-83ec-4da4-954a-45156b5bc735","resolution":{"observed_at":"2026-08-08T18:39:26.689538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.693420Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.693420Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:1b89d0a882ca4239e23ab26ca84dd86bb0d68a11c6d3aea0481c85ea84c4d7e4","observation_id":"119a693b-5eb1-4cc3-9424-73b0357368e0","resolution":{"observed_at":"2026-08-08T18:39:26.693420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.696992Z","title":"Large-scale multi-modal pre-trained models: A comprehensive survey,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.696992Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:25d6fc6c667a369d9400a98a69d7a9ed8710892d47cacc80e7d5569710cce76c","observation_id":"04e2d147-9b67-48fc-af70-fd20dee12992","resolution":{"observed_at":"2026-08-08T18:39:26.696992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.09720","last_updated":"2024-08-19T06:19:31Z","snapshot_observed_at":"2026-08-07T06:18:40.789545Z","submitted_at":"2024-08-19T06:19:31Z","title":"Pedestrian Attribute Recognition: A New Benchmark Dataset and A Large Language Model Augmented Framework","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.09720","snapshot_observed_at":"2026-08-08T18:39:26.700706Z","title":"Pedestrian attribute recognition: A new benchmark dataset and a large language model augmented framework,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.700706Z"},"links":{"cited_paper":"/paper/2408.09720","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:fdbce394166ed1825ead79bdc5d1abeb79b61f2202788ad1bfbc3528a4dff59f","observation_id":"cfec1c5c-bb98-45d5-80c6-8d3a4fe4fbb3","resolution":{"observed_at":"2026-08-08T18:39:26.700706Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.703984Z","title":"R2gencsr: Re- trieving context samples for large language model based x-ray medical report generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.703984Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:e4a0e6bd3b1e1d26c17a1c7f8d53091a5b6ff0c81e8f18f07ae4db2d822d0b20","observation_id":"52365a3f-0ef8-41af-a51f-5df86ff9c886","resolution":{"observed_at":"2026-08-08T18:39:26.703984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03458","last_updated":"2025-01-07T01:19:48Z","snapshot_observed_at":"2026-07-06T20:17:24.683086Z","submitted_at":"2025-01-07T01:19:48Z","title":"Activating Associative Disease-Aware Vision Token Memory for LLM-Based X-ray Report Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03458","snapshot_observed_at":"2026-08-08T18:39:26.707552Z","title":"Activating associative disease-aware vision token memory for llm-based x-ray report generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.707552Z"},"links":{"cited_paper":"/paper/2501.03458","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:b2d71e555e89f7d48fd7ca050ee02c2be626b2d761471236fb09dd86958aed6d","observation_id":"e7a3e002-0ed1-4b90-bead-ff95d4dd71c6","resolution":{"observed_at":"2026-08-08T18:39:26.707552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.711917Z","title":"Large lan- guage models are zero-shot reasoners,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.711917Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:769e28e19613180419708913265c7d478e685d9172ab57249f9558dc2b4a3fba","observation_id":"6dc30d4e-4717-4929-85fb-2b16a122722c","resolution":{"observed_at":"2026-08-08T18:39:26.711917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-08T18:39:26.715711Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.715711Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:4fcd523aed7966e300fcf5ebd5ada652343b4d411714a27c171a6262588a2871","observation_id":"8008fca1-e464-4409-aa46-76cacb0c5f32","resolution":{"observed_at":"2026-08-08T18:39:26.715711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12022","last_updated":"2023-11-20T18:57:34Z","snapshot_observed_at":"2026-08-04T22:55:15.345443Z","submitted_at":"2023-11-20T18:57:34Z","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12022","snapshot_observed_at":"2026-08-08T18:39:26.719837Z","title":"Gpqa: A graduate-level google-proof q&a benchmark,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.719837Z"},"links":{"cited_paper":"/paper/2311.12022","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:ea8e2394235c5df1143a66810bb2f8b6b1c2fa3d78d50fdf2cf4051673c8e817","observation_id":"588f7f49-3d85-4906-83b4-c6ce847a07a2","resolution":{"observed_at":"2026-08-08T18:39:26.719837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-08T18:39:26.723622Z","title":"Llama: Open and efficient foundation language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.723622Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:70a3864817be126eada6f27c482ae54de65c5bf64cf0d8bce7e97ca190996771","observation_id":"a54db0c9-3a6b-454b-b4d2-b4c8d5ab8822","resolution":{"observed_at":"2026-08-08T18:39:26.723622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-08T18:39:26.727912Z","title":"Llama 2: Open foundation and fine-tuned chat models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.727912Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:321b366c7d0b4c2940407f14123b19d5dc452c0f97afccb3b09b5cd601988bb0","observation_id":"c43afe50-9fe8-4d11-9f4b-8bbfc0cbdbcc","resolution":{"observed_at":"2026-08-08T18:39:26.727912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.731591Z","title":"The llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.731591Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:9ad7e321be273cd68c4f7fb6628a08ee35b3ba0afe480c0d624e2ba7a04e59c2","observation_id":"cc8b81bc-a723-474f-af01-d653c3120d13","resolution":{"observed_at":"2026-08-08T18:39:26.731591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-08T18:39:26.734987Z","title":"Gemini: a family of highly capable multimodal models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.734987Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:86cd63b5c785db34402e1ad449c47fc86e4282f9dc7ef8291c82720797cab976","observation_id":"6d140c31-3774-4f21-8a22-8e7f2d21a603","resolution":{"observed_at":"2026-08-08T18:39:26.734987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-08T18:39:26.739233Z","title":"Qwen technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.739233Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:f6b0d63ca0afac125bed9edc6fb9d282de0c917bb57dc8b6dfeddac74dd346e6","observation_id":"5e41bddd-f14d-4ade-9bf7-22e1388798a3","resolution":{"observed_at":"2026-08-08T18:39:26.739233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.10305","last_updated":"2025-04-17T08:34:42Z","snapshot_observed_at":"2026-08-06T06:52:14.558389Z","submitted_at":"2023-09-19T04:13:22Z","title":"Baichuan 2: Open Large-scale Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.10305","snapshot_observed_at":"2026-08-08T18:39:26.743287Z","title":"Baichuan 2: Open large-scale language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.743287Z"},"links":{"cited_paper":"/paper/2309.10305","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:8ce0a8f1cf95bb0f2334ed9aa0ed2e27d49d08a1f5c34c5b14a8c87fb9fe5956","observation_id":"b6a1b100-ab91-4923-9da0-ee42641112cd","resolution":{"observed_at":"2026-08-08T18:39:26.743287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.09223","last_updated":"2019-04-19T15:10:56Z","snapshot_observed_at":"2026-07-06T07:47:14.837747Z","submitted_at":"2019-04-19T15:10:56Z","title":"ERNIE: Enhanced Representation through Knowledge Integration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.09223","snapshot_observed_at":"2026-08-08T18:39:26.748606Z","title":"Ernie: Enhanced representation through knowledge integration,","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.748606Z"},"links":{"cited_paper":"/paper/1904.09223","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:fa5caf35b3e9d494a7ca6cd7dea0667fd0da593d0e3973029c6d8291ea9908eb","observation_id":"fd106cb2-be20-465d-a7e6-aefb800ed204","resolution":{"observed_at":"2026-08-08T18:39:26.748606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08879","last_updated":"2024-10-11T14:58:19Z","snapshot_observed_at":"2026-07-06T19:31:53.397265Z","submitted_at":"2024-10-11T14:58:19Z","title":"Multi-modal Fusion based Q-distribution Prediction for Controlled Nuclear Fusion","version":1},"cited_work":{"arxiv_id":"2410.08879","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.08879","snapshot_observed_at":"2026-08-08T18:39:27.026985Z","title":"Multi-modal Fusion based Q-distribution Prediction for Controlled Nuclear Fusion","venue":"cs.CV","work_id":"fa09486f-c4dd-4c66-96b3-e0421e369241","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.752376Z"},"links":{"cited_paper":"/paper/2410.08879","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:977fc5c0cd544761a3a6d537b68a083560b3384db05b388a85befb107eca5f09","observation_id":"9a7d1365-ba9a-4e10-8814-a763c3617b02","resolution":{"observed_at":"2026-08-08T18:39:27.030781Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08889","last_updated":"2024-10-11T15:05:52Z","snapshot_observed_at":"2026-07-06T19:31:53.397265Z","submitted_at":"2024-10-11T15:05:52Z","title":"Exploiting Memory-aware Q-distribution Prediction for Nuclear Fusion via Modern Hopfield Network","version":1},"cited_work":{"arxiv_id":"2410.08889","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.08889","snapshot_observed_at":"2026-08-08T18:39:27.011244Z","title":"Exploiting Memory-aware Q-distribution Prediction for Nuclear Fusion via Modern Hopfield Network","venue":"cs.CV","work_id":"fd3a1d1c-0f7f-4c68-9de0-abd8cff87c25","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.756122Z"},"links":{"cited_paper":"/paper/2410.08889","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:e0a4c6c0e0c9bf4fc0e8697beb42dec1cac5161f5436a795ac6efb94ee2c902e","observation_id":"e3fa4171-8a64-42d6-80da-a9b3109e2619","resolution":{"observed_at":"2026-08-08T18:39:27.017040Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.636527Z","title":"Optimization of modular and helical coils applying genetic algorithm and fully-three-dimensional b-spline curves,","venue":null,"work_id":"1edb92b8-b551-407e-b5bb-136b5c324634","year":2021},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.759870Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:ce3d5caf0f25d0878275a210980134152fcee35c95892f9ab942ad853e50ccb9","observation_id":"2895ea57-da60-4989-9a3a-b020a14ce68d","resolution":{"observed_at":"2026-08-08T18:39:27.640594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.626275Z","title":"Real-time prediction of high-density east disruptions using random forest,","venue":null,"work_id":"2b1a91b7-4342-4ead-a3b4-a7eef29bdd29","year":2021},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.763258Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:797af486f84e5b98f26de4d8453a524869391a4ad43afca4b91a079f6da7e2c3","observation_id":"4b3603af-c699-42ef-9c15-9aecf946894b","resolution":{"observed_at":"2026-08-08T18:39:27.629936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.615558Z","title":"Neural networks for reconstruction and uncertainty quantification of fast-ion phase-space distributions using fild and inpa measurements,","venue":null,"work_id":"32b04143-c2fa-47fc-8fdd-56915e7f4b31","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.766763Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:c0e066b97c82fad47258dbd398c77c524907cc8e86951e7bbef2f9bb20d0842d","observation_id":"24c8973f-34ba-4aaf-8603-347f057882eb","resolution":{"observed_at":"2026-08-08T18:39:27.619223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.594655Z","title":"Vertical instability prediction and its direction control using a support vector machine in integrated commissioning of jt-60sa solely based on mag- netics,","venue":null,"work_id":"f178954a-79bb-4c2c-9924-8dbfc0e7f78d","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.773334Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:5e9fa2ebf2525867adb5428412ac51ec5c05ee7a5f217c7f082c76870e5e1f7f","observation_id":"501a1e15-ebbe-4366-8246-235c28b1af11","resolution":{"observed_at":"2026-08-08T18:39:27.598411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.583820Z","title":"Surrogate model of turbulent transport in fusion plasmas using machine learning,","venue":null,"work_id":"b7911882-d68f-4b68-b23c-68426c0e63cf","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.776608Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:629f457a6ab4000a66604f1c9b316acf1933e8c9ea6c665913cfb28624f9132c","observation_id":"67ed1e29-8118-424b-a4f3-76dff82bb33c","resolution":{"observed_at":"2026-08-08T18:39:27.587617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.573145Z","title":"Experimental identification of ion cyclotron emission on hl-2a using yolo neural network algorithm,","venue":null,"work_id":"0af6ef2e-45cf-41c7-9f80-6b8bf9438490","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.780415Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:33f3ea25e9be17071a7a6523071351762be622b1b1162f49e25a3b19bfecf344","observation_id":"302070e3-2cbd-4273-8f64-70edcf483af8","resolution":{"observed_at":"2026-08-08T18:39:27.577314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.785277Z","title":"You only look once: Unified, real-time object detection,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.785277Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:815aabb6fd112dc19f95f531d093f19d4fb9e2affea79372cdbe9245aae2215c","observation_id":"b491e80e-787a-4823-b5d1-df66c075acf7","resolution":{"observed_at":"2026-08-08T18:39:26.785277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.788648Z","title":"Yolo9000: better, faster, stronger,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.788648Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:eee211d83038810ddd26d5297641e011c2f31761886d4dddc933bdc4b721d109","observation_id":"b5dd2596-b7c6-4f7f-8691-e9fab32bc163","resolution":{"observed_at":"2026-08-08T18:39:26.788648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.792109Z","title":"Yolov3: An incremental improvement,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.792109Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:c01c99b4d949f385b6cd1ae85147001c5a64fa5046b8a5f8b9846f47e2ac2ad5","observation_id":"33098066-d84e-4d91-aca8-4270d7715a7e","resolution":{"observed_at":"2026-08-08T18:39:26.792109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.534626Z","title":"A machine-learning-based tool for last closed-flux surface reconstruction on tokamaks,","venue":null,"work_id":"c013336d-3d8d-4f95-9e88-29460098309f","year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.801373Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:2c4a76710dcdf921058aec0d53e48b208204f2172286a45e625a460b9b9b8e0f","observation_id":"7f6dd205-92ee-493d-bb15-b147eb192c5f","resolution":{"observed_at":"2026-08-08T18:39:27.537974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.524273Z","title":"Neural networks for estimation of divertor conditions in diii-d using c iii imaging,","venue":null,"work_id":"19a1d36c-142c-4568-b87d-a3ffc27d5356","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.805936Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:783a795aa5aae590c4778969e9be3e468d7b24e67da6c437485056338cccfab0","observation_id":"e7c6e1ad-a62e-470e-8dcf-47b5c65627a8","resolution":{"observed_at":"2026-08-08T18:39:27.528197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.514124Z","title":"Avoiding fusion plasma tearing instability with deep reinforcement learning,","venue":null,"work_id":"b02cf44e-877a-420b-ab53-5a6cedb1091b","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.809752Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:320ea2bdf11ac92c28426f1d6cdc5e7a7d4713a56e2be2be6e6b88d2e634d7fd","observation_id":"17babacf-cdf6-4630-842b-9ca14d4b9e53","resolution":{"observed_at":"2026-08-08T18:39:27.518225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.503911Z","title":"Prediction of plasma rotation velocity and ion temperature profiles in east tokamak using artificial neural network models,","venue":null,"work_id":"aa0841df-b9a6-4171-9f88-cbb0bc62b14f","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.813307Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:aeed9a03d5f0a453276b7fb5153c22b0d94e5a18db6dce37cfbb5f9fe44158e1","observation_id":"3193d0dd-ff1d-4ecd-9248-b99d5efec918","resolution":{"observed_at":"2026-08-08T18:39:27.507588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.493451Z","title":"Efficient training sets for surrogate models of tokamak turbulence with active deep ensembles,","venue":null,"work_id":"0c63cca9-adad-4607-a2aa-722c77e7bf91","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.816910Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:3c4573576b14b973006d7b3b0ac177f9ebce5a6c60dbd3c70bd5c30469dd10ca","observation_id":"c7cc6793-8d49-4813-8b41-43bc0395be5b","resolution":{"observed_at":"2026-08-08T18:39:27.497465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.483126Z","title":"Tokamak edge localized mode onset prediction with deep neural network and pedestal turbulence,","venue":null,"work_id":"ba440fcc-0b60-4ec8-88a9-19cb518d6864","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.821559Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:7327d9c5633fc82134e5e2b75da1f9444b0e29595133a43e7910deb1b73fc138","observation_id":"4f9a2947-1f02-4535-9aa0-c780c0de41e7","resolution":{"observed_at":"2026-08-08T18:39:27.486902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.605095Z","title":"Reconstruction of plasma equilibrium and separatrix using convolutional physics-informed neural operator,","venue":null,"work_id":"9036aebe-c485-4d22-afd7-4f733b47e7c1","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.826094Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:67d09354c38ae740fa11df6fd3d9b8ccfc829a9295215042c9c7b6adca377d6a","observation_id":"bd2aeb98-b189-4843-aaaa-8ffdcb09866f","resolution":{"observed_at":"2026-08-08T18:39:27.608807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.545339Z","title":"Impact of various diii-d diag- nostics on the accuracy of neural network surrogates for kinetic efit reconstructions,","venue":null,"work_id":"10023e7a-ff26-4428-a40b-0c8df13eee35","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.830836Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:1dbd18c44a91072d8782e06d4707847b2b4b2b4e64930a1b7394cc72ed41a4c6","observation_id":"fd3b3f87-ac06-4dda-9d2d-76af0a713150","resolution":{"observed_at":"2026-08-08T18:39:27.548872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.472191Z","title":"Real-time capable modeling of icrf heating on nstx and west via machine learning approaches,","venue":null,"work_id":"300df231-f513-4c38-82a3-2bcd1d326cde","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.835490Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:476699cc2cfc272fae792f54a1e367b106b67354a3f48ba18bc3803945e47188","observation_id":"56d81ec8-5e06-4553-b1c4-764b08005590","resolution":{"observed_at":"2026-08-08T18:39:27.475974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.461398Z","title":"Automated experimental design of safe rampdowns via probabilistic machine learning,","venue":null,"work_id":"c1e28367-6dd3-4fa7-add2-5379dbf4ba0c","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.840104Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:d57dab36eea6f037636479157e7fbc6d866f93fff75e9b0cc06c4043cd9428b4","observation_id":"99aecfb0-ea01-401f-82d7-230caad58e59","resolution":{"observed_at":"2026-08-08T18:39:27.465364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.449189Z","title":"Towards practical reinforcement learning for tokamak magnetic control,","venue":null,"work_id":"15cb65d3-9d39-46dd-a9e4-1bc152ec4b23","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.844556Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:2479aec0c1f83af80e30a35c923a73a3c36b64b4a1c0d707ed0bb866d758be32","observation_id":"2b14e8fe-cf12-4b91-92fe-ca0097f2c41a","resolution":{"observed_at":"2026-08-08T18:39:27.453619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.436941Z","title":"Disruption prediction on east with different wall conditions based on a multi-scale deep hybrid neural network,","venue":null,"work_id":"af57389f-d266-40fd-bd14-e7963e25730a","year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.849168Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:4bcb19dfb0597319fc02e99fb99e918e775098e07e6eef16cff0e85a04dbc51a","observation_id":"8dcd155c-5308-40df-8e19-2f1a11ab7b98","resolution":{"observed_at":"2026-08-08T18:39:27.440954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.426724Z","title":"Preemptive rmp-driven elm crash suppression automated by a real-time machine-learning classifier in kstar,","venue":null,"work_id":"2154f072-3f90-4457-908e-0cc1c0dad8f5","year":2022},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.852756Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:a6d04b42ce181e50ef6dc166e290363c31fc1a8215dc2f81b8882fd12220ab43","observation_id":"2b8f582d-7441-41f9-8d01-cf06ecc2e137","resolution":{"observed_at":"2026-08-08T18:39:27.430470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.415821Z","title":"Towards revealing the mystery behind chain of thought: a theoretical perspective,","venue":null,"work_id":"977a66da-532d-4e0f-b14e-5683f665f298","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.856352Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:575b6a3da2313d6553d95250e7befabfa6d9ad74874c1c521171cf224b6a5ae9","observation_id":"793d6a41-a34b-4a4d-b086-29c137b4ef77","resolution":{"observed_at":"2026-08-08T18:39:27.420116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.06769","last_updated":"2025-11-03T00:53:34Z","snapshot_observed_at":"2026-08-07T06:05:27.895209Z","submitted_at":"2024-12-09T18:55:56Z","title":"Training Large Language Models to Reason in a Continuous Latent Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.06769","snapshot_observed_at":"2026-08-08T18:39:26.860317Z","title":"Training large language models to reason in a continuous latent space,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.860317Z"},"links":{"cited_paper":"/paper/2412.06769","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:033f7ace39f7a051dceb0afa52dd3678ed8419ce0c22f541d672e86b146c8c41","observation_id":"d713aef2-1bde-48d4-b319-c462666f58df","resolution":{"observed_at":"2026-08-08T18:39:26.860317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03262","last_updated":"2023-04-18T14:45:18Z","snapshot_observed_at":"2026-07-06T15:13:06.155585Z","submitted_at":"2023-04-06T17:47:29Z","title":"When do you need Chain-of-Thought Prompting for ChatGPT?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03262","snapshot_observed_at":"2026-08-08T18:39:26.864954Z","title":"When do you need chain- of-thought prompting for chatgpt?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.864954Z"},"links":{"cited_paper":"/paper/2304.03262","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:d226583e713e20857288f961d930b44b32050d75d2812aaa6ba33c36cd860d4f","observation_id":"d2c70843-27e6-4d6b-9b38-d4c040e97fba","resolution":{"observed_at":"2026-08-08T18:39:26.864954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.405613Z","title":"What makes chain- of-thought prompting effective? a counterfactual study,","venue":null,"work_id":"5e3b4a15-413c-461a-929b-1f7269f149f5","year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.869440Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:9ce8dde1ea1fd9efc512ef9c87fab2d85becd518138c89ad6d5c03a7924c561b","observation_id":"86660cc0-2dd3-469b-946e-c78d96d2a221","resolution":{"observed_at":"2026-08-08T18:39:27.409383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10001","last_updated":"2023-06-01T05:38:00Z","snapshot_observed_at":"2026-08-07T18:44:16.941060Z","submitted_at":"2022-12-20T05:20:54Z","title":"Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10001","snapshot_observed_at":"2026-08-08T18:39:26.873992Z","title":"Towards understanding chain-of-thought prompting: An empirical study of what matters,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.873992Z"},"links":{"cited_paper":"/paper/2212.10001","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:720384cef65abae34d71d4e1879e7f9f403618e8d5d1a23d5a47c4c3ef01d660","observation_id":"173ef2ff-54f8-439b-adec-bcbda335e871","resolution":{"observed_at":"2026-08-08T18:39:26.873992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13339","last_updated":"2023-07-25T08:51:30Z","snapshot_observed_at":"2026-08-04T05:41:19.823896Z","submitted_at":"2023-07-25T08:51:30Z","title":"Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13339","snapshot_observed_at":"2026-08-08T18:39:26.878890Z","title":"Analyzing chain-of-thought prompting in large language models via gradient-based feature attributions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.878890Z"},"links":{"cited_paper":"/paper/2307.13339","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:d3c3f6e7cb60917ef39ae5aee37d0128b0b4c5e36c3145292e418d28c514b688","observation_id":"b09b16eb-50f3-40d1-8d74-e1dd01e07034","resolution":{"observed_at":"2026-08-08T18:39:26.878890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07919","last_updated":"2023-06-17T06:40:27Z","snapshot_observed_at":"2026-08-08T01:58:48.156445Z","submitted_at":"2023-04-16T23:59:25Z","title":"Chain of Thought Prompt Tuning in Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07919","snapshot_observed_at":"2026-08-08T18:39:26.883500Z","title":"Chain of thought prompt tuning in vision language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.883500Z"},"links":{"cited_paper":"/paper/2304.07919","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:fca31df04cb3c640f89e524b6a6c7df2804aa25defbae19fa3ec79182435fa3f","observation_id":"83fddc40-fa78-41bc-8c60-1f9080abe723","resolution":{"observed_at":"2026-08-08T18:39:26.883500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11538","last_updated":"2025-03-26T19:20:59Z","snapshot_observed_at":"2026-07-06T19:17:13.095667Z","submitted_at":"2024-09-17T20:16:43Z","title":"Chain-of-Thought Prompting for Speech Translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11538","snapshot_observed_at":"2026-08-08T18:39:26.888458Z","title":"Chain-of-thought prompting for speech translation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.888458Z"},"links":{"cited_paper":"/paper/2409.11538","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:9003ebb0c12e31c746856aeb8a8dc6f9af6932ebebaa848b7fb58752dfc7c6cb","observation_id":"bf42e130-0fbf-43fc-8f56-8210fdb458d9","resolution":{"observed_at":"2026-08-08T18:39:26.888458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:27.393585Z","title":"A chain-of-thought prompting approach with llms for evaluating students’ formative assess- ment responses in science,","venue":null,"work_id":"5212b057-df9a-4ec6-956d-ae70c08f278e","year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.893447Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:2ab9579e725b6e2d15cabdd90899623f5913947b59c65ec10796348b6c534d10","observation_id":"ebc363e7-d40a-4be6-a522-d924d8305d6b","resolution":{"observed_at":"2026-08-08T18:39:27.397805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17230","last_updated":"2024-02-27T05:48:18Z","snapshot_observed_at":"2026-08-08T04:55:22.343894Z","submitted_at":"2024-02-27T05:48:18Z","title":"Chain-of-Thought Prompting of Large Language Models for Discovering and Fixing Software Vulnerabilities","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17230","snapshot_observed_at":"2026-08-08T18:39:26.898014Z","title":"Chain-of- thought prompting of large language models for discovering and fixing software vulnerabilities,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.898014Z"},"links":{"cited_paper":"/paper/2402.17230","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:24c0ad4f03d518374116a30af39a6a6076cda2d5c61bc4711b88c3675b25bae9","observation_id":"91da7f7c-b482-4205-a508-16d1d6155346","resolution":{"observed_at":"2026-08-08T18:39:26.898014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T18:39:26.902728Z","title":"Structured chain-of-thought prompting for code generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.902728Z"},"links":{"citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:a49e8247d4d752bf5dace12c801c641a9aef74fb00b7b264b42655865258b183","observation_id":"8337f792-e7be-4f77-81c8-570f516b002e","resolution":{"observed_at":"2026-08-08T18:39:26.902728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12793","last_updated":"2024-07-30T03:58:11Z","snapshot_observed_at":"2026-08-07T13:56:34.167869Z","submitted_at":"2024-06-18T16:58:21Z","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12793","snapshot_observed_at":"2026-08-08T18:39:26.907123Z","title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.907123Z"},"links":{"cited_paper":"/paper/2406.12793","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:6fedbc68b92023e2bfc835d29687d97612f06a5e962b05aaf7d8b2dc8ae331bd","observation_id":"7158ab23-2e12-4366-b77e-b214c64475c0","resolution":{"observed_at":"2026-08-08T18:39:26.907123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-08T18:39:26.685425Z","title":"Available: https://arxiv.org/abs/2412.19437","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T18:39:26.685425Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.05615"},"observation_digest":"sha256:a473751abde3a7a6e4395fa7b10deff3716a21040f17bebf29a69eaffa8c9a93","observation_id":"9c8615e4-4928-469f-9789-693ae3ba9c8d","resolution":{"observed_at":"2026-08-08T18:39:26.685425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.05615","last_updated":"2025-02-08T15:47:48Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T18:34:55.205970Z","submitted_at":"2025-02-08T15:47:48Z","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":2,"verified_fuzzy":22},"total_outbound_references":54},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 1 inbound Pith citation observation for arXiv:2502.05615."}