{"as_of":"2026-08-20T21:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ae0175ed2ba85881a300638ecd0f5de1e085ce5e6736316f3cbef044b278f2d5","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:27:14.768095Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"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":[],"links":{"evidence":"/evidence","html":"/paper/2505.04723/citation-record","integrity":"/paper/2505.04723/integrity","json":"/paper/2505.04723/citation-record.json","paper":"/paper/2505.04723"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:27:15.065149Z","title":"In: International Conference on Services Computing","venue":null,"work_id":"604e06ed-1440-4b20-89e7-9c2a4458b2d1","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.669600Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:44ab0aa8d80c7e688785a7c6e5bab46365fe20aeca1127067fa66db08004451c","observation_id":"aef93fac-bedf-459d-b692-fa7a1b702d40","resolution":{"observed_at":"2026-08-15T23:27:15.068541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:15.054979Z","title":"Computer Stan- dards & Interfaces p","venue":null,"work_id":"6d3b4d16-b3a9-483a-ae08-b27c49153326","year":2025},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.673644Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:e70f0e2dfe8c535186bd29c177c96523d623554ae16906fcfa1da6029ce69d1b","observation_id":"7360241d-fca9-49bb-b1f3-ed183fdb3a82","resolution":{"observed_at":"2026-08-15T23:27:15.058573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10708","last_updated":"2025-08-30T11:17:17Z","snapshot_observed_at":"2026-08-18T02:43:02.251721Z","submitted_at":"2025-02-15T07:43:43Z","title":"Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10708","snapshot_observed_at":"2026-08-15T23:27:14.676966Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.676966Z"},"links":{"cited_paper":"/paper/2502.10708","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:c83a0ce1e027ba4172937f514e7ff66a65ee98eb69f0bd72e5408adf1adbc1cf","observation_id":"6ab72c5e-4ffc-4a3c-bdb2-e054b5b2f9dc","resolution":{"observed_at":"2026-08-15T23:27:14.676966Z","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":"2026-08-15T23:27:15.043152Z","title":"In: 2024 IEEE 17th International Conference on Signal Processing (ICSP)","venue":null,"work_id":"c86ff720-ac8d-4325-9abb-5648a3a4b5b9","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.680814Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:0a1916b544b530b37199231d9ca8dd6c86ae2ab076b4aab7ff2998e0fc6b51ba","observation_id":"5e58696d-92a3-451b-8e97-1c7cde77feca","resolution":{"observed_at":"2026-08-15T23:27:15.047009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:15.029696Z","title":"In: ICASSP 2025-2025 IEEE International Conference on Acous- tics, Speech and Signal Processing (ICASSP)","venue":null,"work_id":"46bbab55-1f93-4c1e-9546-eb275d5109e7","year":2025},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.685071Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:560e5294f365f82f6ccf8a2bf7f4efb56ed1489e5fccd71943954cbf35df0621","observation_id":"95bab909-0348-489c-b491-fe8862fe4fde","resolution":{"observed_at":"2026-08-15T23:27:15.034594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11451","last_updated":"2024-05-08T12:11:00Z","snapshot_observed_at":"2026-08-16T14:51:17.504913Z","submitted_at":"2023-10-17T17:58:34Z","title":"Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11451","snapshot_observed_at":"2026-08-15T23:27:14.688451Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.688451Z"},"links":{"cited_paper":"/paper/2310.11451","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:791a0baa7182c045a80fb9e6f20626760c5d322b28df28804a86827c1afa7dfb","observation_id":"79b08b38-0ca8-4a9d-8b25-1707fdc2ee61","resolution":{"observed_at":"2026-08-15T23:27:14.688451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14294","last_updated":"2024-07-19T04:47:36Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T15:53:08Z","title":"A Survey on Efficient Inference for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14294","snapshot_observed_at":"2026-08-15T23:27:14.692575Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.692575Z"},"links":{"cited_paper":"/paper/2404.14294","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:d91cd3bcb215c3f267f4186ca6a254b80d36c2771269a3f1821ea3740bcc1cde","observation_id":"6a002c95-f0fa-432c-8a4d-b3f9040aad8a","resolution":{"observed_at":"2026-08-15T23:27:14.692575Z","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":"2026-08-15T23:27:14.696554Z","title":"In: Proceedings of the fourth ACM international conference on AI in finance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.696554Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:52dfb4916c6e38a583cfa2469cbc548e6852b4eb0cd811ef946a191c7abf0365","observation_id":"92b6d827-f4f0-4c32-bc53-0835d6e9b835","resolution":{"observed_at":"2026-08-15T23:27:14.696554Z","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":"2026-08-15T23:27:15.013016Z","title":"Health Care Science 2(4), 255–263 (2023)","venue":null,"work_id":"8cb9a14c-1bb0-4109-9011-a95ea307cbc1","year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.699965Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:3384896080eeaedd0463318d4ac03a1e12acae260431ccc022c9080cd327da65","observation_id":"10418670-ef03-40c9-a1fd-ca2bc142644e","resolution":{"observed_at":"2026-08-15T23:27:15.016292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:14.703419Z","title":"In: Pro- ceedings of the 26th annual international conference on machine learning","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.703419Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:cf8bebe3afbdc3328ad086bbfddfd83faf8ba57674187002fc79a3236b54f1bf","observation_id":"a018c488-42be-4998-9b2d-43ee1469ef42","resolution":{"observed_at":"2026-08-15T23:27:14.703419Z","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":"2026-08-15T23:27:14.997244Z","title":"In: Fu, X., Fleisig, E","venue":null,"work_id":"48ce98ff-0191-4ab8-88df-dcf3b7027c70","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.706617Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:04bbc6dcee40dd9c000dd1227051dbedca2e6a796db79a5550386efd249f8f41","observation_id":"2336e83c-a4c3-4147-b812-cffd7660ba99","resolution":{"observed_at":"2026-08-15T23:27:15.001035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:14.986528Z","title":"In: Al-Onaizan, Y., Bansal, M., Chen, Y.N","venue":null,"work_id":"f342d7b4-3e21-4f66-98e2-7762bd7e19e9","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.709989Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:b95971d9fe7edbebb043ad7a0d28783173a46143384912e9dcbfec064599b0cf","observation_id":"ddc6db4a-0d8b-4919-98a4-a43cdc8be440","resolution":{"observed_at":"2026-08-15T23:27:14.990867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.10738","last_updated":"2024-06-16T13:26:10Z","snapshot_observed_at":"2026-08-16T14:17:57.549081Z","submitted_at":"2024-02-16T14:55:33Z","title":"Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.10738","snapshot_observed_at":"2026-08-15T23:27:14.716291Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.716291Z"},"links":{"cited_paper":"/paper/2402.10738","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:fda035c60d56ccf83ed313b63835acc2b77e8eb2c47308ffa4632f3572b5d492","observation_id":"4441d46e-1f1f-4163-b63b-aa37e4d151f7","resolution":{"observed_at":"2026-08-15T23:27:14.716291Z","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":"2026-08-15T23:27:14.965023Z","title":"https:// huggingface.co/datasets/BAAI/Infinity-Instruct (2024), accessed: 2024-04- 08","venue":null,"work_id":"c5e6e301-0129-4a5d-9c0f-dde8f70e30cf","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.720882Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:c5de506a6ded0108ebd0dd262f293b46c451518a21f48be9190a7521637df108","observation_id":"7acb583f-7e21-4b76-9fd9-0280383bfe19","resolution":{"observed_at":"2026-08-15T23:27:14.968709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.07055","last_updated":"2024-08-13T17:46:12Z","snapshot_observed_at":"2026-08-16T13:26:40.463635Z","submitted_at":"2024-08-13T17:46:12Z","title":"LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.07055","snapshot_observed_at":"2026-08-15T23:27:14.724102Z","title":"arXiv preprint arXiv:2408.07055 (2024) 14 Jingyang Deng †, Ran Chen†, Jo-Ku Cheng, and Jinwen Ma∗","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.724102Z"},"links":{"cited_paper":"/paper/2408.07055","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:876019c442f8c72bad0c14acec1fdc4ce5cf708c564efc2c7ed9c47ae984a9e6","observation_id":"00b35da8-089e-45da-a6c2-476882170ebb","resolution":{"observed_at":"2026-08-15T23:27:14.724102Z","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":"2026-08-14T09:56:00.692687Z","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":"2026-08-15T23:27:14.728221Z","title":"arXiv preprint arXiv:2406.12793 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.728221Z"},"links":{"cited_paper":"/paper/2406.12793","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:1d4687fa6c2ae9f5e61592c7fa30d61498110b59a3d7381f572ed6d86c03ad53","observation_id":"a15dd0be-4242-4ee4-9b0d-e545bf571a30","resolution":{"observed_at":"2026-08-15T23:27:14.728221Z","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":"2026-08-15T23:27:14.732200Z","title":"In: International Conference on Machine Learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.732200Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:867dd7088c7b4c987969a7835dbf4f90c1584c571e97f5aa4af1f73413b0947f","observation_id":"e3587fb8-9d6b-497f-954d-fcebfa565d38","resolution":{"observed_at":"2026-08-15T23:27:14.732200Z","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":"2026-08-15T23:27:14.947218Z","title":"https://github.com/apoorvumang/ prompt-lookup-decoding/ (November 2023), accessed: 2024-04-08","venue":null,"work_id":"f20d22af-216c-4bf3-b767-29b08b4f9e85","year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.735773Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:3eb7160f04c7c6166bf92ca7fc67b9097c78c0f16101d26b27c78c11a8e43ef3","observation_id":"228d35f9-bf2c-4f0d-9a66-d80c783710ad","resolution":{"observed_at":"2026-08-15T23:27:14.951271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-08-17T18:50:07.059564Z","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":"2026-08-15T23:27:14.739248Z","title":"5 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.739248Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:82b0f8b527e7c5011e652205fc5388e63f6f5fa36f0cf135fa68eb70ab9ab3d8","observation_id":"0eb17a2d-2588-485d-8f6b-c02dcb959ab1","resolution":{"observed_at":"2026-08-15T23:27:14.739248Z","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":"2026-08-15T23:27:14.743163Z","title":"In: Proceed- ings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.743163Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:13c476b4f71d1d31c2f1222dd9c0e614eb5a2885525de699fd35e290d267e7bf","observation_id":"791c098e-c1e0-4205-a32a-970ac1e31e02","resolution":{"observed_at":"2026-08-15T23:27:14.743163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1604.06174","last_updated":"2016-04-22T19:21:36Z","snapshot_observed_at":"2026-08-14T14:33:36.303679Z","submitted_at":"2016-04-21T04:15:27Z","title":"Training Deep Nets with Sublinear Memory Cost","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.06174","snapshot_observed_at":"2026-08-15T23:27:14.746402Z","title":"arXiv preprint arXiv:1604.06174 (2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.746402Z"},"links":{"cited_paper":"/paper/1604.06174","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:af314adac30e52c0cfebf81e3ae38457fe3dd409fbc75e567349af385ab462e7","observation_id":"9d84844a-759e-48f3-ba9b-12fb21de9cf6","resolution":{"observed_at":"2026-08-15T23:27:14.746402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08691","last_updated":"2023-07-17T17:50:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-17T17:50:36Z","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08691","snapshot_observed_at":"2026-08-15T23:27:14.749998Z","title":"arXiv preprint arXiv:2307.08691 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.749998Z"},"links":{"cited_paper":"/paper/2307.08691","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:07299a35336a2c76fc790075d387ac378bc1eff578ed749276694486268245f8","observation_id":"1ca28f5f-182d-4fde-8d73-9b0c1a10f0dd","resolution":{"observed_at":"2026-08-15T23:27:14.749998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.02027","last_updated":"2022-10-05T20:14:52Z","snapshot_observed_at":"2026-08-17T03:10:15.141603Z","submitted_at":"2021-06-29T04:37:23Z","title":"Efficient Sequence Packing without Cross-contamination: Accelerating Large Language Models without Impacting Performance","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.02027","snapshot_observed_at":"2026-08-15T23:27:14.753674Z","title":"arXiv preprint arXiv:2107.02027 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.753674Z"},"links":{"cited_paper":"/paper/2107.02027","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:2a1dd054fa14177cd5517ce4f0dabf2e5b1a3cdb511761c1fb608b9f19f1d600","observation_id":"9687c014-cdd3-4e44-90ff-f2a0829f8ace","resolution":{"observed_at":"2026-08-15T23:27:14.753674Z","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":"2026-08-18T18:18:37.449517Z","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":"2026-08-15T23:27:14.757330Z","title":"arXiv preprint arXiv:2412.19437 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.757330Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:076e8c248c1bdbb1688c78e4bf15808b91f1039888c6d0ef45cd76d46f743bbb","observation_id":"9b0bee15-dcf4-43b3-b587-f58f4c43e456","resolution":{"observed_at":"2026-08-15T23:27:14.757330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09212","last_updated":"2024-01-17T19:09:57Z","snapshot_observed_at":"2026-08-04T18:52:19.083847Z","submitted_at":"2023-06-15T15:49:51Z","title":"CMMLU: Measuring massive multitask language understanding in Chinese","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09212","snapshot_observed_at":"2026-08-15T23:27:14.760897Z","title":"arXiv preprint arXiv:2306.09212 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.760897Z"},"links":{"cited_paper":"/paper/2306.09212","citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:37a77474ec4bc4f5047c6a724d09825b3dd90f945c46d847aa2f959353591c57","observation_id":"dbdf2aa0-687e-4133-b8e3-3fcf6ecce1b7","resolution":{"observed_at":"2026-08-15T23:27:14.760897Z","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":"2026-08-15T23:27:14.930176Z","title":"Advances in Neural Information Processing Systems 36, 62991–63010 (2023)","venue":null,"work_id":"bb64b4e4-9770-4daf-9646-aa51a022fb7c","year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.764559Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:7770920efc95c63ba93c147e35dc39105fb356dc04b4af2a2f8d43088b14e2d4","observation_id":"771168a9-1241-4484-ad8e-53f7c6ccc7a9","resolution":{"observed_at":"2026-08-15T23:27:14.934219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:14.918106Z","title":"In: Proceedings of the 29th Symposium on Operating Systems Principles","venue":null,"work_id":"cab87448-6466-4ea6-8645-3daf4c8ae1c0","year":2023},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.768095Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:dd42c29d4d4d32dec1bbf75b8382dd34b6d9c08d097a66e7ac6f642706e83205","observation_id":"26398668-2718-4bc6-b1c7-9a423bfa923f","resolution":{"observed_at":"2026-08-15T23:27:14.922923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T23:27:14.976441Z","title":null,"venue":null,"work_id":"583ded5d-507b-456f-bba8-4a3dddb11e90","year":2024},"citing_paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","version":1},"reference_index":4572,"source":"pdf_text","source_observed_at":"2026-08-15T23:27:14.713232Z"},"links":{"citing_paper":"/paper/2505.04723"},"observation_digest":"sha256:7b889da1d5afa93209306545061310bc43a02ec15de17a4e7864f18d72bc64f4","observation_id":"5edbe3eb-39e2-47fb-82a6-2b77836439a5","resolution":{"observed_at":"2026-08-15T23:27:14.979942Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.04723","last_updated":"2025-05-07T18:21:47Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-20T18:35:31.099024Z","submitted_at":"2025-05-07T18:21:47Z","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":28},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2505.04723."}