{"as_of":"2026-08-17T13:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecfed365bbd0f45ac755750b15396ff846da511d8f3e5c02a91469dd04c0ec9f","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2454,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T18:51:31.843700Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-11T03:37:46.293270Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2410.04047","last_updated":"2026-04-10T06:16:18Z","snapshot_observed_at":"2026-07-06T19:28:18.775189Z","submitted_at":"2024-10-05T06:04:19Z","title":"TS-Reasoner: Domain-Oriented Time Series Inference Agents for Reasoning and Automated Analysis","version":6},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-23T19:45:39.130509Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2410.04047"},"observation_digest":"sha256:f1f2d4add619f0a9ff88c0ba050b8539337ea14394849abf703cab99e3f37829","observation_id":"eae6b165-9978-48ce-95a0-02bc18353653","resolution":{"observed_at":"2026-05-23T19:45:47.153284Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2411.04996","last_updated":"2025-05-08T01:53:55Z","snapshot_observed_at":"2026-08-14T02:18:08.215462Z","submitted_at":"2024-11-07T18:59:06Z","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T02:48:44.900467Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2411.04996"},"observation_digest":"sha256:518e0b4b664bf5752e0d753a7b166110a10795d58234713a7e9995af340e837a","observation_id":"ea390263-8236-488d-a20e-d93296c887ed","resolution":{"observed_at":"2026-05-18T02:48:44.972097Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-12T18:51:31.843700Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11266","last_updated":"2025-05-19T14:51:44Z","snapshot_observed_at":"2026-08-15T15:29:01.975226Z","submitted_at":"2024-11-18T03:45:34Z","title":"VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs","version":5},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T18:51:31.843700Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2411.11266"},"observation_digest":"sha256:e4047f011b9e4ec92f996f673a9594a0f70f8185746dba5ea26834dd96310a3d","observation_id":"46282825-feb2-4081-8fd5-c4cddec069c2","resolution":{"observed_at":"2026-08-12T18:51:31.843700Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-12T17:10:55.508760Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12882","last_updated":"2025-06-06T05:27:10Z","snapshot_observed_at":"2026-08-15T15:30:04.308785Z","submitted_at":"2024-11-19T22:00:01Z","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T17:10:55.508760Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2411.12882"},"observation_digest":"sha256:c7af0ff9323ad07b9f96177f23e8ed5ca95dc4e3853a6752d191b8a98ca9ee63","observation_id":"4d31cdbb-e251-4c58-be3a-59cccf0e8650","resolution":{"observed_at":"2026-08-12T17:10:55.508760Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-12T15:58:48.075969Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13820","last_updated":"2025-07-14T02:22:43Z","snapshot_observed_at":"2026-08-16T03:10:21.519704Z","submitted_at":"2024-11-21T03:52:41Z","title":"InstCache: A Predictive Cache for LLM Serving","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T15:58:48.075969Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2411.13820"},"observation_digest":"sha256:bc7a84013cc457c9f91b110fd408fc0262fe020d1b7a0406de615d2191a742a1","observation_id":"5328728b-8302-47b7-8681-5b26f7cb8a89","resolution":{"observed_at":"2026-08-12T15:58:48.075969Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-12T05:35:51.662254Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00316","last_updated":"2025-05-24T15:43:59Z","snapshot_observed_at":"2026-08-14T13:43:37.144553Z","submitted_at":"2024-11-30T01:50:42Z","title":"HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T05:35:51.662254Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.00316"},"observation_digest":"sha256:20dc19bf1222498361580604790bc8db4469bd2a57804f253b39682797a06eff","observation_id":"f076307c-d8c7-4411-9fb1-be9a7fdafffd","resolution":{"observed_at":"2026-08-12T05:35:51.662254Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-12T04:31:46.188692Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01340","last_updated":"2025-09-12T12:10:06Z","snapshot_observed_at":"2026-08-14T09:51:52.464752Z","submitted_at":"2024-12-02T10:07:01Z","title":"A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T04:31:46.188692Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.01340"},"observation_digest":"sha256:61c209d30e10e4e2bb5e2fd99fac3de10585ee5485461e6a4f8e2ab7557123e7","observation_id":"6da6fca4-b8d2-413c-bf2d-9bf59e5597b0","resolution":{"observed_at":"2026-08-12T04:31:46.188692Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T23:21:42.007108Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02592","last_updated":"2025-08-30T07:10:08Z","snapshot_observed_at":"2026-08-16T23:34:46.066896Z","submitted_at":"2024-12-03T17:23:47Z","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T23:21:42.007108Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.02592"},"observation_digest":"sha256:fe2e9210ecab2d02ae21ca8a8b1c47f2ad8895171c3cd8af07c4dbb7a9e0b0a2","observation_id":"4fe95007-a469-4ce0-9551-e537de44e732","resolution":{"observed_at":"2026-08-11T23:21:42.007108Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T20:19:51.176047Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.05862","last_updated":"2025-05-30T22:50:03Z","snapshot_observed_at":"2026-08-14T18:06:33.184779Z","submitted_at":"2024-12-08T08:54:13Z","title":"Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T20:19:51.176047Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.05862"},"observation_digest":"sha256:026d85552edeb398b90a0e7deb9c10f412572a21410682677a623cb69f50f77d","observation_id":"55be5b6d-f7b9-47be-af5b-f31bfbce3f67","resolution":{"observed_at":"2026-08-11T20:19:51.176047Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2412.06288","last_updated":"2026-06-08T05:39:34Z","snapshot_observed_at":"2026-08-15T03:02:25.733318Z","submitted_at":"2024-12-09T08:20:11Z","title":"Health-Informed Computing: Estimating and Addressing the Public Health Impact of Data Centers","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-23T07:55:04.197907Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.06288"},"observation_digest":"sha256:0dd86bcf8f71c844dab54c4dafb4db0bbe5a8bdf97179590ac6f4b5d06e96d59","observation_id":"5b30cef5-bfb8-4b7f-9062-8ed75513b202","resolution":{"observed_at":"2026-05-23T07:55:28.802466Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T19:53:31.120126Z","title":"Deepseek-v3 technical report.arXiv 2412.19437, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06288","last_updated":"2026-06-08T05:39:34Z","snapshot_observed_at":"2026-08-15T03:02:25.733318Z","submitted_at":"2024-12-09T08:20:11Z","title":"Health-Informed Computing: Estimating and Addressing the Public Health Impact of Data Centers","version":4},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-11T19:53:31.120126Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.06288"},"observation_digest":"sha256:cb04ae226be2691ecd1cbb04240115d2df85fcb4d23a54c6897f3c9cf8bbff21","observation_id":"67732f15-0c1c-4d61-b83f-d06d45f5ce78","resolution":{"observed_at":"2026-08-11T19:53:31.120126Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T19:28:54.330737Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06681","last_updated":"2025-04-06T13:58:40Z","snapshot_observed_at":"2026-08-17T00:28:03.592140Z","submitted_at":"2024-12-09T17:24:41Z","title":"Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-11T19:28:54.330737Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.06681"},"observation_digest":"sha256:3e55fa46b7f0625751537dd2326d6944537dd3a07bc09171c1c0fcc3a610d5d2","observation_id":"304a7ad2-6fba-4aaa-9302-ba376dbe45e0","resolution":{"observed_at":"2026-08-11T19:28:54.330737Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T20:27:18.301141Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06845","last_updated":"2025-07-04T00:04:42Z","snapshot_observed_at":"2026-08-12T22:29:58.744757Z","submitted_at":"2024-12-08T02:01:46Z","title":"7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement","version":6},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T20:27:18.301141Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.06845"},"observation_digest":"sha256:549fe7db55aac3153cbd9eccec474a442354b70c4a774d654a826ae5b4aee936","observation_id":"d1079219-1573-4a92-b259-054ff5840111","resolution":{"observed_at":"2026-08-11T20:27:18.301141Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T18:41:26.600177Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07626","last_updated":"2025-03-25T06:19:32Z","snapshot_observed_at":"2026-08-15T15:31:36.046464Z","submitted_at":"2024-12-10T16:05:56Z","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T18:41:26.600177Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.07626"},"observation_digest":"sha256:2a6da2826b1bc8fe9130679dfa17e18152988a228aabf5fe493920bae5d3e94e","observation_id":"9c3580c1-f681-44d6-90f2-fdd3999d35cd","resolution":{"observed_at":"2026-08-11T18:41:26.600177Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T18:28:56.012263Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07923","last_updated":"2025-03-12T13:48:12Z","snapshot_observed_at":"2026-08-17T13:26:35.260492Z","submitted_at":"2024-12-10T21:09:12Z","title":"Asking Again and Again: Exploring LLM Robustness to Repeated Questions","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T18:28:56.012263Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.07923"},"observation_digest":"sha256:cd99948258b1a9f6c4a4c6143eb548ede939720a890e441de4d9b2ad656f9933","observation_id":"25af1cd3-2241-4ddf-83f9-57a9d2e5afca","resolution":{"observed_at":"2026-08-11T18:28:56.012263Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T17:25:31.420922Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.09041","last_updated":"2025-06-20T10:28:15Z","snapshot_observed_at":"2026-08-16T19:48:12.439679Z","submitted_at":"2024-12-12T08:07:26Z","title":"Towards Wireless Native Big AI Model: The Mission and Approach Differ From Large Language Model","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T17:25:31.420922Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.09041"},"observation_digest":"sha256:cb7945001556a58f8820af0ab131642b8e94e865d2465333a730bdc3b2b9af65","observation_id":"85a6f3b5-85df-4b15-bc32-5338dd303f98","resolution":{"observed_at":"2026-08-11T17:25:31.420922Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T16:33:54.716204Z","title":"Deepseek-v3 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.10028","last_updated":"2025-06-26T15:06:14Z","snapshot_observed_at":"2026-08-15T09:04:36.513140Z","submitted_at":"2024-12-13T10:39:27Z","title":"Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts","version":4},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T16:33:54.716204Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.10028"},"observation_digest":"sha256:2db2411ae8f4dd228bded8b2443c36664e877e0d998d1df0b7f3a6cb7a4634c1","observation_id":"9c0ce407-7854-4028-951e-ebf097e256ab","resolution":{"observed_at":"2026-08-11T16:33:54.716204Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T14:24:28.778723Z","title":"font- variant:small-caps","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.12040","last_updated":"2025-05-27T11:23:24Z","snapshot_observed_at":"2026-08-17T00:21:17.651506Z","submitted_at":"2024-12-16T18:08:22Z","title":"How Private are Language Models in Abstractive Summarization?","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-11T14:24:28.778723Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.12040"},"observation_digest":"sha256:8f2a831665e05a9e9ec191206233a32004d3c4d1947a92d14115453850536054","observation_id":"fc3d4699-2566-428d-98c4-3cee310b9c6f","resolution":{"observed_at":"2026-08-11T14:24:28.778723Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T14:11:39.644086Z","title":"Deepseek- v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.12465","last_updated":"2025-08-04T03:37:34Z","snapshot_observed_at":"2026-08-17T05:05:53.009167Z","submitted_at":"2024-12-17T01:54:08Z","title":"Core Context Aware Transformers for Long Context Language Modeling","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-11T14:11:39.644086Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.12465"},"observation_digest":"sha256:64452a0bc5330527a5d35f1bc1b56df6cb1290baaa08d8fed1d1388960ad9d22","observation_id":"23c79c42-8f28-4294-b24e-edb9a870f05a","resolution":{"observed_at":"2026-08-11T14:11:39.644086Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T12:44:35.277153Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14219","last_updated":"2025-01-22T03:33:25Z","snapshot_observed_at":"2026-08-17T05:50:31.197474Z","submitted_at":"2024-12-18T14:11:15Z","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T12:44:35.277153Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.14219"},"observation_digest":"sha256:bfede974b651e6347da516b10ee70a3978450b069781aa330709b5d9dca662bd","observation_id":"f571f914-c158-4d77-bf54-3a425daa95a5","resolution":{"observed_at":"2026-08-11T12:44:35.277153Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-11T05:04:51.940367Z","title":"Deepseek-v3 technical report.arXiv preprint arXiv:2412.19437, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.18148","last_updated":"2025-06-01T15:06:21Z","snapshot_observed_at":"2026-08-17T08:46:50.230603Z","submitted_at":"2024-12-24T04:04:54Z","title":"Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T05:04:51.940367Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.18148"},"observation_digest":"sha256:6997d9f38918908c10a787391915aa6d9c4b93813a038751de90dc02f5ce8680","observation_id":"bcbba09f-2f6b-4799-935b-cd2e2531be45","resolution":{"observed_at":"2026-08-11T05:04:51.940367Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T23:08:26.574840Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.21124","last_updated":"2025-03-16T21:10:15Z","snapshot_observed_at":"2026-08-14T23:33:35.228932Z","submitted_at":"2024-12-30T17:55:28Z","title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T23:08:26.574840Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2412.21124"},"observation_digest":"sha256:14bb97bbd84aad99835243ed9b3324e0fb31e9313cf5c254ec4b66f1f20d2696","observation_id":"15bc84be-5671-4d28-8a77-668b9b38bd04","resolution":{"observed_at":"2026-08-10T23:08:26.574840Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T22:57:16.890766Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.00363","last_updated":"2025-03-21T12:52:57Z","snapshot_observed_at":"2026-08-16T19:46:04.199020Z","submitted_at":"2024-12-31T09:29:38Z","title":"SPDZCoder: Combining Expert Knowledge with LLMs for Generating Privacy-Computing Code","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T22:57:16.890766Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.00363"},"observation_digest":"sha256:48598cf90c7f2edc939aa53b9a7052cbfc0c0c55b4203d31d84e743baa111ff8","observation_id":"d4a17d1c-134c-4890-8a18-fe7ce4f6fe74","resolution":{"observed_at":"2026-08-10T22:57:16.890766Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T22:52:00.767804Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.00513","last_updated":"2025-03-18T16:01:24Z","snapshot_observed_at":"2026-08-10T22:46:57.431139Z","submitted_at":"2024-12-31T15:53:50Z","title":"CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T22:52:00.767804Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.00513"},"observation_digest":"sha256:6973fc56c38d2769f4896a39c5a56309a5280cff093d36180d72c0f1af48b7ff","observation_id":"7bd7d569-e7fe-4cbb-b30f-d89553934dff","resolution":{"observed_at":"2026-08-10T22:52:00.767804Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T22:41:15.174907Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01031","last_updated":"2025-05-08T01:07:15Z","snapshot_observed_at":"2026-08-17T05:53:00.464127Z","submitted_at":"2025-01-02T03:26:13Z","title":"ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T22:41:15.174907Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.01031"},"observation_digest":"sha256:b3ad5b655793afbed3ab604a53a2fa147eedf064f9fad8825df6e13290fba136","observation_id":"85505580-11c7-4304-a5d9-c1aa5d469ada","resolution":{"observed_at":"2026-08-10T22:41:15.174907Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T22:19:55.682063Z","title":"DeepSeek-V3: An ultra-large open-source AI model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.02156","last_updated":"2025-01-08T14:26:51Z","snapshot_observed_at":"2026-08-15T12:41:53.750860Z","submitted_at":"2025-01-04T01:45:32Z","title":"The Race to Efficiency: A New Perspective on AI Scaling Laws","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T22:19:55.682063Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.02156"},"observation_digest":"sha256:80978279ae64e2f0170a345ec723afb636f07076d315e0adf131c14bc58641b5","observation_id":"52e1fbf3-6ca6-41fd-b332-1b5d4f98ee8a","resolution":{"observed_at":"2026-08-10T22:19:55.682063Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T21:57:33.012498Z","title":"Deepseek-v3 technical report, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03491","last_updated":"2025-06-17T18:44:37Z","snapshot_observed_at":"2026-08-13T16:22:57.799819Z","submitted_at":"2025-01-07T03:21:17Z","title":"Can LLMs Ask Good Questions?","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T21:57:33.012498Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.03491"},"observation_digest":"sha256:bf460908a35cdbce84e49498f6858780eb4c6de37dabdcc702040f05b1e4b137","observation_id":"5ff070ae-521e-49c7-9adb-57c5b802be34","resolution":{"observed_at":"2026-08-10T21:57:33.012498Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T21:46:30.872415Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.04211","last_updated":"2025-01-10T14:36:48Z","snapshot_observed_at":"2026-08-15T14:46:08.718885Z","submitted_at":"2025-01-08T01:11:17Z","title":"CURing Large Models: Compression via CUR Decomposition","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T21:46:30.872415Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.04211"},"observation_digest":"sha256:4c7b5932f4607e08ad9ce98032704940e26d28112d8a5aeaa18b14aa7e52dbf3","observation_id":"12958c37-73dc-4faa-b3d5-964fa3e43f32","resolution":{"observed_at":"2026-08-10T21:46:30.872415Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2501.05067","last_updated":"2026-04-20T07:42:35Z","snapshot_observed_at":"2026-08-17T12:15:46.752690Z","submitted_at":"2025-01-09T08:43:57Z","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-23T06:01:00.775721Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.05067"},"observation_digest":"sha256:849cc63127c85f53655bf0e7eac9113d6593a03b94233e47247bd22582947ca8","observation_id":"5751cac5-3ecf-476c-bdeb-718513c4ad81","resolution":{"observed_at":"2026-05-23T06:02:37.317671Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T20:43:45.363393Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.07482","last_updated":"2025-05-20T17:09:53Z","snapshot_observed_at":"2026-08-16T18:33:37.341055Z","submitted_at":"2025-01-13T16:58:32Z","title":"TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:43:45.363393Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.07482"},"observation_digest":"sha256:a17213e01c1fd88530e9a6f99f4cc653b837495ffb7ed147a7c987713b8fd68a","observation_id":"d8a3cec9-c06d-4f1f-8f18-1d0aa2b3d7c1","resolution":{"observed_at":"2026-08-10T20:43:45.363393Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T20:44:16.911696Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.07674","last_updated":"2025-06-20T03:44:20Z","snapshot_observed_at":"2026-08-14T02:20:26.429445Z","submitted_at":"2025-01-13T20:13:59Z","title":"CDS: Knowledge Component-Driven Data Synthesis Guided by Cognitive Diagnosis Theory","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T20:44:16.911696Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.07674"},"observation_digest":"sha256:dff1fd03b463529d4a384732e732f197034aeee9f1b63f894790f54ae565eaf7","observation_id":"0033d20c-6c9e-4382-a9e0-a84e4168f0fc","resolution":{"observed_at":"2026-08-10T20:44:16.911696Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T20:41:57.782233Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.07721","last_updated":"2025-01-13T22:14:45Z","snapshot_observed_at":"2026-08-17T02:55:32.460535Z","submitted_at":"2025-01-13T22:14:45Z","title":"LLMic: Romanian Foundation Language Model","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:41:57.782233Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.07721"},"observation_digest":"sha256:c19d7e13856904d1be4e068f58eec7cd195f4f580fab0e029fc61ce63c4e8911","observation_id":"5c32bcf4-9d58-4b2a-8a56-225864a7d8a6","resolution":{"observed_at":"2026-08-10T20:41:57.782233Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T20:14:59.010148Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.09223","last_updated":"2025-06-15T13:24:11Z","snapshot_observed_at":"2026-08-15T10:26:22.406164Z","submitted_at":"2025-01-16T01:03:56Z","title":"Foundations of Large Language Models","version":2},"reference_index":150,"source":"arxiv_source","source_observed_at":"2026-08-10T20:14:59.010148Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.09223"},"observation_digest":"sha256:1e9a908b6fc6880e94717db63469f1e803d9d55278b8c1cdb2168c704260625d","observation_id":"1e19283d-a70a-4efa-affa-08724f50f409","resolution":{"observed_at":"2026-08-10T20:14:59.010148Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T20:03:00.255792Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.09484","last_updated":"2025-03-11T06:54:09Z","snapshot_observed_at":"2026-08-16T19:13:22.692176Z","submitted_at":"2025-01-16T11:41:14Z","title":"Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T20:03:00.255792Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.09484"},"observation_digest":"sha256:98c20894792a214918c8a0431476dc561199888ce8cd23a3b0b281b1bdd539ea","observation_id":"e990ceda-3eb0-4f31-905e-88d6eedbd3f2","resolution":{"observed_at":"2026-08-10T20:03:00.255792Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T17:51:06.951937Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.11833","last_updated":"2025-01-21T02:29:15Z","snapshot_observed_at":"2026-08-17T08:37:43.010104Z","submitted_at":"2025-01-21T02:29:15Z","title":"Is your LLM trapped in a Mental Set? Investigative study on how mental sets affect the reasoning capabilities of LLMs","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T17:51:06.951937Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.11833"},"observation_digest":"sha256:655f1af33b4fe1ee78661f6591b6a82bd9d9c1209c89b040057b1e4951d81e30","observation_id":"131930ce-7202-41cd-abb1-8f8ad6b1b823","resolution":{"observed_at":"2026-08-10T17:51:06.951937Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T21:41:21.630869Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12399","last_updated":"2025-07-09T03:59:49Z","snapshot_observed_at":"2026-08-14T21:27:08.089198Z","submitted_at":"2025-01-08T07:50:50Z","title":"FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:41:21.630869Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.12399"},"observation_digest":"sha256:6a48e56dd54fe0cb9ddf2e622608f5b6749e5f58af1199255217f1c4e2c617b8","observation_id":"65300832-b983-49f9-902b-c3d9cfb7fc64","resolution":{"observed_at":"2026-08-10T21:41:21.630869Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2501.13106","last_updated":"2025-06-03T03:33:14Z","snapshot_observed_at":"2026-08-13T11:53:19.464291Z","submitted_at":"2025-01-22T18:59:46Z","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-11T01:19:59.603343Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.13106"},"observation_digest":"sha256:a14f28365ed025e3f7a6c5d8df02081ab5f4c638b974163ba90e36b24aaf06aa","observation_id":"076187a3-1f86-441b-82d2-b6145164ea09","resolution":{"observed_at":"2026-05-11T01:19:59.863169Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T16:17:33.624581Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13391","last_updated":"2025-01-23T05:24:18Z","snapshot_observed_at":"2026-08-16T10:05:57.315310Z","submitted_at":"2025-01-23T05:24:18Z","title":"Can Large Language Models Understand Preferences in Personalized Recommendation?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T16:17:33.624581Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.13391"},"observation_digest":"sha256:05f774cff611493d836452d22caae9ba6b95eec7e212b3a5dd535d74cb7d0c2f","observation_id":"2c7e6ccd-4b61-40ba-a0dc-12f0e0b1ae21","resolution":{"observed_at":"2026-08-10T16:17:33.624581Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T16:13:36.185222Z","title":"Deepseek-v3 techni- cal report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13411","last_updated":"2025-01-23T06:33:05Z","snapshot_observed_at":"2026-08-15T17:00:20.776391Z","submitted_at":"2025-01-23T06:33:05Z","title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T16:13:36.185222Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.13411"},"observation_digest":"sha256:71c3c6df70c7b2447739e49b2d6c3d0eada5749254a5167bccf9d813f2fdce6c","observation_id":"e4fe04df-b524-43c0-831e-09432397544d","resolution":{"observed_at":"2026-08-10T16:13:36.185222Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T16:15:39.456266Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13428","last_updated":"2026-06-01T01:21:19Z","snapshot_observed_at":"2026-08-15T21:59:40.323843Z","submitted_at":"2025-01-23T07:21:08Z","title":"Softplus Attention with Re-weighting Boosts Length Extrapolation in Large Language Models","version":6},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T16:15:39.456266Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.13428"},"observation_digest":"sha256:f502a34899a5775ac2ff8995e704c0622158b4ec42e469e447f9197483520599","observation_id":"e7531074-dbdf-4d2c-a97b-48e9c4b45065","resolution":{"observed_at":"2026-08-10T16:15:39.456266Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T15:42:43.984481Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13731","last_updated":"2025-01-23T15:04:22Z","snapshot_observed_at":"2026-08-11T04:10:47.517119Z","submitted_at":"2025-01-23T15:04:22Z","title":"Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T15:42:43.984481Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.13731"},"observation_digest":"sha256:46260fbf3fb7b1e81ff6d87bcfa9e12c74f56d2571efd8ba6e19bc14810159cd","observation_id":"43dcfc53-45c4-46d8-8420-0dbad8405940","resolution":{"observed_at":"2026-08-10T15:42:43.984481Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T14:41:39.156151Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15087","last_updated":"2025-05-19T03:34:25Z","snapshot_observed_at":"2026-08-16T01:30:38.656357Z","submitted_at":"2025-01-25T05:30:58Z","title":"Multi-Grained Patch Training for Efficient LLM-based Recommendation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T14:41:39.156151Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.15087"},"observation_digest":"sha256:ed67cec22a20270c98175fc45ad151c6a252d46f958cad0bff29769c8503b14f","observation_id":"eb6a7ce0-06db-468e-a011-4adb987d3888","resolution":{"observed_at":"2026-08-10T14:41:39.156151Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T14:21:24.232256Z","title":"arXiv preprint arXiv:2412.19437","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15451","last_updated":"2025-05-20T06:52:00Z","snapshot_observed_at":"2026-08-10T14:14:28.540107Z","submitted_at":"2025-01-26T08:45:37Z","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:24.232256Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.15451"},"observation_digest":"sha256:0ee5983ccbb860dce3f45753e8957e957d8ba802e3ee02a97d1615f0496e24e7","observation_id":"5a307099-4009-4049-87bb-7248b4f65b60","resolution":{"observed_at":"2026-08-10T14:21:24.232256Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T13:45:09.687618Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16155","last_updated":"2025-08-11T07:52:42Z","snapshot_observed_at":"2026-08-15T15:12:56.441198Z","submitted_at":"2025-01-27T15:49:24Z","title":"CITYWALK: Enhancing LLM-Based C++ Unit Test Generation via Project-Dependency Awareness and Language-Specific Knowledge","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T13:45:09.687618Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.16155"},"observation_digest":"sha256:5bc7214968c69979680de71915987bd6af1c7ac614a2a405697e0d5faa3bfd14","observation_id":"b6b41f06-ddc8-4565-a88e-1901afc1a1ee","resolution":{"observed_at":"2026-08-10T13:45:09.687618Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T12:52:08.915129Z","title":"DeepSeek-V3 Technical Report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16500","last_updated":"2025-01-27T21:02:38Z","snapshot_observed_at":"2026-08-16T21:53:07.330217Z","submitted_at":"2025-01-27T21:02:38Z","title":"Towards Frontier Safety Policies Plus","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T12:52:08.915129Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.16500"},"observation_digest":"sha256:2779585e67e0e6442b47a9fc7d23f4ba528478012cf3784cd7a3f510c95af339","observation_id":"311c7064-6913-4931-ae11-e5609d423d40","resolution":{"observed_at":"2026-08-10T12:52:08.915129Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T11:55:54.605909Z","title":"arXiv preprint arXiv:2412.19437 (2024), https://arxiv.org/abs/2412.19437","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16616","last_updated":"2025-01-28T01:26:22Z","snapshot_observed_at":"2026-08-13T08:22:53.035293Z","submitted_at":"2025-01-28T01:26:22Z","title":"Few-Shot Optimized Framework for Hallucination Detection in Resource-Limited NLP Systems","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T11:55:54.605909Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.16616"},"observation_digest":"sha256:572f9151b2ba8e31727725023eb3396753c3966da2f9ad42f4ae1a5ec4161468","observation_id":"3fabc616-ec12-468f-a680-0e53ab9c3810","resolution":{"observed_at":"2026-08-10T11:55:54.605909Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-10T05:28:04.785484Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16975","last_updated":"2025-05-23T08:32:07Z","snapshot_observed_at":"2026-08-16T10:44:18.951863Z","submitted_at":"2025-01-28T14:15:42Z","title":"Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T05:28:04.785484Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.16975"},"observation_digest":"sha256:a6ae08a1ff178565cb1de055c0526916dd19eab95d4c3970503d74c528cae653","observation_id":"a92c7303-5d98-45d0-838c-5856cb7e068f","resolution":{"observed_at":"2026-08-10T05:28:04.785484Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T23:17:19.720712Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.18512","last_updated":"2025-01-30T17:23:50Z","snapshot_observed_at":"2026-08-17T01:10:02.239643Z","submitted_at":"2025-01-30T17:23:50Z","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T23:17:19.720712Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.18512"},"observation_digest":"sha256:748353f7245f5f6652d93e84b2233956dd0fb425a21e4c53404a299804199893","observation_id":"f7132edd-9506-474e-a247-546d6150db42","resolution":{"observed_at":"2026-08-09T23:17:19.720712Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2501.19201","last_updated":"2026-05-04T05:23:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-31T15:10:29Z","title":"Efficient Reasoning with Hidden Thinking","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-23T04:45:38.608009Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.19201"},"observation_digest":"sha256:c8ca9006a1ff0f4c4f36c2d7afa923bd9d8b9a0baf4b0e3839292c0bda5a0b62","observation_id":"c9b73896-490b-4114-bf22-b89138d1044d","resolution":{"observed_at":"2026-05-23T04:47:33.618476Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T20:34:09.120975Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.19337","last_updated":"2026-07-23T01:56:42Z","snapshot_observed_at":"2026-08-10T04:25:39.129278Z","submitted_at":"2025-01-31T17:36:12Z","title":"Token-Level Entropy Reveals Demographic Disparities in Large Language Models","version":5},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T20:34:09.120975Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2501.19337"},"observation_digest":"sha256:de8688fd21db372ae4091510b1854937ffe1a05dc3e4f84311fe88d7ed2473b4","observation_id":"e80ed96b-742e-4a51-9e74-7e215efa2225","resolution":{"observed_at":"2026-08-09T20:34:09.120975Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T19:40:09.950221Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00281","last_updated":"2025-05-24T02:54:56Z","snapshot_observed_at":"2026-08-14T00:39:22.575092Z","submitted_at":"2025-02-01T02:36:14Z","title":"Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T19:40:09.950221Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.00281"},"observation_digest":"sha256:90f8e16d0c4021f9b96b345bee7aaf79953e8d70414f62c8b7727d1fbea3fcaa","observation_id":"fa7dafaf-4d6b-46be-baf8-2b81dce23543","resolution":{"observed_at":"2026-08-09T19:40:09.950221Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T18:51:12.535773Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00500","last_updated":"2025-02-04T15:19:12Z","snapshot_observed_at":"2026-08-13T15:10:28.704658Z","submitted_at":"2025-02-01T17:40:11Z","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T18:51:12.535773Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.00500"},"observation_digest":"sha256:dc03b02b4a3dd064c2ac9656c9d76eeb1a5448bdb774f6ef966ae2e85c4f8533","observation_id":"e8b3f769-5d16-49d0-8aba-b3a01f2205fa","resolution":{"observed_at":"2026-08-09T18:51:12.535773Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T18:02:12.410562Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00722","last_updated":"2025-06-05T07:54:05Z","snapshot_observed_at":"2026-08-14T13:57:55.592899Z","submitted_at":"2025-02-02T08:44:43Z","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T18:02:12.410562Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.00722"},"observation_digest":"sha256:fae273656eb38450a6da5b18490b40b9940f7227ddcd1a25d1f3df274f1fd49f","observation_id":"1b734057-3f44-4891-af51-ce931e65f5ac","resolution":{"observed_at":"2026-08-09T18:02:12.410562Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T16:47:23.542920Z","title":"Deepseek-v3 technical report, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01070","last_updated":"2025-08-25T06:01:25Z","snapshot_observed_at":"2026-08-12T16:29:34.108900Z","submitted_at":"2025-02-03T05:26:22Z","title":"An Inquiry into Datacenter TCO for LLM Inference with FP8","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T16:47:23.542920Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01070"},"observation_digest":"sha256:1ebcd2cad18c4ddee788cf4eeeebaa6e86453af6671e19c73aa460bc418e8960","observation_id":"e40b0cc7-4855-4ceb-8b2e-62c105ff3c4c","resolution":{"observed_at":"2026-08-09T16:47:23.542920Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T16:35:28.422266Z","title":"DeepSeek- v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01118","last_updated":"2025-02-03T07:19:05Z","snapshot_observed_at":"2026-08-16T09:44:37.526574Z","submitted_at":"2025-02-03T07:19:05Z","title":"Large Language Model-Enhanced Multi-Armed Bandits","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T16:35:28.422266Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01118"},"observation_digest":"sha256:604b1685f8c4fa793b81a6741da980813480d253f6ed98479da7cac4f5466fa7","observation_id":"e19a04e7-8d86-4d17-8419-f2bd12ee4e85","resolution":{"observed_at":"2026-08-09T16:35:28.422266Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T16:18:41.078851Z","title":"terminal cost","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01208","last_updated":"2025-06-20T10:54:05Z","snapshot_observed_at":"2026-08-16T10:10:26.213081Z","submitted_at":"2025-02-03T09:59:32Z","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","version":3},"reference_index":124,"source":"pdf_text","source_observed_at":"2026-08-09T16:18:41.078851Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01208"},"observation_digest":"sha256:ba8d4cd88db693d804eca80ebe8093ec609ee848cbfb94d803d7a39499f26189","observation_id":"88f2dfbc-6ae2-4a65-9cad-c4611684a46a","resolution":{"observed_at":"2026-08-09T16:18:41.078851Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T16:10:24.939025Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01243","last_updated":"2025-02-03T11:04:51Z","snapshot_observed_at":"2026-08-13T15:01:44.141448Z","submitted_at":"2025-02-03T11:04:51Z","title":"OphthBench: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Ophthalmology","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-09T16:10:24.939025Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01243"},"observation_digest":"sha256:2b8fc5c9bba5a594ee85c0ce89f51baaf13b1e88a0cc5f796724bf6da68b4411","observation_id":"9cda63fa-7b6c-4bb5-9f13-9021b92ca758","resolution":{"observed_at":"2026-08-09T16:10:24.939025Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T15:05:03.746335Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01540","last_updated":"2025-02-03T17:17:26Z","snapshot_observed_at":"2026-08-15T22:40:52.033412Z","submitted_at":"2025-02-03T17:17:26Z","title":"What is a Number, That a Large Language Model May Know It?","version":1},"reference_index":1966,"source":"pdf_text","source_observed_at":"2026-08-09T15:05:03.746335Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01540"},"observation_digest":"sha256:0c422a1cca6a16ca9a6b002110bbfcd8307dad0b4b5b2e682664ebacf77d5f4e","observation_id":"7a6945d2-7741-406e-9ba6-183fb5576d04","resolution":{"observed_at":"2026-08-09T15:05:03.746335Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T19:34:42.831914Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01662","last_updated":"2025-05-29T15:20:23Z","snapshot_observed_at":"2026-08-14T10:54:27.500239Z","submitted_at":"2025-02-01T05:22:11Z","title":"Fast Large Language Model Collaborative Decoding via Speculation","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T19:34:42.831914Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01662"},"observation_digest":"sha256:d94237bd92101c382a75154a657cf03a2cd1d99d05fcdbb5a12aeba12a75e87f","observation_id":"48bfff0f-49b9-468d-981c-56d669518c22","resolution":{"observed_at":"2026-08-09T19:34:42.831914Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.01941","last_updated":"2026-05-12T08:04:27Z","snapshot_observed_at":"2026-08-14T08:23:35.104382Z","submitted_at":"2025-02-04T02:23:06Z","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-23T04:15:36.906263Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.01941"},"observation_digest":"sha256:3b5325909fa0130266e0de027e9b8bd6358704d71ddda76349319a36b7bdedf0","observation_id":"5292182d-541b-4b05-ad58-94f2257098e7","resolution":{"observed_at":"2026-05-23T04:17:31.146691Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T11:53:29.353746Z","title":"DeepSeek-V3 Technical Report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02523","last_updated":"2025-02-07T15:02:21Z","snapshot_observed_at":"2026-08-16T01:51:50.738591Z","submitted_at":"2025-02-04T17:45:32Z","title":"Brief analysis of DeepSeek R1 and its implications for Generative AI","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T11:53:29.353746Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.02523"},"observation_digest":"sha256:2d6b74cf5e22e5d8a5dc9ccebf372ed052e8c8d97939f6aa80cbd140cd57b228","observation_id":"c972d878-e692-4cd8-b891-31ea59d79358","resolution":{"observed_at":"2026-08-09T11:53:29.353746Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T11:34:57.012110Z","title":"Deepseek- v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02671","last_updated":"2025-02-04T19:26:28Z","snapshot_observed_at":"2026-08-12T19:27:02.778679Z","submitted_at":"2025-02-04T19:26:28Z","title":"On Teacher Hacking in Language Model Distillation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T11:34:57.012110Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.02671"},"observation_digest":"sha256:e328534d80e161a5164cb0a1be29294f880f5f739bb26026667e92408c6f5e81","observation_id":"380e2e34-d2b9-4b37-8a5c-2a7648de7c00","resolution":{"observed_at":"2026-08-09T11:34:57.012110Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.02970","last_updated":"2026-04-02T13:28:28Z","snapshot_observed_at":"2026-08-14T07:57:53.156590Z","submitted_at":"2025-02-05T08:11:23Z","title":"Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-23T04:27:59.317818Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.02970"},"observation_digest":"sha256:7548f8894cecfbe5d6e79fd2dd5f3c2012686f820802646f7d694c7a5847277e","observation_id":"1452674c-96c5-456b-998f-a4fc73d4b3f0","resolution":{"observed_at":"2026-05-23T04:32:34.085554Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T05:48:07.656856Z","title":"Deepseek- v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03147","last_updated":"2025-02-05T13:16:41Z","snapshot_observed_at":"2026-08-17T08:23:37.706260Z","submitted_at":"2025-02-05T13:16:41Z","title":"Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T05:48:07.656856Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.03147"},"observation_digest":"sha256:063b2545f30cbc64f76567fa7cb6ed46cdfd0a900f3c232c8a056f9c1c5c53f0","observation_id":"36a506c9-99ec-41e2-bd38-4364cce233ab","resolution":{"observed_at":"2026-08-09T05:48:07.656856Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T04:45:34.586462Z","title":"DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03461","last_updated":"2025-02-05T18:58:19Z","snapshot_observed_at":"2026-08-10T16:22:07.766175Z","submitted_at":"2025-02-05T18:58:19Z","title":"Do Large Language Model Benchmarks Test Reliability?","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T04:45:34.586462Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.03461"},"observation_digest":"sha256:8a699a2e4f28ceb9e67fbf80b6dd4f0823fe844ea6cf8235a29cd26ce2f9a02f","observation_id":"82bdb3d6-3b3f-4600-ab45-79296c2a0103","resolution":{"observed_at":"2026-08-09T04:45:34.586462Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T00:49:12.156833Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03793","last_updated":"2025-02-10T14:08:19Z","snapshot_observed_at":"2026-08-14T20:03:22.255390Z","submitted_at":"2025-02-06T05:47:37Z","title":"It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T00:49:12.156833Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.03793"},"observation_digest":"sha256:d4c67adcc04bf0cfe6173471bc81b0629589b16cefeab3f8be89570e89ee57db","observation_id":"9d14c827-305c-4ec8-827a-3e4a1f7c6089","resolution":{"observed_at":"2026-08-09T00:49:12.156833Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.03814","last_updated":"2026-05-03T03:24:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-06T06:52:14Z","title":"Large Language Models for Multi-Robot Systems: A Survey","version":5},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-23T04:32:05.138744Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.03814"},"observation_digest":"sha256:c068c4437d6badda2fa73995ea35ce0614e13567c35989adba958486518be189","observation_id":"8a13cc3b-5db4-4ec4-b93c-0049e19c9991","resolution":{"observed_at":"2026-05-23T04:32:32.164101Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T00:27:31.075403Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.03885","last_updated":"2025-08-04T02:36:49Z","snapshot_observed_at":"2026-08-17T06:56:12.922888Z","submitted_at":"2025-02-06T09:01:24Z","title":"InfiniteHBD: Building Datacenter-Scale High-Bandwidth Domain for LLM with Optical Circuit Switching Transceivers","version":6},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T00:27:31.075403Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.03885"},"observation_digest":"sha256:ee13d13cf76bd58909c1407c617a07cef16f4c22a6fe6495a697d0dfda32e738","observation_id":"46a23293-397f-4d7f-b03c-1a76ad22cb29","resolution":{"observed_at":"2026-08-09T00:27:31.075403Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T23:52:33.684187Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04022","last_updated":"2025-02-06T12:25:16Z","snapshot_observed_at":"2026-08-11T19:55:04.038213Z","submitted_at":"2025-02-06T12:25:16Z","title":"Quantification of Biodiversity from Historical Survey Text with LLM-based Best-Worst Scaling","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T23:52:33.684187Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04022"},"observation_digest":"sha256:ace4f6e4633f30b1deead83fac58ec32e528e5820fd915b3b64943c91616ed14","observation_id":"cab062a9-d0c5-4ae0-b7d7-ee1707ce529c","resolution":{"observed_at":"2026-08-08T23:52:33.684187Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T23:20:01.057079Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04176","last_updated":"2025-04-21T12:02:08Z","snapshot_observed_at":"2026-08-17T10:47:56.823907Z","submitted_at":"2025-02-06T16:07:24Z","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T23:20:01.057079Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04176"},"observation_digest":"sha256:ea583d97b9b75ef2d42e182a45f00bb6ce5168347fedd292dc0cc1e486c7162e","observation_id":"9538a13a-9d2b-4ddf-8226-c174c3ddb07c","resolution":{"observed_at":"2026-08-08T23:20:01.057079Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T22:57:12.708501Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04306","last_updated":"2025-02-06T18:47:49Z","snapshot_observed_at":"2026-08-14T21:16:48.876864Z","submitted_at":"2025-02-06T18:47:49Z","title":"ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T22:57:12.708501Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04306"},"observation_digest":"sha256:4e37acd54d7959182d8f8a222951f69cfe1481e9842ac128c22f48675698187d","observation_id":"9182281b-7a15-4fd4-9b4f-7ffc17c828cd","resolution":{"observed_at":"2026-08-08T22:57:12.708501Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T11:29:21.207722Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04358","last_updated":"2025-05-29T16:46:00Z","snapshot_observed_at":"2026-08-13T11:09:40.360183Z","submitted_at":"2025-02-04T20:47:43Z","title":"Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T11:29:21.207722Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04358"},"observation_digest":"sha256:7564d0f064a7d9929b4cd6973e89d3930316863f079ca2ebebcdbf24990518d6","observation_id":"61edb299-0ff9-4818-b055-d01619502b46","resolution":{"observed_at":"2026-08-09T11:29:21.207722Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T05:28:51.575637Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04375","last_updated":"2025-05-21T09:17:46Z","snapshot_observed_at":"2026-08-17T06:51:22.005276Z","submitted_at":"2025-02-05T15:23:26Z","title":"An Analysis for Reasoning Bias of Language Models with Small Initialization","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T05:28:51.575637Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04375"},"observation_digest":"sha256:eb4ad7320e82d2f06e25ae348b88bac3eee36acc5ee12e6bf207360a371335b3","observation_id":"7d20637e-1d00-4009-a74c-95afaac33a48","resolution":{"observed_at":"2026-08-09T05:28:51.575637Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.04416","last_updated":"2026-04-23T00:51:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-06T14:05:30Z","title":"Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-23T04:08:29.089438Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04416"},"observation_digest":"sha256:3e139eb0ace9b5f8c52fb3bc0cb3760e5fc3512e3581ecefd9b9d642ece814fa","observation_id":"21117b2c-ec02-4c3c-b4c4-9cd800c9a037","resolution":{"observed_at":"2026-05-23T04:12:31.120576Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T22:23:28.265727Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04556","last_updated":"2025-02-06T23:10:14Z","snapshot_observed_at":"2026-08-16T12:09:40.316285Z","submitted_at":"2025-02-06T23:10:14Z","title":"TruthFlow: Truthful LLM Generation via Representation Flow Correction","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T22:23:28.265727Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04556"},"observation_digest":"sha256:89beb579cf768bc1480651821eade78b1b80fa6b69b2868f5b59abe90e200f09","observation_id":"c04a9a4f-0fa6-42ba-ade7-812b9f983853","resolution":{"observed_at":"2026-08-08T22:23:28.265727Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T22:03:46.410664Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.04644","last_updated":"2025-07-14T20:06:23Z","snapshot_observed_at":"2026-08-12T17:37:05.160293Z","submitted_at":"2025-02-07T04:08:46Z","title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T22:03:46.410664Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04644"},"observation_digest":"sha256:42513a0d3b3792d49ca968097dbd1a7e08c92322881711477d6de1b64b53f7b0","observation_id":"5631c1a8-bae6-4087-b558-1f239ac15b86","resolution":{"observed_at":"2026-08-08T22:03:46.410664Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.04689","last_updated":"2026-04-16T17:03:43Z","snapshot_observed_at":"2026-08-15T03:49:21.171204Z","submitted_at":"2025-02-07T06:30:33Z","title":"Improving Language Models with Intentional Analysis","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-23T03:44:33.625252Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.04689"},"observation_digest":"sha256:4a30355cca583a4f8f533a6586656935bca9b916fb8af17fa93c82cecff9d9ad","observation_id":"0060660f-055c-4f78-97b3-65748da08df3","resolution":{"observed_at":"2026-05-23T03:45:21.601506Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T20:08:57.409176Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.05159","last_updated":"2025-05-27T16:54:17Z","snapshot_observed_at":"2026-08-16T09:58:13.847234Z","submitted_at":"2025-02-07T18:41:21Z","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T20:08:57.409176Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.05159"},"observation_digest":"sha256:564bcdc27657b35c09bf44f3890e4cb6604bab701efe7eaa42d82f024450b9f2","observation_id":"7d5c5bf9-f9db-43e4-9c49-9eaaaac4dd13","resolution":{"observed_at":"2026-08-08T20:08:57.409176Z","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":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":"2412.19437","doi":"10.1016/j.neucom.2023.127063.url:https://www.sciencedirect","metadata_source":"pith","pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"DeepSeek-V3 Technical Report","venue":"cs.CL","work_id":"57d2791d-2219-4c31-a077-afc04b12a75c","year":2024},"citing_paper":{"arxiv_id":"2502.05171","last_updated":"2025-02-17T17:14:04Z","snapshot_observed_at":"2026-08-15T00:53:48.099058Z","submitted_at":"2025-02-07T18:55:02Z","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-05-12T15:39:40.845703Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.05171"},"observation_digest":"sha256:335aa5fb3f562f22f41f266eec769a568b4401f54b6a8429b332eb2baadc6867","observation_id":"78436f21-3456-4ef8-8f60-8fdb75e71b35","resolution":{"observed_at":"2026-05-12T15:39:41.101561Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-16T12:32:27.721450Z","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":"sha256:5009f902ecd42a18299a4bbbc2e6a743c2bfaa3c1d6fb188d31c2492de5edb60","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"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T16:20:38.261204Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06244","last_updated":"2025-06-04T02:16:01Z","snapshot_observed_at":"2026-08-13T14:09:35.895261Z","submitted_at":"2025-02-10T08:23:05Z","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T16:20:38.261204Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06244"},"observation_digest":"sha256:0d98311d0a062d9a727327b931f0b7e3c331fbcd6631c1a5f54fd8a65fea906c","observation_id":"0ebbc5bc-b4bd-4e9f-b7c8-538b129b2a3b","resolution":{"observed_at":"2026-08-08T16:20:38.261204Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T15:08:34.749990Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06551","last_updated":"2025-02-10T15:19:22Z","snapshot_observed_at":"2026-08-14T20:03:26.462799Z","submitted_at":"2025-02-10T15:19:22Z","title":"Efficient Scientific Full Text Classification: The Case of EICAT Impact Assessments","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T15:08:34.749990Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06551"},"observation_digest":"sha256:d74de3a1fcb99a91cf7a0e9787f844a06a5a7adb63a2ae451d3f6d3586dddae3","observation_id":"a3c27fc1-d4d8-479c-a20d-02eba64c8274","resolution":{"observed_at":"2026-08-08T15:08:34.749990Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T15:05:14.698193Z","title":"Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06572","last_updated":"2025-02-13T07:24:46Z","snapshot_observed_at":"2026-08-17T01:13:00.611056Z","submitted_at":"2025-02-10T15:40:35Z","title":"LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T15:05:14.698193Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06572"},"observation_digest":"sha256:9b304171c7757bb4e8b228a7b03f95beaf58355eb9fe925b59f50a7aa3571365","observation_id":"63663d68-cd9d-4c9c-8be3-f41ef5f6488c","resolution":{"observed_at":"2026-08-08T15:05:14.698193Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T14:27:50.997289Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06781","last_updated":"2025-02-10T18:57:29Z","snapshot_observed_at":"2026-08-16T03:56:33.383172Z","submitted_at":"2025-02-10T18:57:29Z","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T14:27:50.997289Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06781"},"observation_digest":"sha256:7c253cdce0f6bb657cd76e1853cb2f02a7ba3dd278178cdad1d2a0fb33b9283b","observation_id":"292779e5-b639-4409-a57b-e2699deb09de","resolution":{"observed_at":"2026-08-08T14:27:50.997289Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T11:20:02.854961Z","title":"Deitke, M., Clark, C., Lee, S., Tripathi, R., Yang, Y ., Park, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06814","last_updated":"2025-05-25T15:41:21Z","snapshot_observed_at":"2026-08-15T03:31:15.521541Z","submitted_at":"2025-02-04T22:20:20Z","title":"Diffusion Instruction Tuning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T11:20:02.854961Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06814"},"observation_digest":"sha256:b5417a0cfdac0bec51c75e74f7f817deee49c6474124a265bec454bafc6f0af1","observation_id":"fd0b7c91-341b-4bd7-b841-e62f05ec2dd8","resolution":{"observed_at":"2026-08-09T11:20:02.854961Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-09T00:46:59.289400Z","title":"Deepseek-v3 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06838","last_updated":"2025-02-06T05:42:30Z","snapshot_observed_at":"2026-08-09T00:40:51.486239Z","submitted_at":"2025-02-06T05:42:30Z","title":"TorchResist: Open-Source Differentiable Resist Simulator","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T00:46:59.289400Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.06838"},"observation_digest":"sha256:d507675acb1e1bd412fd61ca7741121bd5f61bf2c982c7f04759635182e2f39d","observation_id":"ae10fe3c-79cc-4918-87e7-aa4bc051ff88","resolution":{"observed_at":"2026-08-09T00:46:59.289400Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T13:07:22.479919Z","title":"arXiv preprint arXiv:2412.19437","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07346","last_updated":"2025-04-20T12:19:46Z","snapshot_observed_at":"2026-08-15T11:34:18.364818Z","submitted_at":"2025-02-11T08:17:19Z","title":"BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T13:07:22.479919Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07346"},"observation_digest":"sha256:2b86a6b6e8695641154674922d4f7366a26279248dca394ebdc221ae7c64cdea","observation_id":"bb3e6816-1878-451c-8c04-f8f4646b7cda","resolution":{"observed_at":"2026-08-08T13:07:22.479919Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T13:08:22.723607Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07350","last_updated":"2025-09-06T07:54:06Z","snapshot_observed_at":"2026-08-14T02:41:58.313570Z","submitted_at":"2025-02-11T08:22:12Z","title":"KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T13:08:22.723607Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07350"},"observation_digest":"sha256:3bee0033144353ca58ed62c5fb97798f071f2119e7e133463f6ac348b5531388","observation_id":"84e747ee-853e-4173-a2ac-7ac7671c35ab","resolution":{"observed_at":"2026-08-08T13:08:22.723607Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T12:59:23.323090Z","title":"4 Qianggang Ding, Haochen Shi, and Bang Liu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07393","last_updated":"2025-02-11T09:23:14Z","snapshot_observed_at":"2026-08-15T21:45:35.308181Z","submitted_at":"2025-02-11T09:23:14Z","title":"FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T12:59:23.323090Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07393"},"observation_digest":"sha256:775e946225271014654432c9ad168aa4b2b4a125f075ae79457fee7efe1ac54c","observation_id":"555fb950-d288-47cd-a5bc-05525f05a5f0","resolution":{"observed_at":"2026-08-08T12:59:23.323090Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T12:31:51.949280Z","title":"al: DeepSeek-V3 Technical Report (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07527","last_updated":"2025-06-20T05:18:13Z","snapshot_observed_at":"2026-08-09T17:43:38.820458Z","submitted_at":"2025-02-11T13:08:03Z","title":"Nature Language Model: Deciphering the Language of Nature for Scientific Discovery","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T12:31:51.949280Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07527"},"observation_digest":"sha256:13ffe8fbe43809b60624acd5214142e46791130f92a28b67c269e4078b2379e2","observation_id":"6a81e1ff-3720-4148-92a2-2297c984b8c5","resolution":{"observed_at":"2026-08-08T12:31:51.949280Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T12:19:43.109950Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07578","last_updated":"2025-05-03T04:07:07Z","snapshot_observed_at":"2026-08-13T04:11:45.770763Z","submitted_at":"2025-02-11T14:25:20Z","title":"PIM Is All You Need: A CXL-Enabled GPU-Free System for Large Language Model Inference","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-08T12:19:43.109950Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07578"},"observation_digest":"sha256:7f6298b59a2767fccf9af46a31a7bfa074c7b7422d2f3cae37802d8ed241f047","observation_id":"7f709682-02b2-49d6-829d-af86e7374b5a","resolution":{"observed_at":"2026-08-08T12:19:43.109950Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T12:07:05.005543Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07640","last_updated":"2025-04-19T13:53:05Z","snapshot_observed_at":"2026-08-15T13:54:00.996017Z","submitted_at":"2025-02-11T15:27:35Z","title":"Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T12:07:05.005543Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07640"},"observation_digest":"sha256:5005b7f1996ced32c6614f4c4f35d0348e44f9b30f73217250cd68e1baf72819","observation_id":"252bd5cf-8d13-49d8-ace9-9794637aebda","resolution":{"observed_at":"2026-08-08T12:07:05.005543Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T11:40:22.629463Z","title":"Liu, et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07772","last_updated":"2025-02-11T18:56:20Z","snapshot_observed_at":"2026-08-08T11:35:09.604915Z","submitted_at":"2025-02-11T18:56:20Z","title":"Automatic Robot Task Planning by Integrating Large Language Model with Genetic Programming","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T11:40:22.629463Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07772"},"observation_digest":"sha256:9ba803ffb54d3f536845dae3ea793d9a344e49494c9af4c3fb64afc5640a96d0","observation_id":"6790b94a-e77b-4cc6-8242-1cb83a8ab86e","resolution":{"observed_at":"2026-08-08T11:40:22.629463Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T12:59:38.681544Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07846","last_updated":"2025-02-11T09:51:25Z","snapshot_observed_at":"2026-08-08T12:49:23.882573Z","submitted_at":"2025-02-11T09:51:25Z","title":"Memory Analysis on the Training Course of DeepSeek Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T12:59:38.681544Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07846"},"observation_digest":"sha256:7c6d16f0b63e9312bacb11b5cc1835726b79584c5da66b9c931362bd195fc08e","observation_id":"09d9dc3f-e77c-4f6f-b7a9-556239caeadf","resolution":{"observed_at":"2026-08-08T12:59:38.681544Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T11:48:01.102517Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07864","last_updated":"2025-06-12T11:45:57Z","snapshot_observed_at":"2026-08-10T11:58:20.177769Z","submitted_at":"2025-02-11T18:20:18Z","title":"TransMLA: Multi-Head Latent Attention Is All You Need","version":5},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T11:48:01.102517Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.07864"},"observation_digest":"sha256:700c40b01356afbd2b922d87d1ba5aeb0c3050bd7e359273cd6edf3544eac126","observation_id":"5b88a6ef-0185-4862-bd57-22afcac7d2fe","resolution":{"observed_at":"2026-08-08T11:48:01.102517Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T10:25:12.998707Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08127","last_updated":"2025-06-14T03:19:54Z","snapshot_observed_at":"2026-08-17T02:33:08.589106Z","submitted_at":"2025-02-12T05:13:04Z","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T10:25:12.998707Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08127"},"observation_digest":"sha256:21f1d88fd07eddc823f167802ea5df29978a926acc8459e15856a6473669b841","observation_id":"8d364605-829e-46e2-a240-aea2647b6864","resolution":{"observed_at":"2026-08-08T10:25:12.998707Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T10:26:45.463846Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-15T06:50:09.744191Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.463846Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:ef39e6a0293bafcc74676370ee4710eccb713e5b5992dd4a8f290d5d39fb294d","observation_id":"2786401a-3b35-43b9-adb6-26099075eb8a","resolution":{"observed_at":"2026-08-08T10:26:45.463846Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T05:44:10.185662Z","title":"Deepseek-v3 technical report, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08298","last_updated":"2025-02-12T10:58:57Z","snapshot_observed_at":"2026-08-11T21:19:49.270749Z","submitted_at":"2025-02-12T10:58:57Z","title":"Improving Existing Optimization Algorithms with LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T05:44:10.185662Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08298"},"observation_digest":"sha256:3ab742ae8b825c24a2c192c02e33cea6f06eb9755da456547380edf28a5404d5","observation_id":"ffbf2ab4-f552-4b1e-a991-c0f243eba732","resolution":{"observed_at":"2026-08-08T05:44:10.185662Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T05:20:20.492413Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08395","last_updated":"2025-09-10T10:08:08Z","snapshot_observed_at":"2026-08-16T06:39:25.308021Z","submitted_at":"2025-02-12T13:37:03Z","title":"IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T05:20:20.492413Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08395"},"observation_digest":"sha256:5fa0511bf3ea30717a77d1c4029f277d81d06add70399b190631ebd560501a26","observation_id":"4ff52adb-7b33-43e9-ba3a-54abf805112c","resolution":{"observed_at":"2026-08-08T05:20:20.492413Z","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":"2026-08-15T17:27:11.980940Z","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":"2026-08-08T04:54:39.280782Z","title":"Deepseek-v3 technical report.arXiv preprint arXiv:2412.19437,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.08524","last_updated":"2025-02-12T16:00:11Z","snapshot_observed_at":"2026-08-14T07:35:42.261374Z","submitted_at":"2025-02-12T16:00:11Z","title":"LLM Pretraining with Continuous Concepts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T04:54:39.280782Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2502.08524"},"observation_digest":"sha256:cbdb04c652e2d669d8ce5fe74f8d87be7532feaa3109ccabbd510f28d0fb0700","observation_id":"6995f843-6bb6-462c-93e1-aff7e85b49e4","resolution":{"observed_at":"2026-08-08T04:54:39.280782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.19437/citation-record","integrity":"/paper/2412.19437/integrity","json":"/paper/2412.19437/citation-record.json","paper":"/paper/2412.19437"},"outbound":[],"paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T17:27:11.980940Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 100 inbound Pith citation observations for arXiv:2412.19437."}