{"as_of":"2026-08-04T01:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6046f3a7dfc0554fa05e9e3a136ed6db26a8aa5f4bb8ca2967e196ffb295894c","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T16:11:25.023880Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.19349/citation-record","integrity":"/paper/2607.19349/integrity","json":"/paper/2607.19349/citation-record.json","paper":"/paper/2607.19349"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.160373Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.160373Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:ccb283098f42babb14a38442e461ad608b4c9e2b0ad61a25d46a8a30e26b9c9d","observation_id":"94e0d9db-14f6-4fc9-a3b6-d347d4f34262","resolution":{"observed_at":"2026-08-02T16:11:21.160373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.227514Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.227514Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:ee43d63a11a5b0e41cb4ecb05d360a5d34f8619b2c35434fd59483b85f2be62a","observation_id":"87220510-7364-4e1e-9363-dea846e2020c","resolution":{"observed_at":"2026-08-02T16:11:21.227514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.393859Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.393859Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:5c9e0471056d95121f72ccaf4a7fa5865b4d59b5d19a0644ae52e4537a59baa6","observation_id":"8484de09-1552-422d-9aa1-1f59e7c639e2","resolution":{"observed_at":"2026-08-02T16:11:21.393859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05176","last_updated":"2023-05-09T05:11:02Z","snapshot_observed_at":"2026-07-31T18:33:34.529799Z","submitted_at":"2023-05-09T05:11:02Z","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05176","snapshot_observed_at":"2026-08-02T16:11:21.450783Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.450783Z"},"links":{"cited_paper":"/paper/2305.05176","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:7eb2b9ba78dda8bf4af6962a1267c966096f81d97604bc0dc6aed9f2bbb0ef5e","observation_id":"f08b317a-dc96-4def-ba05-ed3062dd38a9","resolution":{"observed_at":"2026-08-02T16:11:21.450783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.531266Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.531266Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:a5cc9da9fec35df76a27de2158c0042161b944b7cb903f7934f7262b7730049d","observation_id":"a4da20ee-fc8f-4f82-aba4-580d135c1131","resolution":{"observed_at":"2026-08-02T16:11:21.531266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.678343Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.678343Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:48f3a6b093362f1e5b051c015b12b47919d932bbb56492ab335cea9fb7e29695","observation_id":"4ebe57b1-df91-40cd-b490-7906e9ab631c","resolution":{"observed_at":"2026-08-02T16:11:21.678343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.787003Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.787003Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:6642a546d2af76a1ee80e1ec8c2dca59b5f28c66f0eeab6ab3609d2b8f3d9a60","observation_id":"fe1613ba-e3f3-4371-890d-855870344906","resolution":{"observed_at":"2026-08-02T16:11:21.787003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-02T16:11:21.880509Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.880509Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:b71074b467568c45ca90986e5dcec2e1367848c53cee9c05f45c784f18f159ee","observation_id":"443434bc-c9f0-4101-8b9e-4bcbcb8dbaeb","resolution":{"observed_at":"2026-08-02T16:11:21.880509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.comnet.2016.03.024","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:13:35.365012Z","title":"Gonçalves, Idilio Drago, Alex B","venue":null,"work_id":"a355c2c9-936d-4e12-b9dc-d7c5f1d255d8","year":2016},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.992117Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:e59260a9b9e7b180e3c6611583565d0c7045f2577f552e5df9d53cab83669cc9","observation_id":"d8601c5d-d8c8-4fef-a12d-3654f4eaea70","resolution":{"observed_at":"2026-08-02T16:13:35.495937Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.079408Z","title":"2011.Negative binomial regression","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.079408Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:fb8eec4c5bb4af5c7015edd842bf532601de30b160527b5787888697715cb86a","observation_id":"2960a6de-4126-4430-a883-2cac18e2726a","resolution":{"observed_at":"2026-08-02T16:11:22.079408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.173176Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.173176Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:b996e0942356c34a5d6d987077465568a395e10a7181b635561de3db467fe478","observation_id":"186713d6-b58a-4db6-9b67-2c7849b89546","resolution":{"observed_at":"2026-08-02T16:11:22.173176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.287600Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.287600Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:d5912fc0744a9dfad2520e202492d51fd9867cae1c434061e7e872fa20eff398","observation_id":"bbf4848f-ad16-44cb-adfe-94931b5c84f8","resolution":{"observed_at":"2026-08-02T16:11:22.287600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.406799Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.406799Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:061fbe82a29888b21aa68cac42671a59db9870335d3ef307735e2860dd1d9ef7","observation_id":"ed8274c6-89bd-48a7-90b1-278bf435cb21","resolution":{"observed_at":"2026-08-02T16:11:22.406799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.20534","last_updated":"2026-02-03T04:57:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-28T05:35:43Z","title":"Kimi K2: Open Agentic Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.20534","snapshot_observed_at":"2026-08-02T16:11:22.525320Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.525320Z"},"links":{"cited_paper":"/paper/2507.20534","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:82a769c2b0271b8c52967eeafad4e240842d956bbac9f23416e05a16b6058764","observation_id":"1649053b-e8f9-4b56-907e-28b9a4f41052","resolution":{"observed_at":"2026-08-02T16:11:22.525320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.742394Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.742394Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:55ae136aec41869c977552f90327ea77e54fe8947d6f6c6f7e34844e7d1e8704","observation_id":"4bfdf309-cd7e-4725-aa4d-96201482ffe1","resolution":{"observed_at":"2026-08-02T16:11:22.742394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:22.915750Z","title":"Gonzalez, and Ion Sto- ica","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:22.915750Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:35dcbf352fde860fb681d67a8f4b2e4db7f0b5092fdb7bc72d20f93b669337cb","observation_id":"30788554-7a3e-46e5-beae-b569a78a4307","resolution":{"observed_at":"2026-08-02T16:11:22.915750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.040053Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.040053Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:b36e5dfde3eb5104529aadab065a6e75d84a25fd9c801ca050b69ba76040e87d","observation_id":"21fcfb0f-65ea-4c9d-b9fe-a22e97318718","resolution":{"observed_at":"2026-08-02T16:11:23.040053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.218864Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.218864Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:3cf508e24f6bb952c58e9095b916e69e49e6bc893568f4bc0e2eaaf87c8f650b","observation_id":"ce55d7a5-e695-469d-9580-4800a4aaea7f","resolution":{"observed_at":"2026-08-02T16:11:23.218864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.420629Z","title":"Gonzalez, M","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.420629Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:c72fe60970130826c11dfba924e9d7b7bc45ae635d931dacd6e337fbf18cc9a2","observation_id":"09c7c0de-6259-42ed-96c0-9b1bca7021bd","resolution":{"observed_at":"2026-08-02T16:11:23.420629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.621542Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.621542Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:140d90d7284c14eb0e932c321066c4941535c0766f665d1cc3d839f1f92cc5df","observation_id":"14fb6e09-a086-4112-8247-8c4a4ad94d69","resolution":{"observed_at":"2026-08-02T16:11:23.621542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.746210Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.746210Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:97f63225ba41751f0bf0782276d3d1982be70cba6ac727caa4e0a857b7447428","observation_id":"a2b611a3-48dd-46cf-8532-82fa02075ad5","resolution":{"observed_at":"2026-08-02T16:11:23.746210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.836804Z","title":"Le, Geoffrey E","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.836804Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:bc2c072e7382c9b2509967531c48c59859bb264ee75040803e438c74650117da","observation_id":"f7bf29c9-3cd6-4a69-91d3-b1215a269252","resolution":{"observed_at":"2026-08-02T16:11:23.836804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.916671Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.916671Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:f26f914059c1808578770a50bde9481b166763b7bb2641eca1806c0be7bea8fc","observation_id":"ae34b082-3bb9-4632-8893-58a57ef45306","resolution":{"observed_at":"2026-08-02T16:11:23.916671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.041904Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.041904Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:9a5d3aa3aa48baadd299c019320b3b3a4ef699f3edcf5430d69f747ea61467fb","observation_id":"8dd4fa52-de90-43ff-9df9-82cfb52835bc","resolution":{"observed_at":"2026-08-02T16:11:24.041904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-02T16:11:24.116525Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.116525Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:8147e954e9406ca8d0e4c0944caa2805f375d18caa2db8eceb658f533a29d93a","observation_id":"7c19beca-b570-49a8-819f-aa9e624ebed4","resolution":{"observed_at":"2026-08-02T16:11:24.116525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-02T16:11:24.192687Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.192687Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:7675e6b8fd8ffdfe6e29d58f9fdb6bf9677896219465f67c0b6f47cd305fa1f1","observation_id":"547acb74-38a2-4d87-badf-283f75ede075","resolution":{"observed_at":"2026-08-02T16:11:24.192687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.259978Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.259978Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:d79932cbdc7a02d065de64d63bb043a6067b7b0a858e9bc74c01c5f1aaa1ff93","observation_id":"3c354435-931d-412a-a494-35fe8eb3cd0e","resolution":{"observed_at":"2026-08-02T16:11:24.259978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.318088Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.318088Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:85676a69d8624f646b33a45bc84aaf48895610490e721b6dece87001d7caa53b","observation_id":"384e9310-b0e2-486a-8dc0-6af1f2b2b5cb","resolution":{"observed_at":"2026-08-02T16:11:24.318088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.401901Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.401901Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:f8beb1ef20336d05795328d67d36681b1b80913b460797c2a0d1abb35d4db389","observation_id":"52a7d837-f784-4854-9d87-ecc486fc3547","resolution":{"observed_at":"2026-08-02T16:11:24.401901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.471418Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.471418Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:47d1ade708c00dc20f5892f14c60c28b454845f8f786e6f34e7b089e01d09cd6","observation_id":"cdcc76a4-22a8-48d6-ab5b-7a743a8f0e89","resolution":{"observed_at":"2026-08-02T16:11:24.471418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05920","last_updated":"2024-09-25T05:57:51Z","snapshot_observed_at":"2026-07-06T15:25:24.491136Z","submitted_at":"2023-05-10T06:17:50Z","title":"Fast Distributed Inference Serving for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05920","snapshot_observed_at":"2026-08-02T16:11:24.540611Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.540611Z"},"links":{"cited_paper":"/paper/2305.05920","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:0f9e46be6d366aad85dd10b0df3d8f8a05f130036961599685367aaa2e247b35","observation_id":"ac712d06-997d-4932-9153-723bcede4336","resolution":{"observed_at":"2026-08-02T16:11:24.540611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.599467Z","title":"Awadallah, Ryen White, Doug Burger, and Chi Wang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.599467Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:16b18471d7c01a8d009455cb8c0e4e3faf68a66fa4dc2e597357d805180e69ad","observation_id":"6d2f7af0-6827-4bf1-a36c-a679225f4dec","resolution":{"observed_at":"2026-08-02T16:11:24.599467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09999","last_updated":"2026-05-11T03:41:00Z","snapshot_observed_at":"2026-07-30T05:05:51.180006Z","submitted_at":"2025-05-15T06:24:08Z","title":"ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09999","snapshot_observed_at":"2026-08-02T16:11:24.730483Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.730483Z"},"links":{"cited_paper":"/paper/2505.09999","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:a5df4e176168fb60b009b795059ec17893ef6b08e0b4af186c002552feafd2d4","observation_id":"44c91035-d0ac-4364-ada6-53e1d98cb2fa","resolution":{"observed_at":"2026-08-02T16:11:24.730483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.873162Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.873162Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:cc141c99fa130a66f17113529715166ce767ba486fa2f44dae91972bcec88079","observation_id":"7e310d9e-7459-47f5-ac4a-f7a9cbcd2bca","resolution":{"observed_at":"2026-08-02T16:11:24.873162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:24.956009Z","title":"Gonzalez, Clark W","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:24.956009Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:c1ad7d11098e0fefdfebab500f7463e0663422b375a12ab7a7d764e88e139899","observation_id":"10b7ce66-f80b-43c7-ab0e-0d4fc8c7ecba","resolution":{"observed_at":"2026-08-02T16:11:24.956009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:25.023880Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:25.023880Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:689b985c1fd24a29557e344085fa7f10724488391789c3a4f975aba669d23e78","observation_id":"e7f14b32-2966-49fb-834b-1fdbcdc245da","resolution":{"observed_at":"2026-08-02T16:11:25.023880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16609","last_updated":"2023-09-28T17:07:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T17:07:49Z","title":"Qwen Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16609","snapshot_observed_at":"2026-08-02T16:11:21.312067Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.312067Z"},"links":{"cited_paper":"/paper/2309.16609","citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:d32f5a795c3b24fd7f22fbbc08c0e419dc7b29d9503d2f17ff1279b3a48edc94","observation_id":"d52b4425-40c5-4e61-86a2-cd7112aeb674","resolution":{"observed_at":"2026-08-02T16:11:21.312067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:21.613961Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:21.613961Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:4eacd4ed22b7b622d92d641269f609bfe960d6aefea60faefa7b60621184fa9f","observation_id":"c06220dc-e369-489a-a036-251458253617","resolution":{"observed_at":"2026-08-02T16:11:21.613961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T16:11:23.983233Z","title":"InIEEE International Symposium on High-Performance Computer Architecture (HPCA)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:23.983233Z"},"links":{"citing_paper":"/paper/2607.19349"},"observation_digest":"sha256:9eaf6911bb271fcd3c6ed80bd01b939728d46e27d4303eac2f35794f0999f379","observation_id":"6678231f-1c18-4556-9944-94014b4acae3","resolution":{"observed_at":"2026-08-02T16:11:23.983233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.19349","last_updated":"2026-04-17T13:02:56Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-02T16:11:17.649205Z","submitted_at":"2026-04-17T13:02:56Z","title":"FineServe: A Fine-Grained Dataset and Characterization of Global LLM Serving Workloads"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":39},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2607.19349."}