{"as_of":"2026-08-09T20:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:efd6fedd57651a5c6fcd94735c776ee0483bc9418a627594b3f8fe5d770d9e6b","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:46:15.035924Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T02:06:15.294236Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-08-07T13:46:15.035924Z","title":"Revisiting moe and dense speed-accuracy comparisons for llm training","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21079","last_updated":"2025-05-27T12:03:30Z","snapshot_observed_at":"2026-08-08T23:14:14.149778Z","submitted_at":"2025-05-27T12:03:30Z","title":"Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:46:15.035924Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2505.21079"},"observation_digest":"sha256:7d88e0d54a3bd4f2d144db6194654c336d8344a4c6b0929a51769fd8014a9391","observation_id":"4e6411fb-704c-43ea-b942-30c9f3e33ffb","resolution":{"observed_at":"2026-08-07T13:46:15.035924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-08-06T16:26:58.571348Z","title":"Yann Dubois, Balázs Galambosi, Percy Liang, and Tatsunori B","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13575","last_updated":"2025-08-27T16:34:47Z","snapshot_observed_at":"2026-08-09T12:02:36.199859Z","submitted_at":"2025-07-17T23:37:19Z","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:26:58.571348Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2507.13575"},"observation_digest":"sha256:dc49227c7c4f57b9281641db471724c66aa33dd1d928fab9dec08da1721c821c","observation_id":"1030b647-c9d1-4893-b1b6-7d7d65700e0a","resolution":{"observed_at":"2026-08-06T16:26:58.571348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":"2405.15052","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Revisiting MoE and dense speed-accuracy comparisons for LLM training","venue":null,"work_id":"4dfd5661-44d3-4ece-9c2b-f6ee37182011","year":2024},"citing_paper":{"arxiv_id":"2604.19835","last_updated":"2026-05-10T18:33:52Z","snapshot_observed_at":"2026-08-08T23:43:56.161397Z","submitted_at":"2026-04-21T05:53:33Z","title":"Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T03:29:16.555166Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2604.19835"},"observation_digest":"sha256:63dc7b774c05431df5f940d9ec48e34daf6dc4e1b5b1963e75fe903cf9a13016","observation_id":"cde7d86d-5877-483f-80f7-a268292c726c","resolution":{"observed_at":"2026-05-10T03:29:21.485118Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":"2405.15052","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Revisiting MoE and dense speed-accuracy comparisons for LLM training","venue":null,"work_id":"4dfd5661-44d3-4ece-9c2b-f6ee37182011","year":2024},"citing_paper":{"arxiv_id":"2604.19835","last_updated":"2026-05-10T18:33:52Z","snapshot_observed_at":"2026-08-08T23:43:56.161397Z","submitted_at":"2026-04-21T05:53:33Z","title":"Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T02:03:02.654035Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2604.19835"},"observation_digest":"sha256:e5c54cb7037dc4598bc3f6725d6f70ba9ec42a13fe89d596a21ce96fdc4f53f9","observation_id":"5f91cbc4-dc2c-4fa7-b1a7-448a098d30ca","resolution":{"observed_at":"2026-05-12T02:06:15.296559Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-08-01T21:01:42.897579Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16427","last_updated":"2026-07-17T18:22:42Z","snapshot_observed_at":"2026-08-09T12:02:22.399950Z","submitted_at":"2026-07-17T18:22:42Z","title":"Multi-level context Modeling for consistent expert selection in Mixture-of-Experts","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T21:01:42.897579Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2607.16427"},"observation_digest":"sha256:c932b08df5fab26e1a3e99f39bcfe0670a8e9d71445c8e41298e99517027fb9e","observation_id":"e9430e14-a9f1-4186-b8ea-18e2ccd84f87","resolution":{"observed_at":"2026-08-01T21:01:42.897579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15052","snapshot_observed_at":"2026-08-06T04:28:21.538572Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.05137","last_updated":"2026-08-05T17:56:35Z","snapshot_observed_at":"2026-08-08T23:36:21.714124Z","submitted_at":"2026-08-05T17:56:35Z","title":"SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T04:28:21.538572Z"},"links":{"cited_paper":"/paper/2405.15052","citing_paper":"/paper/2608.05137"},"observation_digest":"sha256:e1c2f0bf43b6411fff3dd8ab3ffb35caeead2ca6a5acb62bece77df0a1b19397","observation_id":"248168a5-3351-464d-97e0-7416d7d609d9","resolution":{"observed_at":"2026-08-06T04:28:21.538572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.15052/citation-record","integrity":"/paper/2405.15052/integrity","json":"/paper/2405.15052/citation-record.json","paper":"/paper/2405.15052"},"outbound":[],"paper":{"arxiv_id":"2405.15052","last_updated":"2024-06-28T19:39:45Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T12:02:12.929800Z","submitted_at":"2024-05-23T21:00:53Z","title":"Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2405.15052."}