{"as_of":"2026-08-17T15:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6864ad8f91997f957a7eb8967246dfbbb5400154395cf7b6072b003899f97bb7","coverage":[{"denominator":9,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-13T07:34:15.530836Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.27081","snapshot_observed_at":"2026-07-13T07:34:15.530836Z","title":"arXiv preprint arXiv:2605.27081 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.08780","last_updated":"2026-06-12T23:47:19Z","snapshot_observed_at":"2026-08-14T09:06:16.495988Z","submitted_at":"2026-06-12T23:47:19Z","title":"Sticky Routing: Training MoE Models for Memory-Efficient Inference","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-13T07:34:15.530836Z"},"links":{"cited_paper":"/paper/2605.27081","citing_paper":"/paper/2607.08780"},"observation_digest":"sha256:2b235f6d018df0ecf645e25094c356d8cd0e4a3681ca0eb8c6e2196f28714a5f","observation_id":"c18475df-10cf-4ca0-86ea-1845ab5b2fba","resolution":{"observed_at":"2026-07-13T07:34:15.530836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.27081/citation-record","integrity":"/paper/2605.27081/integrity","json":"/paper/2605.27081/citation-record.json","paper":"/paper/2605.27081"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":"2110.14168","doi":"10.1002/j.1545-","metadata_source":"pith","pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training Verifiers to Solve Math Word Problems","venue":"cs.LG","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":2021},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:ee7be0e142d0aa279071565e9622ab074e9df8f645a2e7d7def6b1394a5a9bf9","observation_id":"738ff0f3-2d0b-4ffd-9290-8dd68ab0648d","resolution":{"observed_at":"2026-06-29T19:03:51.008223Z","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":"2503.03777","last_updated":"2025-03-04T20:08:03Z","snapshot_observed_at":"2026-08-16T12:53:04.936274Z","submitted_at":"2025-03-04T20:08:03Z","title":"FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference","version":1},"cited_work":{"arxiv_id":"2503.03777","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.03777","snapshot_observed_at":"2026-06-29T19:03:51.301959Z","title":"Du, H., Wu, S., Kharlamova, A., Guan, N., and Xue, C","venue":null,"work_id":"154b8237-007d-473e-91aa-6d9a50c18a33","year":2025},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"cited_paper":"/paper/2503.03777","citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:cef43cac8640458208542d2abd1c6f892ab5cc6de6384c64aeb1ec1c54816bcf","observation_id":"e2e6146d-ef46-4372-b650-dd839794794b","resolution":{"observed_at":"2026-06-29T19:03:51.303845Z","resolver_source":"arxiv_id","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":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2025.findings-acl.997","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://aclanthology.org/2025.findin gs-acl.997/","venue":null,"work_id":"5581f68a-d490-4bcc-99f0-7b4e1aa02450","year":2025},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:95ae7ee56ce95bed9d73e4c1a7ccb9a158558ffef958c7e6913bc05565a2a430","observation_id":"19eab902-1c9b-455a-87c0-d6237bd22480","resolution":{"observed_at":"2026-06-29T19:03:51.007116Z","resolver_source":"doi","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":null,"cited_work":{"arxiv_id":"6641.371598","doi":"10.1145/3676641.3715986","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Berger, Marie Nguyen, Xun Jian, Sam H","venue":null,"work_id":"e35f5473-eb5d-4629-bcfb-86f1655111da","year":2022},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:d98fe863b561498dfdd39a7fde9d7aaeb0dfebe625ce1c04e290e52aebfc4fd9","observation_id":"e2622156-cdd5-4e34-a20e-46c1ed3b6d02","resolution":{"observed_at":"2026-06-29T19:03:51.001555Z","resolver_source":"arxiv_id","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":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3724420","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Empowering edge intelligence: A comprehensive survey on on-device ai models","venue":"ACM Computing Surveys","work_id":"aef7e11d-0d13-4f90-bf27-668b6ee978e2","year":2025},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:510117a1d19d21053cc95fb2c5041633188db5300ac9f92f9d520d6ebb7bcd76","observation_id":"99c27e79-fc6b-4786-be29-373af5904d31","resolution":{"observed_at":"2026-06-29T19:03:51.009237Z","resolver_source":"doi","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":"2026-07-15T19:20:18.744671+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:18.744671+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-29T18:59:37.443084Z","title":"For instance, if K= 6 and C= 4 , even if Et =E t−1, the cache cannot hold all 6 experts simultaneously, so a guarantee of the form(17) no longer holds","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:1a34f9b3856e4cb6a1af8455e1415eb4027569ccc2f4e490ca589817f5e441ea","observation_id":"e7e3a6e1-2a48-41ec-b5c6-86837fd021da","resolution":{"observed_at":"2026-06-29T18:59:37.443084Z","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":"2026-06-29T18:59:37.443084Z","title":"Then even if Et−1 was fully loaded during step t−1 , some of these experts might be evicted before step t begins, and the containment in Lemma A.5 can fail","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:fd2ec24dcfe935a0caf0bb8236dfa19602463eb2900852943c4a3170a2843d00","observation_id":"ccc91e82-0e28-41d6-b7fd-bac9e8fb5232","resolution":{"observed_at":"2026-06-29T18:59:37.443084Z","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":"2026-06-29T18:59:37.443084Z","title":"For example, with C=K , any insertion of an expert not in Et−1 forces an eviction; if the policy/prefetcher evicts from Et−1, then Et−1 ⊈C t","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:d15d55c5c7eaa702b442742c1fc785a0e1efcdab9c49e39833a7b375750b5204","observation_id":"50b3d48e-c0c4-4fdd-947f-c40c68b8ef1c","resolution":{"observed_at":"2026-06-29T18:59:37.443084Z","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":"2026-06-29T18:59:37.443084Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T18:59:37.443084Z"},"links":{"citing_paper":"/paper/2605.27081"},"observation_digest":"sha256:7b0e2fe8c09ce80416f23af487cceb5b6a5a807492265603274ad4d49eb3a032","observation_id":"3c78c984-c4cb-480d-b3f5-f20592a8b37c","resolution":{"observed_at":"2026-06-29T18:59:37.443084Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.27081","last_updated":"2026-05-26T14:32:56Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T19:24:07.592479Z","submitted_at":"2026-05-26T14:32:56Z","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference"},"reference_resolution":{"displayed":9,"state_counts":{"malformed_identifier":1,"metadata_mismatch":3,"parse_uncertain":0,"unresolved":3,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":9},"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 9 of 9 outbound references and 1 inbound Pith citation observation for arXiv:2605.27081."}