{"as_of":"2026-08-15T20:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:45266cf820a901ea676b9a1e51f2464395bf6d626e5dbe6f0c02deeacd9faa13","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T13:54:34.773511Z","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":"2026-07-04T09:39:47.170037Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1611.04581","last_updated":"2016-11-14T20:59:54Z","snapshot_observed_at":"2026-08-14T21:30:28.408283Z","submitted_at":"2016-11-14T20:59:54Z","title":"How to scale distributed deep learning?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.04581","snapshot_observed_at":"2026-08-14T13:54:34.773511Z","title":"Jin, Qiaochu Yuan, Forrest N","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.04207","last_updated":"2025-08-21T07:39:24Z","snapshot_observed_at":"2026-08-15T08:39:23.320015Z","submitted_at":"2019-08-12T15:37:51Z","title":"Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations","version":5},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T13:54:34.773511Z"},"links":{"cited_paper":"/paper/1611.04581","citing_paper":"/paper/1908.04207"},"observation_digest":"sha256:f4eb87c7a8c90405812c3955e9e5a6e463a73a84594f5bf6371e3730fbe2b48d","observation_id":"0ae32da0-7e30-40ee-82b3-13cea8b66514","resolution":{"observed_at":"2026-08-14T13:54:34.773511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.04581","last_updated":"2016-11-14T20:59:54Z","snapshot_observed_at":"2026-08-14T21:30:28.408283Z","submitted_at":"2016-11-14T20:59:54Z","title":"How to scale distributed deep learning?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.04581","snapshot_observed_at":"2026-08-12T11:52:40.193192Z","title":"How to scale distributed deep learning? arXiv preprint arXiv:1611.04581 ,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.17866","last_updated":"2025-03-07T19:35:00Z","snapshot_observed_at":"2026-08-12T11:42:55.738715Z","submitted_at":"2024-11-26T20:31:11Z","title":"Distributed Sign Momentum with Local Steps for Training Transformers","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-12T11:52:40.193192Z"},"links":{"cited_paper":"/paper/1611.04581","citing_paper":"/paper/2411.17866"},"observation_digest":"sha256:f1d55845eb4fb5c6701b281695eb262176b2ee8b58fdfabb49aab66dc4605000","observation_id":"9c3be546-6f44-4312-8a1a-ebd0bc63e72a","resolution":{"observed_at":"2026-08-12T11:52:40.193192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.04581","last_updated":"2016-11-14T20:59:54Z","snapshot_observed_at":"2026-08-14T21:30:28.408283Z","submitted_at":"2016-11-14T20:59:54Z","title":"How to scale distributed deep learning?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.04581","snapshot_observed_at":"2026-08-07T04:47:27.523987Z","title":"How to scale distributed deep learning?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.09769","last_updated":"2025-06-11T14:09:53Z","snapshot_observed_at":"2026-08-15T01:30:27.378318Z","submitted_at":"2025-06-11T14:09:53Z","title":"Load-Aware Training Scheduling for Model Circulation-based Decentralized Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:47:27.523987Z"},"links":{"cited_paper":"/paper/1611.04581","citing_paper":"/paper/2506.09769"},"observation_digest":"sha256:bce91a690ef60bc74ac2fd177bf697308c4e545358416c9b4ed8e20451529e96","observation_id":"dc369c6a-c7e9-483a-9ec6-01932fb175bc","resolution":{"observed_at":"2026-08-07T04:47:27.523987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.04581","last_updated":"2016-11-14T20:59:54Z","snapshot_observed_at":"2026-08-14T21:30:28.408283Z","submitted_at":"2016-11-14T20:59:54Z","title":"How to scale distributed deep learning?","version":1},"cited_work":{"arxiv_id":"1611.04581","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.04581","snapshot_observed_at":"2026-07-04T09:39:47.170037Z","title":"How to scale distributed deep learning?","venue":"cs.LG","work_id":"dae1de2a-381e-4442-aed6-5a332b1b5c1d","year":2016},"citing_paper":{"arxiv_id":"2606.22768","last_updated":"2026-06-22T02:15:13Z","snapshot_observed_at":"2026-08-08T04:47:34.853247Z","submitted_at":"2026-06-22T02:15:13Z","title":"Factored Gossip DiLoCo: Reducing Blocking Communication in DiLoCo","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-06-26T09:36:44.011799Z"},"links":{"cited_paper":"/paper/1611.04581","citing_paper":"/paper/2606.22768"},"observation_digest":"sha256:e11d9931d2c5a42c778d33736eb2c77bdb51879d18dfa0ab4b46d1f7a4af02aa","observation_id":"86bd5311-663d-4acf-b965-a53d868c0922","resolution":{"observed_at":"2026-07-04T09:39:47.171231Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1611.04581/citation-record","integrity":"/paper/1611.04581/integrity","json":"/paper/1611.04581/citation-record.json","paper":"/paper/1611.04581"},"outbound":[],"paper":{"arxiv_id":"1611.04581","last_updated":"2016-11-14T20:59:54Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T21:30:28.408283Z","submitted_at":"2016-11-14T20:59:54Z","title":"How to scale distributed deep learning?"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1611.04581."}