{"as_of":"2026-08-09T00:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f46af75be5fe4c683532a8808d11031882f95fa0f1f6b600b0c846041d08b591","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:34:40.851607Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.25785/citation-record","integrity":"/paper/2607.25785/integrity","json":"/paper/2607.25785/citation-record.json","paper":"/paper/2607.25785"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T01:34:40.268209Z","title":"Convergence of first-order methods for constrained nonconvex optimization with dependent data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.268209Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:a1d247763bcb143e117c72f15724e6e13ea6c585ed34355b6b8a9cc73af82529","observation_id":"1445bab2-2e25-4313-8596-1b791dc5e690","resolution":{"observed_at":"2026-08-01T01:34:40.268209Z","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":"2026-08-01T01:34:40.329352Z","title":"Duchi, Dylan J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.329352Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:61bda87ea5df43accfb0e6b5c21e9baea4ee4c03c4996b14e4888011f0ebe46b","observation_id":"17a92a89-1d99-433f-95d9-440f58928d30","resolution":{"observed_at":"2026-08-01T01:34:40.329352Z","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":"2026-08-01T01:34:40.392451Z","title":"Blanchet and Peter W","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.392451Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:4e7296a0c87e3f2a70dd24dd5cf7f2e4b0a628ceb53528898bf667c178f9f483","observation_id":"81fdf752-988e-407c-9774-5d65e1e7dc62","resolution":{"observed_at":"2026-08-01T01:34:40.392451Z","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":"2026-08-01T01:34:40.488517Z","title":"High-probability bounds for non-convex stochastic optimization with heavy tails","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.488517Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:9211b546b03388f566561d7f3fa4170234ce857586c1293d8ad14c771b04bf76","observation_id":"7789cf76-42e2-4f65-bc2d-3bfe3a9e15bf","resolution":{"observed_at":"2026-08-01T01:34:40.488517Z","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":"2026-08-01T01:34:40.550591Z","title":"Momentum-based variance reduction in non- convex SGD","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.550591Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:b87b3e55af8f3465aedd0dab0c7c5c73dcc3d1dbc9b7e8e01fddffbb945d1f74","observation_id":"d114afdd-579b-4a0a-9395-a820b9be0d35","resolution":{"observed_at":"2026-08-01T01:34:40.550591Z","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":"2026-08-01T01:34:40.612340Z","title":"Adapting to mixing time in stochastic optimiza- tion with Markovian data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.612340Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:3df21943198aa12a28041a1131177851120cc862fa3096a6a21d455eed89fa05","observation_id":"cfc2a41a-afa7-4b91-9ae5-9d016207dd4d","resolution":{"observed_at":"2026-08-01T01:34:40.612340Z","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":"10.1137/110836043","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Duchi, Alekh Agarwal, Mikael Johansson, and Michael I","venue":"SIAM Journal on Optimization","work_id":"8c840e3c-e81e-4a0f-b094-162de74ac5bd","year":2012},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.661188Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:778f90e3ae9e62d681391b9d187f5e415ca1d8d249c2dec98e7b503e101b5610","observation_id":"0b5937fe-1f0d-4b97-871a-f2538522ad7c","resolution":{"observed_at":"2026-08-01T01:36:15.802029Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-01T01:34:40.721342Z","title":"Stochastic gradient descent under Markovian sampling schemes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.721342Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:79d620f243f362f99980d87ad2deaec88446e50bd7234a31872b60ce78ea1e69","observation_id":"539f47f4-6f47-42bf-ac3d-5ae2295ad39c","resolution":{"observed_at":"2026-08-01T01:34:40.721342Z","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":"2026-08-01T01:34:40.775200Z","title":"SPIDER: Near-optimal non- convex optimization via stochastic path-integrated differential estimator","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.775200Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:5756a12c03a38b74cf873721e98757dddf54b2cb35268d86cdc995d296accef7","observation_id":"03e68795-9def-4533-a0cc-1242b797cc28","resolution":{"observed_at":"2026-08-01T01:34:40.775200Z","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":"2026-08-01T01:34:40.786378Z","title":"An algorithm for quadratic programming","venue":null,"work_id":null,"year":1956},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.786378Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:b782ff3da26646b287fb7f4c975ddc2d4b6c2bb6874cea6d183195c6af6db307","observation_id":"9913ccf3-a111-4e05-9023-b50afaf85575","resolution":{"observed_at":"2026-08-01T01:34:40.786378Z","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":"2026-08-01T01:34:40.789081Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.789081Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:640c7684c7cdb2f8a2f1c5147077711138806ea788da3171bd017d5a47434b19","observation_id":"59554f98-fe3b-46fa-8c3f-d1a71d7e3dff","resolution":{"observed_at":"2026-08-01T01:34:40.789081Z","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":"2026-08-01T01:34:40.791585Z","title":"Stochastic optimization with heavy-tailed noise via accelerated gradient clipping","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.791585Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:e1b0ccc6447f6cfe026807d4f5f2a4f998b526db689fc4208b7d7baa9107f9e5","observation_id":"b17678a4-e57c-4473-8d83-d80b4ad2d05d","resolution":{"observed_at":"2026-08-01T01:34:40.791585Z","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":"2026-08-01T01:34:40.793971Z","title":"Variance-reduced and projection-free stochastic optimization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.793971Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:782c592a48b7265843c52f2b7ad1e1c452d99ac558b937f40c2e75d4dd1c8a9f","observation_id":"d8c6a4d2-e070-431a-8884-e01c3f97c2b5","resolution":{"observed_at":"2026-08-01T01:34:40.793971Z","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":"2026-08-01T01:34:40.796576Z","title":"Revisiting Frank–Wolfe: Projection-free sparse convex optimization","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.796576Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:4b25b86320d26b9729f8aa28d84159e1da429f7822c4df9d52adf600b5809db4","observation_id":"954fa53b-3367-4d3f-a3c4-84bdb713fc99","resolution":{"observed_at":"2026-08-01T01:34:40.796576Z","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":"2026-08-01T01:34:40.798839Z","title":"Non-asymptotic analy- sis of biased stochastic approximation scheme","venue":null,"work_id":null,"year":1944},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.798839Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:7d42e7575316dbb0ffc39c6b8bfc55d05bd16d6e60e0f3d7b717c209eb27426f","observation_id":"0f8cc516-5469-4a78-8232-234727ac2bd4","resolution":{"observed_at":"2026-08-01T01:34:40.798839Z","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":"2026-08-01T01:34:40.801305Z","title":"Stochastic-constrained stochastic optimization with Markovian data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.801305Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:eb540ce58cc69badedb95bb4f29001b2b085e29129be4b51cb507187212c1685","observation_id":"628e8068-df46-41a3-a51b-9eacc5f726f9","resolution":{"observed_at":"2026-08-01T01:34:40.801305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.00345","last_updated":"2016-07-01T18:37:33Z","snapshot_observed_at":"2026-07-06T05:02:06.677337Z","submitted_at":"2016-07-01T18:37:33Z","title":"Convergence Rate of Frank-Wolfe for Non-Convex Objectives","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.00345","snapshot_observed_at":"2026-08-01T01:34:40.803458Z","title":"Convergence rate of Frank–Wolfe for non-convex objectives","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.803458Z"},"links":{"cited_paper":"/paper/1607.00345","citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:fe12eb6bbe91f5161ea7de7fcb7b412c349d89b0af23438a7bf0d54f77ad94b4","observation_id":"19de6938-5290-4b0b-b7eb-9ae043dc1612","resolution":{"observed_at":"2026-08-01T01:34:40.803458Z","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":"2026-08-01T01:34:40.805999Z","title":"Levin and Yuval Peres","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.805999Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:6dc74b7bd345b4054501b18c121d7d1eb9b99ef184d000a050ad04090c56b75d","observation_id":"d380a10e-ce97-473e-a194-d2018dd65f03","resolution":{"observed_at":"2026-08-01T01:34:40.805999Z","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":"2026-08-01T01:34:40.808276Z","title":"Levy, Ali Kavis, and Volkan Cevher","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.808276Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:42d3bb9ccd4cb57e46491934aefc40c7ec44f55f520af5985786e0ead70ce6bd","observation_id":"c5273543-5df1-4309-8b2c-0cba2f87ca51","resolution":{"observed_at":"2026-08-01T01:34:40.808276Z","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":"2026-08-01T01:34:40.810428Z","title":"Stochastic conditional gradient meth- ods: From convex minimization to submodular maximization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.810428Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:3856c5c4c02a8e98a9c853f953ea54ca50caf70489584b6f05f5e35c7fef5e99","observation_id":"9f75571c-0291-4e50-a0be-61ecb53fff03","resolution":{"observed_at":"2026-08-01T01:34:40.810428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.25255","last_updated":"2026-05-24T21:04:26Z","snapshot_observed_at":"2026-07-06T23:35:16.647496Z","submitted_at":"2026-05-24T21:04:26Z","title":"Boosted Stochastic Frank-Wolfe for Constrained Nonconvex Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.25255","snapshot_observed_at":"2026-08-01T01:34:40.812932Z","title":"Boosted stochastic Frank– Wolfe for constrained nonconvex optimization","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.812932Z"},"links":{"cited_paper":"/paper/2605.25255","citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:bf8be55e5e35fe433a0e1a09484461da4321c38ba84983524505f8253fbb1860","observation_id":"eb4199d4-e019-42c1-8ec1-a4f4b0b58df1","resolution":{"observed_at":"2026-08-01T01:34:40.812932Z","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":"2026-08-01T01:34:40.815379Z","title":"Stochastic Frank–Wolfe: Unified analysis and zoo of spe- cial cases","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.815379Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:3872a2715d7066160a1ce6a799ea9e5f69024b2739d574af6b5d8a72c0bb906a","observation_id":"36baf953-333f-46c6-b742-169d8b79099f","resolution":{"observed_at":"2026-08-01T01:34:40.815379Z","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":"2026-08-01T01:34:40.817631Z","title":"Stochastic variance-reduced policy gradient","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.817631Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:c43e0d2720a9e0485492b71f8cc9bca63e2b0612d44762834ac3529660282119","observation_id":"a58b1166-28ab-4ad2-b6c8-4098d936a1ff","resolution":{"observed_at":"2026-08-01T01:34:40.817631Z","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":"2026-08-01T01:34:40.819813Z","title":"A hybrid stochastic policy gradient algorithm for reinforcement learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.819813Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:0760bcf1794698d7a20af34b488b38ce05cb99ef8e1060576f67d427518ec7b1","observation_id":"c36328ab-f3f1-4294-9407-5ef3ff6494f1","resolution":{"observed_at":"2026-08-01T01:34:40.819813Z","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":"2026-08-01T01:34:40.822110Z","title":"Reddi, Suvrit Sra, Barnabás Póczos, and Alexander J","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.822110Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:7ca41e9b007e288ecd7b084d3892216a9393665f22084a6409eb5b135cec564e","observation_id":"b96528c0-7fdf-4935-bb76-a557a2290ef4","resolution":{"observed_at":"2026-08-01T01:34:40.822110Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v40i30.39746","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Methods for optimization problems with Markovian stochasticity and non-Euclidean geom- etry","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"a35ace46-8ce6-4d6e-9195-62ac5ab4a67a","year":2026},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.824458Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:1e978e384ef0c59dc363bc869f8387a7bd21a4f281c821b3bbd899f495868e23","observation_id":"0f2431c8-efaf-431b-bf60-21d016edfd98","resolution":{"observed_at":"2026-08-01T01:36:15.464801Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-01T01:34:40.826810Z","title":"On Markov chain gradient descent","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.826810Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:31baffbab131950fe9ad8b3ca2a080761d52a06de99f5a585877685312d1ff9d","observation_id":"49934a83-2de0-44c7-9bb6-fd2458532334","resolution":{"observed_at":"2026-08-01T01:34:40.826810Z","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":"2026-08-01T01:34:40.828957Z","title":"Learning from a single markovian trajectory: Optimality and variance reduction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.828957Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:f23eaf94868b216f5ce9389f94784df30cd6bbae3981bb15128ea72fcebccd22","observation_id":"e88829e2-a550-44d9-b4b7-0c72ab995dd4","resolution":{"observed_at":"2026-08-01T01:34:40.828957Z","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":"2026-08-01T01:34:40.831237Z","title":"Stability and generaliza- tion for Markov chain stochastic gradient methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.831237Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:45832efb0e9bcceb7aa9285aef3520ab9fc2b5daf8ffe2f4b16ab2a6a8d5b462","observation_id":"412fe694-f84b-4a84-a2c7-b57526b804e0","resolution":{"observed_at":"2026-08-01T01:34:40.831237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.21099","last_updated":"2025-05-17T09:56:02Z","snapshot_observed_at":"2026-08-07T17:39:37.901655Z","submitted_at":"2025-02-28T14:37:56Z","title":"Adaptive Extrapolated Proximal Gradient Methods with Variance Reduction for Composite Nonconvex Finite-Sum Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.21099","snapshot_observed_at":"2026-08-01T01:34:40.833582Z","title":"Adaptive extrapolated proximal gradient methods with variance reduction for composite nonconvex finite-sum minimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.833582Z"},"links":{"cited_paper":"/paper/2502.21099","citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:a9ab6d67c331805a4bcdb5d76d184c011c5b95679bee3d310555ab1121ef402e","observation_id":"3163d563-7d98-4d9a-a17c-2d418c501166","resolution":{"observed_at":"2026-08-01T01:34:40.833582Z","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":"2026-08-01T01:34:40.836218Z","title":"Adaptive Lipschitz-free conditional gradient methods for stochastic com- posite nonconvex optimization","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.836218Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:5058dd34beddc5024fefc829c82491ba79439f61eff59acadf1e183217719d74","observation_id":"9516b107-f874-4cb1-b56e-9017889e2f6c","resolution":{"observed_at":"2026-08-01T01:34:40.836218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04302","last_updated":"2020-03-09T17:59:03Z","snapshot_observed_at":"2026-08-08T13:39:11.073695Z","submitted_at":"2020-03-09T17:59:03Z","title":"Stochastic Recursive Momentum for Policy Gradient Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04302","snapshot_observed_at":"2026-08-01T01:34:40.838381Z","title":"Stochastic recursive momentum for policy gradient methods","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.838381Z"},"links":{"cited_paper":"/paper/2003.04302","citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:f41f2fabfbb39b40a927aa6fc947cf093f308ce27b15ea6f0496d7192ebb2697","observation_id":"cab4ab87-3bb1-4a87-9574-f96f2676c630","resolution":{"observed_at":"2026-08-01T01:34:40.838381Z","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":"2026-08-01T01:34:40.840893Z","title":"Why gradient clipping accel- erates training: A theoretical justification for adaptivity","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.840893Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:4a78c2243f99302130504ca70a7865f05ae95d61e86a0c2814edccecd8f5bea1","observation_id":"6668da21-cb54-473d-b44f-000fdc3d0a29","resolution":{"observed_at":"2026-08-01T01:34:40.840893Z","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":"10.1007/s10107-021-01709-z","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Stochastic variance-reduced prox-linear algorithms for non- convex composite optimization","venue":"Mathematical Programming","work_id":"c79e09a8-fe08-4e39-9767-b30deb1f67af","year":2022},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.843020Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:2791383945a2bf7693e396256676f8e39955268a4c88f2386d25b05005879377","observation_id":"03ec8e9b-3024-419a-893b-c46fa890d8d8","resolution":{"observed_at":"2026-08-01T01:36:15.216298Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-01T01:34:40.845806Z","title":"the base coefficient system","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.845806Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:25649495d300f10f8bbedd7096d736ed4d0f5a20040ea2b5aecaed255cd1dc72","observation_id":"efe184cc-598e-4fa3-96b2-2653f60edde1","resolution":{"observed_at":"2026-08-01T01:34:40.845806Z","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":"2026-08-01T01:34:40.848777Z","title":"Moreover, max(β1/3 T ,ϑ 2, 0) ϑ = β1/3 T ϑ = β1/6 T +β1/3 T = O (T + 1)−1/6","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.848777Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:f54693d71373be77e9bcfc3011c31a6f577653ad598eb79d28f54c87e79cf95c","observation_id":"a7c93649-72a5-4871-a7bc-f21ebe39613a","resolution":{"observed_at":"2026-08-01T01:34:40.848777Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-01T01:34:40.851607Z","title":"Thus the instance numerically exercises smooth nonconvexity, and h(x) = 0.02kxk1 is nonzero, convex, and nonsmooth","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T01:34:40.851607Z"},"links":{"citing_paper":"/paper/2607.25785"},"observation_digest":"sha256:485a5aa8c5a6469b5f5c95439ab4e272b367e2c10dc63449f2c805340e2a0273","observation_id":"9d058d84-ea17-465d-ba7a-1317f3f7df0b","resolution":{"observed_at":"2026-08-01T01:34:40.851607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.25785","last_updated":"2026-07-28T14:37:47Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-08T19:38:03.272739Z","submitted_at":"2026-07-28T14:37:47Z","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":37},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2607.25785."}