{"as_of":"2026-08-09T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:85302f81ab5ea844c683c691178e9123850cf0a04c78a07c855ba91fd6809478","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-16T11:58:09.917048Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"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/2601.15984/citation-record","integrity":"/paper/2601.15984/integrity","json":"/paper/2601.15984/citation-record.json","paper":"/paper/2601.15984"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.21394","last_updated":"2025-05-27T16:23:23Z","snapshot_observed_at":"2026-08-07T13:26:22.747594Z","submitted_at":"2025-05-27T16:23:23Z","title":"Dual Averaging Converges for Nonconvex Smooth Stochastic Optimization","version":1},"cited_work":{"arxiv_id":"2505.21394","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.21394","snapshot_observed_at":"2026-07-04T09:09:43.440877Z","title":"Dual averaging con- verges for nonconvex smooth stochastic optimiza- tion.arXiv:2505.21394","venue":null,"work_id":"45f8279c-bd04-4cca-91f7-d5c04fdc50da","year":2025},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"cited_paper":"/paper/2505.21394","citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:85ac5e414cd8ea8ea8f7ee1da0fff730673d3c17b5bea207974faa9f2b650c59","observation_id":"83e1fbeb-10ae-4c77-a766-659e7543ca97","resolution":{"observed_at":"2026-05-16T12:00:53.254835Z","resolver_source":"arxiv_id","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On sequential strategies for loss functions with memory.IEEE Transactions on Information Theory, 48(7):1947–1958","venue":null,"work_id":"9a100dc4-10d4-4206-848c-94e0db8fc98c","year":1947},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:049313afe9116fb54e89080d3ed480f5f04a58458b3d53441474bb0d0067d8bf","observation_id":"ff906e46-250e-4ce1-800a-14f96c2758eb","resolution":{"observed_at":"2026-05-16T12:00:53.590087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"1912.13213","last_updated":"2026-06-21T08:13:27Z","snapshot_observed_at":"2026-07-06T08:47:45.187408Z","submitted_at":"2019-12-31T08:16:31Z","title":"Online Learning: A Modern Introduction Using Convex Optimization","version":10},"cited_work":{"arxiv_id":"1912.13213","doi":null,"metadata_source":"pith","pith_arxiv_id":"1912.13213","snapshot_observed_at":"2026-07-04T10:39:44.912057Z","title":"A Modern Introduction to Online Learning","venue":"cs.LG","work_id":"e1cb6c30-151b-4dc8-a662-2c547f07874f","year":2019},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"cited_paper":"/paper/1912.13213","citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:1ed80e8a890850a03958f8c3c6d7150fd5043f1573810e967d3a21c247c2bbb1","observation_id":"b5c525c4-bfa6-4ee8-9783-2b6a4a47cc3d","resolution":{"observed_at":"2026-05-16T12:00:53.257541Z","resolver_source":"local_arxiv","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Output:{x t}T t=1","venue":null,"work_id":"27ed96be-f33e-4d43-8630-2e9daa1832fa","year":2017},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:e66b3d049aaa65233ae6e46fad1897042ae6f4873f5b8afa2c7bf1cc097c39aa","observation_id":"743b6dc9-d4d0-47b0-8530-9442e9295832","resolution":{"observed_at":"2026-05-16T12:00:53.587642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gaussian gradients with variance 10 per coordinate","venue":null,"work_id":"8c0eb216-8b87-455c-91ba-884b014cb5a4","year":2022},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:92afd91bd9e4515e9fcb3f3d4f2d618c9745556b37d9e2bc0f1d77844b18e389","observation_id":"8a3d2aee-99ae-4195-acad-4bcd55c3e5dc","resolution":{"observed_at":"2026-05-16T12:00:53.576172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2d6fd369-41d1-4c19-b750-1c164d2d4635","year":2000},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:fec99f0cb93f4d2e87b29821ce636ba5e3fee1a1e09e33d055ceb7ef16dde370","observation_id":"952f2fe7-571f-4577-896d-c69b5182c95e","resolution":{"observed_at":"2026-05-16T12:00:53.563398Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Moreover, the losses within an active interval differ slightly for the learner and the comparator","venue":null,"work_id":"f4c27aed-e245-483f-87bd-0ac5bcc88561","year":2012},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:11512fc5134a2d42bd88a60d545aa223e8c8785b0a5820835439e2b91c6432cd","observation_id":"32a52ac8-2ed4-4abf-bf03-dc3863c406c8","resolution":{"observed_at":"2026-05-16T12:00:53.565235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"blocking argument","venue":null,"work_id":"e57280d2-9f61-4c70-8985-f10aa97b7a26","year":2002},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:437c4974f1c080578243310338052bd388584790614c73a87bb78d004afb11ee","observation_id":"55d2b1a1-d590-4e06-858d-ee40eca1f472","resolution":{"observed_at":"2026-05-16T12:00:53.582663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The inequality holds because of the update rule for eachx t+1 for anyt","venue":null,"work_id":"344fb20a-13f4-41b9-b8d1-99f18576ac9b","year":2017},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:24ce2b9e6aa94ec64935499e76e6ddac86ea44ba80498eb9efa4b826be3cab0c","observation_id":"f75b216e-c7d4-486a-b8fe-5436a6f9f407","resolution":{"observed_at":"2026-05-16T12:00:53.585322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"In both cases,x t satisfies the optimality condition for minimizingh 0:t−1(x) +⟨g I t ,x⟩overX, and is therefore a valid minimizer","venue":null,"work_id":"8a72ad51-23a3-40d8-8c82-1f3003e9c812","year":2007},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:ddc5865242e1ce2de6aa6211b17fca979cf15c87a7b60dd765554b329439f373","observation_id":"5bfc1e59-560d-45a8-b9f6-4875725f5ce4","resolution":{"observed_at":"2026-05-16T12:00:53.577113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Moreover, settingk=⌊c p T /PT ⌋, c >0 andσ=σ ⋆ .= p (G2+2G)T /(4RP T +R2) gives RT =O p (PT + 1)T","venue":null,"work_id":"569dd57a-8fe8-45d3-85ac-a1a86ad725a8","year":2021},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:6917fc4de469e036bec56968722e1a72f1bb0217c7726ea83261f0be6149a73d","observation_id":"aca5f870-4b84-4023-a492-a55f5c7bae11","resolution":{"observed_at":"2026-05-16T12:00:53.571270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Proof.(ofTheorem","venue":null,"work_id":"feba2552-d916-4c81-bbea-95708be7931a","year":2021},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:fde8bb871141b4f47637edcec9e7959e2c5967dfa278e1794c3deaf58569914b","observation_id":"9594fcff-d276-432d-b7af-1949d32fb5c8","resolution":{"observed_at":"2026-05-16T12:00:53.574266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"unlike those results, this bound requires no additional assumptions on the domain or on the magni- tude/direction of the accumulated gradients","venue":null,"work_id":"ac752de2-644f-4be9-a8d6-aaba9ebc5efb","year":2010},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:a633cabfa997ff84bed8b340cf04dec60d42367ba442305fbe52a3cb3299f7da","observation_id":"a6b9fe3b-f4f4-446c-92c7-10ce1137ee2b","resolution":{"observed_at":"2026-05-16T12:00:53.579781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"In thek-lazy case, the same principle applies phase by phase, with the bound expressed relative to the average within each lazy block","venue":null,"work_id":"0cd89f7e-3c06-429c-892a-2708e6d79310","year":2010},"citing_paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-16T11:58:09.917048Z"},"links":{"citing_paper":"/paper/2601.15984"},"observation_digest":"sha256:a2898d3b3cfe1f74007126fb691a619dac789892785e7bbd68e6e52a319e9807","observation_id":"5b8a653c-a127-4367-8835-b1edbae47faa","resolution":{"observed_at":"2026-05-16T12:00:53.568258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2601.15984","last_updated":"2026-05-08T15:11:58Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T04:02:00.066883Z","submitted_at":"2026-01-22T14:05:08Z","title":"Partially Lazy Gradient Descent for Smoothed Online Learning"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":1,"verified_exact":2,"verified_fuzzy":11},"total_outbound_references":14},"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 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2601.15984."}