{"as_of":"2026-08-23T13:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f354e230b2e2838a3eda047d0642e58a662191e304b6a23704acbe2dff9c5e0d","coverage":[{"denominator":10,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T17:16:59.185567Z","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":"2026-08-23T06:30:58.430688+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/2508.17288/citation-record","integrity":"/paper/2508.17288/integrity","json":"/paper/2508.17288/citation-record.json","paper":"/paper/2508.17288"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.17369","last_updated":"2023-12-28T21:28:08Z","snapshot_observed_at":"2026-08-19T01:36:52.698269Z","submitted_at":"2023-12-28T21:28:08Z","title":"SANIA: Polyak-type Optimization Framework Leads to Scale Invariant Stochastic Algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17369","snapshot_observed_at":"2026-08-15T17:16:59.145097Z","title":"SANIA: Polyak-type optimization framework leads to scale invariant stochastic algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.145097Z"},"links":{"cited_paper":"/paper/2312.17369","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:6b579dfec87c0f7666b4b22e063f2bbd4abf4fc30a985c64c2279ffed13295d2","observation_id":"21e500f8-4131-4553-9f4c-8c872d85494e","resolution":{"observed_at":"2026-08-15T17:16:59.145097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.07583","last_updated":"2024-06-05T14:03:57Z","snapshot_observed_at":"2026-08-21T18:31:15.147599Z","submitted_at":"2023-05-12T16:25:57Z","title":"MoMo: Momentum Models for Adaptive Learning Rates","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.07583","snapshot_observed_at":"2026-08-15T17:16:59.185567Z","title":"MoMo: Momentum models for adaptive learning rates","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":1969,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.185567Z"},"links":{"cited_paper":"/paper/2305.07583","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:c9b54473a88c70d07a27ac4c5a71b5501b64cfb2f04a0facb2a84af099c4ad0a","observation_id":"f8857d48-a2fb-4254-9c28-a875520e6653","resolution":{"observed_at":"2026-08-15T17:16:59.185567Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:16:59.286136Z","title":"SARAH: a novel method for machine learning problems using stochastic recursive gradient","venue":null,"work_id":"44d9026e-6ad9-4ede-bff0-7bae0170162d","year":2017},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.181888Z"},"links":{"citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:e98fefe39eb75b5f620f8be5ec12ae2deab75577647148e0ff266a0a8b603eb3","observation_id":"4cd37360-f9b9-4467-9dd1-20d1074e2544","resolution":{"observed_at":"2026-08-15T17:16:59.289987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02648","last_updated":"2025-01-13T19:05:07Z","snapshot_observed_at":"2026-08-18T14:33:50.683664Z","submitted_at":"2024-03-05T04:35:59Z","title":"Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad","version":4},"cited_work":{"arxiv_id":"2403.02648","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.02648","snapshot_observed_at":"2026-08-15T17:16:59.263297Z","title":"Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad","venue":"cs.LG","work_id":"e06c7179-3c98-4cf8-b656-40f90163b385","year":2024},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.153695Z"},"links":{"cited_paper":"/paper/2403.02648","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:59bac33a947ca897a2b583d1b7b3d7a69a7eece278ad37f5094025215883736e","observation_id":"b272cc98-030d-462d-8609-7f695b3976b6","resolution":{"observed_at":"2026-08-15T17:16:59.269843Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05287","last_updated":"2022-08-10T11:36:00Z","snapshot_observed_at":"2026-08-16T16:40:00.324510Z","submitted_at":"2022-08-10T11:36:00Z","title":"Adaptive Learning Rates for Faster Stochastic Gradient Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.05287","snapshot_observed_at":"2026-08-15T17:16:59.168255Z","title":"Adaptive learning rates for faster stochastic gradient methods","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.168255Z"},"links":{"cited_paper":"/paper/2208.05287","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:590440331c923de34421580439514d93ec542cf04737158450fe8ceb2b987113","observation_id":"73479cd1-5da0-4eff-889b-74185d6a43ba","resolution":{"observed_at":"2026-08-15T17:16:59.168255Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:16:59.308156Z","title":"Aleksandr Beznosikov and Martin Takáˇc","venue":null,"work_id":"fd3501c1-5232-4767-afee-1d410be4ffbe","year":2021},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.149852Z"},"links":{"citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:69edc4c2b8683cfad4ad45ee2e2484f58b9464bde3348f8078962541606e3e97","observation_id":"f909ae24-62ce-4caf-a34c-3834df48234a","resolution":{"observed_at":"2026-08-15T17:16:59.311969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06101","last_updated":"2024-03-19T23:01:06Z","snapshot_observed_at":"2026-08-16T19:18:54.990265Z","submitted_at":"2023-06-09T17:59:35Z","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.06101","snapshot_observed_at":"2026-08-15T17:16:59.177735Z","title":"Prodigy: An expeditiously adaptive parameter-free learner","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.177735Z"},"links":{"cited_paper":"/paper/2306.06101","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:1d944bd472ae5c354f2be46847f4a3107cfaaea1528f06328735ab17d6ffbb67","observation_id":"a1d4dd46-052a-4550-a214-f0858022f07f","resolution":{"observed_at":"2026-08-15T17:16:59.177735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.12328","last_updated":"2022-05-20T21:11:21Z","snapshot_observed_at":"2026-08-16T17:18:49.917520Z","submitted_at":"2022-02-24T19:31:03Z","title":"Cutting Some Slack for SGD with Adaptive Polyak Stepsizes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12328","snapshot_observed_at":"2026-08-15T17:16:59.158704Z","title":"Robert Gower, Guillaume Garrigos, Nicolas Loizou, Dimitris Oikonomou, Konstantin Mishchenko, and Fabian Schaipp","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.158704Z"},"links":{"cited_paper":"/paper/2202.12328","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:127ed31e9fd8cfa2b9658f7f279d682257eaddc768d4aa372cc09ad69a263a07","observation_id":"c50d1f44-5958-4621-8c9c-f70daea224e0","resolution":{"observed_at":"2026-08-15T17:16:59.158704Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T17:16:59.297054Z","title":"SP2: A second order stochastic polyak method","venue":null,"work_id":"fe4ff35b-0042-4be5-9ea8-7fddb73b1ae9","year":2023},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.173239Z"},"links":{"citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:5ed34000457877e292b0fc152b5fcd4761f76c590e240cbf1842528b30003845","observation_id":"cfa78fd4-e21f-46aa-973a-e036e98018a4","resolution":{"observed_at":"2026-08-15T17:16:59.301045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00313","last_updated":"2022-08-02T17:48:25Z","snapshot_observed_at":"2026-08-18T14:32:37.177613Z","submitted_at":"2019-05-01T13:47:40Z","title":"Revisiting the Polyak step size","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00313","snapshot_observed_at":"2026-08-15T17:16:59.163782Z","title":"Revisiting the Polyak step size","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T17:16:59.163782Z"},"links":{"cited_paper":"/paper/1905.00313","citing_paper":"/paper/2508.17288"},"observation_digest":"sha256:2c136920380f871b9e203148a9c69bbfd6b55ef619a24179ed572553a97b0dca","observation_id":"7c58ed40-e93e-47e1-a86e-b62131b8c4c3","resolution":{"observed_at":"2026-08-15T17:16:59.163782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.17288","last_updated":"2025-08-24T10:25:42Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-17T09:54:12.634968Z","submitted_at":"2025-08-24T10:25:42Z","title":"Polyak Stepsize: Estimating Optimal Functional Values Without Parameters or Prior Knowledge"},"reference_resolution":{"displayed":10,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":10},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2508.17288."}