{"as_of":"2026-08-07T10:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a23c91c2158724f9149cefe348446ba16cdddc6a46997e85be1ea530cfaf2458","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":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:12:03.536337Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":44,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":"1910.07454","doi":"10.48550/arxiv.1910.07454","metadata_source":"arxiv_reference","pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhiyuan Li and Sanjeev Arora","venue":"arXiv (Cornell University)","work_id":"83da90a5-e133-42ac-b393-76e279843d54","year":1910},"citing_paper":{"arxiv_id":"2507.15970","last_updated":"2026-05-15T15:54:48Z","snapshot_observed_at":"2026-08-01T20:25:12.383467Z","submitted_at":"2025-07-21T18:06:29Z","title":"CIS-BWE: Chaos-Informed Speech Bandwidth Extension","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-22T00:37:08.364861Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2507.15970"},"observation_digest":"sha256:393068d712aa34163c6429cbe0b834d9f1c59e05d93982c974adc1179d560bae","observation_id":"06281ab7-9b3c-41ea-863b-feb85b06a267","resolution":{"observed_at":"2026-05-22T00:40:51.639835Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-06T15:12:03.536337Z","title":", author Arora, S","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.16571","last_updated":"2025-07-22T13:23:57Z","snapshot_observed_at":"2026-08-06T15:04:30.446130Z","submitted_at":"2025-07-22T13:23:57Z","title":"Data-Driven Adaptive Gradient Recovery for Unstructured Finite Volume Computations","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T15:12:03.536337Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2507.16571"},"observation_digest":"sha256:16dc3cbd815aed75f62c17c4bbec45ac1131eadcae9da2fee913919fd8faffc2","observation_id":"9c2ee32a-94b6-434f-bac1-134b73ef58f3","resolution":{"observed_at":"2026-08-06T15:12:03.536337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-06T12:28:42.277183Z","title":"& Arora, S","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21749","last_updated":"2025-07-29T12:31:21Z","snapshot_observed_at":"2026-08-06T16:58:34.640397Z","submitted_at":"2025-07-29T12:31:21Z","title":"Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T12:28:42.277183Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2507.21749"},"observation_digest":"sha256:cb68af404fd980bcd51cf71f78ab56a6d47c12d3e269c9618e44da273e806450","observation_id":"baa989bd-c063-468f-b6ad-8b9df202b558","resolution":{"observed_at":"2026-08-06T12:28:42.277183Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-06T11:41:58.595410Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22524","last_updated":"2026-06-18T06:54:38Z","snapshot_observed_at":"2026-08-06T11:41:57.266296Z","submitted_at":"2025-07-30T09:50:43Z","title":"HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T11:41:58.595410Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2507.22524"},"observation_digest":"sha256:081df9308ebcc9ca32d8fd8e6651299d377bc314854637b7315c3fa8eb7d61c2","observation_id":"e88324ab-93e1-47e4-ab61-ab26e9ea07b1","resolution":{"observed_at":"2026-08-06T11:41:58.595410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-03T19:38:20.795587Z","title":"An exponen- tial learning rate schedule for deep learning","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2511.23310","last_updated":"2026-08-03T07:38:27Z","snapshot_observed_at":"2026-08-06T23:30:12.269720Z","submitted_at":"2025-11-28T16:09:28Z","title":"Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T19:38:20.795587Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2511.23310"},"observation_digest":"sha256:02e8e569d515b0737ad46381ae1d5e884cf1efc63b8037dd653c40f19a7278d6","observation_id":"a7e70c5d-ca58-4e06-8731-23af5144ae74","resolution":{"observed_at":"2026-08-03T19:38:20.795587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-04T06:47:16.806756Z","title":"An exponen- tial learning rate schedule for deep learning","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2511.23310","last_updated":"2026-08-03T07:38:27Z","snapshot_observed_at":"2026-08-06T23:30:12.269720Z","submitted_at":"2025-11-28T16:09:28Z","title":"Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T06:47:16.806756Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2511.23310"},"observation_digest":"sha256:335c4f1ab90d503de6d82a4e282574be1ab1543153c78eb87d4aa25cd146ee87","observation_id":"ed123b43-a3e8-4bbe-9566-2c76e2078605","resolution":{"observed_at":"2026-08-04T06:47:16.806756Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":"1910.07454","doi":"10.48550/arxiv.1910.07454","metadata_source":"arxiv_reference","pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhiyuan Li and Sanjeev Arora","venue":"arXiv (Cornell University)","work_id":"83da90a5-e133-42ac-b393-76e279843d54","year":1910},"citing_paper":{"arxiv_id":"2605.04418","last_updated":"2026-05-06T02:22:06Z","snapshot_observed_at":"2026-07-06T23:17:13.770090Z","submitted_at":"2026-05-06T02:22:06Z","title":"Demystifying Manifold Constraints in LLM Pre-training","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-08T17:44:44.438637Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2605.04418"},"observation_digest":"sha256:3509218c4f113ad36fff9104eb2919c334c2d18201790c9d44fc4424c116fe30","observation_id":"c6751a95-31bf-4211-9702-2f6b1432e5dc","resolution":{"observed_at":"2026-05-11T17:16:08.896788Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":"1910.07454","doi":"10.48550/arxiv.1910.07454","metadata_source":"arxiv_reference","pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhiyuan Li and Sanjeev Arora","venue":"arXiv (Cornell University)","work_id":"83da90a5-e133-42ac-b393-76e279843d54","year":1910},"citing_paper":{"arxiv_id":"2606.19302","last_updated":"2026-06-17T17:26:22Z","snapshot_observed_at":"2026-07-06T23:54:37.596257Z","submitted_at":"2026-06-17T17:26:22Z","title":"Optimal scenario design for climate emulation","version":1},"reference_index":235,"source":"arxiv_source","source_observed_at":"2026-06-26T18:43:06.382026Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2606.19302"},"observation_digest":"sha256:6a4e87d290d3f9a228ce1985bc70315764f3c05dbdf1949617d0aa285d47a674","observation_id":"07a4976f-5924-4386-8263-0c6bcc556fc7","resolution":{"observed_at":"2026-06-26T18:49:44.397297Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":"1910.07454","doi":"10.48550/arxiv.1910.07454","metadata_source":"arxiv_reference","pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Zhiyuan Li and Sanjeev Arora","venue":"arXiv (Cornell University)","work_id":"83da90a5-e133-42ac-b393-76e279843d54","year":1910},"citing_paper":{"arxiv_id":"2606.25971","last_updated":"2026-07-17T13:42:08Z","snapshot_observed_at":"2026-08-02T10:13:56.529128Z","submitted_at":"2026-06-24T15:40:26Z","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","version":1},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-06-25T20:05:09.179627Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2606.25971"},"observation_digest":"sha256:c300ed88ede216832acd64f6036e54fbd6906162770a5718d4bccd5b53fe59f6","observation_id":"261d8098-b02f-475a-a0af-167f974ae1cf","resolution":{"observed_at":"2026-07-04T20:30:07.771827Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-02T10:14:08.553485Z","title":"An exponential learning rate schedule for deep learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.25971","last_updated":"2026-07-17T13:42:08Z","snapshot_observed_at":"2026-08-02T10:13:56.529128Z","submitted_at":"2026-06-24T15:40:26Z","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-02T10:14:08.553485Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2606.25971"},"observation_digest":"sha256:36ea184b8167c4a2d916f076075d7c92887c805290dd7e897e04ef5efaab54c3","observation_id":"900b21f5-fc8f-4477-be28-2a2c0cc5f588","resolution":{"observed_at":"2026-08-02T10:14:08.553485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-01T22:29:30.146859Z","title":"Li and S","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2607.15742","last_updated":"2026-07-17T08:23:54Z","snapshot_observed_at":"2026-08-07T09:55:58.008637Z","submitted_at":"2026-07-17T08:23:54Z","title":"Path optimization method for the sign problem: Insights from random matrix models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T22:29:30.146859Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2607.15742"},"observation_digest":"sha256:52ce068a80702bd87198cfddd8dc89d659a43c04185c80dd641cfe744108f6eb","observation_id":"6006b382-1d48-4f9e-a0a2-85928852702d","resolution":{"observed_at":"2026-08-01T22:29:30.146859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07454","snapshot_observed_at":"2026-08-01T08:50:41.107729Z","title":"arXiv preprint arXiv:1910.07454 , year=","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2607.21005","last_updated":"2026-07-23T07:39:03Z","snapshot_observed_at":"2026-08-06T16:38:33.932762Z","submitted_at":"2026-07-23T07:39:03Z","title":"Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T08:50:41.107729Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2607.21005"},"observation_digest":"sha256:88d4b1ba398b3928d0d2f0ad07dba9f0b7179d89de19559c766a65e66251775d","observation_id":"93e607d3-3560-4973-bbc3-58267e82bf76","resolution":{"observed_at":"2026-08-01T08:50:41.107729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1910.07454/citation-record","integrity":"/paper/1910.07454/integrity","json":"/paper/1910.07454/citation-record.json","paper":"/paper/1910.07454"},"outbound":[],"paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T08:30:04.777443Z","submitted_at":"2019-10-16T16:22:58Z","title":"An Exponential Learning Rate Schedule for 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 12 inbound Pith citation observations for arXiv:1910.07454."}