{"as_of":"2026-08-10T02:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:786eee33f153d92780f11340d7caddceafb0cc19698d7ea81cf4d9a83537c24a","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":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":16,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T16:20:57.730990Z","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-09T16:20:57.730990Z","title":"and Arora, S","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2502.01179","last_updated":"2025-05-29T14:57:31Z","snapshot_observed_at":"2026-08-09T16:14:55.797133Z","submitted_at":"2025-02-03T09:13:09Z","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T16:20:57.730990Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2502.01179"},"observation_digest":"sha256:7bcc74a78e4c06f7670e39e914c553e92e2bb3c319098c9abf7faf94a1d38c9e","observation_id":"bbe22a72-ee5c-4be1-8873-d46d4b47a96c","resolution":{"observed_at":"2026-08-09T16:20:57.730990Z","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-07T19:51:41.138639Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.09993","last_updated":"2025-02-14T08:24:38Z","snapshot_observed_at":"2026-08-09T08:50:03.119629Z","submitted_at":"2025-02-14T08:24:38Z","title":"Navigating Label Ambiguity for Facial Expression Recognition in the Wild","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T19:51:41.138639Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2502.09993"},"observation_digest":"sha256:46f032689764cbffc286ed07a68bffcefd243ab9e7ae3b24cc9f0dc57875dd16","observation_id":"9861d039-6f20-454a-93d9-946f68a90952","resolution":{"observed_at":"2026-08-07T19:51:41.138639Z","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-07T11:12:43.088731Z","title":"An exponential learning rate schedule for deep learning","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.03323","last_updated":"2025-06-03T19:14:18Z","snapshot_observed_at":"2026-08-09T07:51:30.398298Z","submitted_at":"2025-06-03T19:14:18Z","title":"Fast Machine Learning for Quantum Control of Microwave Qudits on Edge Hardware","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:12:43.088731Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2506.03323"},"observation_digest":"sha256:6f6120145e1ca873a63be2840f32873f908ed5c5286c044c8ca77743752551fd","observation_id":"9065601f-5e8f-4027-afc4-a080eab58ae7","resolution":{"observed_at":"2026-08-07T11:12:43.088731Z","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-07T11:07:16.003624Z","title":"An exponential learning rate schedule for deep learning,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.03515","last_updated":"2025-06-04T03:02:18Z","snapshot_observed_at":"2026-08-08T02:14:58.494663Z","submitted_at":"2025-06-04T03:02:18Z","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:07:16.003624Z"},"links":{"cited_paper":"/paper/1910.07454","citing_paper":"/paper/2506.03515"},"observation_digest":"sha256:8fdcb903ded15b38d34c69bd3652a5122d40f3fa7f67cdffdecfe7a72c276e35","observation_id":"66ccd60d-2f71-4b6a-8be3-0647b003832d","resolution":{"observed_at":"2026-08-07T11:07:16.003624Z","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-08T15:43:33.769807Z","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":"sha256:3d759f20fdca03d6a2958e682364e4284560f765e8a8068ef70f1dd2b17a39ed","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 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-08-08T14:05:33.854211Z","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":"2026-08-07T13:18:24.305616Z","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":"sha256:7d3d797389f50b5909290aa2153e467cb43f2b4dd618a38ff0732651d3f5a173","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":"2026-08-08T14:05:33.854211Z","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":"sha256:5a7668d02e29fd95bc620b332f082e8108d0a8e82f8e0cc4eb03cbcb91cae5c7","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-07T20:31:29.978441Z","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":"sha256:992f3dd637d4cb8028ea7e67ea2e0ae83c844d5e9243d8e326855f4f03f22632","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-08T10:55:12.381857Z","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":"sha256:897b4e12347942b8104bb13805200dd9283862e537ff2e0952bd1ccd40f49e96","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-08T10:55:12.381857Z","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":"sha256:5fd118fe8c707abc03113945a7fd29265232592740b81a38280d9236ed76533b","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-09T01:35:47.502967Z","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:a1129f86b8da2c4a5418a965acd37883ef9b7b36d6799eec14e426ff7b7e3d11","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 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-08-08T14:05:33.854211Z","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":"sha256:0bee0367daf3eb712c85267b9b713eba757b45695cd0b946d9940b5ef42ffe86","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 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-08-08T14:05:33.854211Z","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":"sha256:760b3af50ae1c1e7f4564f483f4f4133be70645e4a3ed772744306d416c3e5ff","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 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07454","last_updated":"2019-11-21T11:01:34Z","snapshot_observed_at":"2026-08-08T14:05:33.854211Z","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":"sha256:14b4523900d954e7b86575543b7720ef258dc9dd93ec2779b5dcde38d37f0267","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-09T03:16:27.404332Z","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":"sha256:6fc2286437588c3bc1c72cf70034b7378e5bafadbbbd752040e824ad771c0d58","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":"2026-08-08T14:05:33.854211Z","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:dabdea33622061b211379c6b9b02205784cac10dacd80160ab186ad1447c0f93","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":"2026-08-08T14:05:33.854211Z","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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:1910.07454."}