{"as_of":"2026-08-21T07:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8688014ff8332d5f9ef42e431d6844245a840f2bef77c05d1ba34ea6dbd8d868","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":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":11,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":11,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:31:56.603881Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T04:31:56.753684Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"cited_work":{"arxiv_id":"2605.27662","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.27662","snapshot_observed_at":"2026-08-06T04:31:56.753684Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","venue":"cs.LG","work_id":"f911caee-5016-47b8-b76a-682a5980f631","year":2026},"citing_paper":{"arxiv_id":"2608.05136","last_updated":"2026-08-05T17:56:26Z","snapshot_observed_at":"2026-08-17T09:51:34.385982Z","submitted_at":"2026-08-05T17:56:26Z","title":"The Loss Does Not See the Basis, but Adam Does","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T04:31:56.603881Z"},"links":{"cited_paper":"/paper/2605.27662","citing_paper":"/paper/2608.05136"},"observation_digest":"sha256:a566c77904c932fe8cd4bbdb93a50ac3971171d85fb79f5ca5bddfdd8a47218d","observation_id":"fb20c61e-15f1-4c34-92cb-2ce4e1bef9b2","resolution":{"observed_at":"2026-08-06T04:31:56.756734Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2605.27662/citation-record","integrity":"/paper/2605.27662/integrity","json":"/paper/2605.27662/citation-record.json","paper":"/paper/2605.27662"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.23179","last_updated":"2025-07-27T09:40:09Z","snapshot_observed_at":"2026-08-20T10:25:28.326876Z","submitted_at":"2024-10-30T16:36:59Z","title":"Does equivariance matter at scale?","version":2},"cited_work":{"arxiv_id":"2410.23179","doi":"10.48550/arxiv.2410.23179","metadata_source":"arxiv_reference","pith_arxiv_id":"2410.23179","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Brehmer, S","venue":"arXiv (Cornell University)","work_id":"449c7cef-3264-4ca5-8b94-5558faef1bc7","year":2025},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"cited_paper":"/paper/2410.23179","citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:24d9072f14d86ca3bc1b1eb11b64d8f8872c613029855094b4bfa93c9fe99936","observation_id":"90e738ae-675c-43ec-8664-83af257ab9d5","resolution":{"observed_at":"2026-06-29T18:03:48.004078Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T17:59:03.152111Z","title":"Elhag, A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:93dae4847a8e45df2627f1fff8e42b34d473974415a2c692c16cd12c5d79d448","observation_id":"67ae714d-7bd5-4ece-92b9-c89e161008f3","resolution":{"observed_at":"2026-06-29T17:59:03.152111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":"1412.6980","doi":"10.1002/mrm.28086","metadata_source":"pith","pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Adam: A Method for Stochastic Optimization","venue":"cs.LG","work_id":"1910796d-9b52-4683-bf5c-de9632c1028b","year":2014},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:7222cb78e105e2dfc0881d348850aff72029d77f16225a23f373281bd3f89c28","observation_id":"7dce4038-4efd-4cde-abbf-a650bab38d5a","resolution":{"observed_at":"2026-06-29T18:03:47.597382Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.12224","last_updated":"2025-07-16T13:33:31Z","snapshot_observed_at":"2026-08-13T10:11:21.319788Z","submitted_at":"2025-07-16T13:33:31Z","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","version":1},"cited_work":{"arxiv_id":"2507.12224","doi":"10.48550/arxiv.2507.12224","metadata_source":"arxiv_reference","pith_arxiv_id":"2507.12224","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Optimizers qualitatively alter solutions and we should leverage this","venue":"ArXiv.org","work_id":"2c3638b4-b599-4ba7-a22b-debecf8353a0","year":2022},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"cited_paper":"/paper/2507.12224","citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:fac57f2186d02ab19430daf8c50200a65cdc7291ac2134b6a1c8f358072ba6cf","observation_id":"0751ef79-8d03-46b6-8692-4a2254da0e66","resolution":{"observed_at":"2026-06-29T18:03:48.001449Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1162/neco.1994.6.1.147","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URLhttps://doi.org/10.1162/neco.1994.6.1.147","venue":"Neural Computation","work_id":"6fbdbd03-37b4-454c-a1ae-ddf933b4154f","year":1994},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:f5bdc8c8b322a3220203740f57b7ae5dbf35f1cc1ecbed6191c5a8762f8ce689","observation_id":"97282371-aacd-41d2-8d1c-0d886d9da56a","resolution":{"observed_at":"2026-06-29T18:03:47.594632Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.00593","last_updated":"2017-04-10T22:25:25Z","snapshot_observed_at":"2026-08-14T21:27:28.037090Z","submitted_at":"2016-12-02T08:40:40Z","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","version":2},"cited_work":{"arxiv_id":"1612.00593","doi":"10.48550/arxiv.1612.00593","metadata_source":"pith","pith_arxiv_id":"1612.00593","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","venue":"cs.CV","work_id":"ce832b4e-62c9-4ea4-9ca1-996c5989f1a0","year":2016},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"cited_paper":"/paper/1612.00593","citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:e8886182443a3770126a2a5b52ccb9daad1fe249b3a4763b19a1c9e12e2fe2da","observation_id":"e4128130-beca-4421-9f3f-4237202705dd","resolution":{"observed_at":"2026-06-29T18:03:47.995713Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-07-11T14:19:08.528391+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T14:19:08.528391+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/sdata.2014.22","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantum chemistry structures and properties of 134 thousand molecules","venue":"Scientific Data","work_id":"82176313-2ed6-4afc-89b4-8845ab32e0ed","year":2014},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:1e82ca47d6f63d20b8a0706a20edfd09a3f50fb9e6a9ca1f41a4c7949f67a629","observation_id":"0d17e655-3b1d-4bde-befe-534f04331c65","resolution":{"observed_at":"2026-06-29T18:03:47.599198Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-07-13T07:20:08.297577+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T07:20:08.297577+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3326362","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Dynamic graph cnn for learning on point clouds","venue":"ACM Transactions on Graphics","work_id":"98eb70c5-fea6-480d-92ad-a5c3a246dca8","year":2019},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:e5ca8ff572db7078a010eb0d41f4c1be38caf418d04b59f400bae555707699ab","observation_id":"a5a623ef-82ec-4f22-ba6f-a4fd170da1a8","resolution":{"observed_at":"2026-06-29T18:03:47.601006Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-07-11T06:49:21.76296+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T06:49:21.76296+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-06-29T17:59:03.152111Z","title":"org/CorpusID:206592833","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:746a648a7e3bcee02e9ee5812114fce6a0e896ccacb1cfb817748fb6fd74f867","observation_id":"8ca68aa1-a0a5-4c30-8ec2-21725ba1feb9","resolution":{"observed_at":"2026-06-29T17:59:03.152111Z","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":"5380.1692","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T18:03:47.997144Z","title":"6 How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks A","venue":null,"work_id":"880d92ed-7e46-47f6-9ca4-59ba766b463b","year":2007},"citing_paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T17:59:03.152111Z"},"links":{"citing_paper":"/paper/2605.27662"},"observation_digest":"sha256:93cd40d41a7ea69d384478808410ab96ee9e3ac941c8450e04017af401fcca2c","observation_id":"9843ce7c-08d0-4f95-87d2-3aaefee50846","resolution":{"observed_at":"2026-06-29T18:03:47.998524Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.27662","last_updated":"2026-05-26T20:25:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-01T16:04:11.431819Z","submitted_at":"2026-05-26T20:25:44Z","title":"How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks"},"reference_resolution":{"displayed":10,"state_counts":{"malformed_identifier":1,"metadata_mismatch":5,"parse_uncertain":0,"unresolved":2,"verified_exact":2,"verified_fuzzy":0},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 1 inbound Pith citation observation for arXiv:2605.27662."}