{"as_of":"2026-08-20T08:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4a54f6daaa626fcb7d3451561832993a222814275266c2c747b856d428ef6af9","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:39:38.259249Z","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":"2026-08-07T00:43:10.358066Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06184","snapshot_observed_at":"2026-08-10T21:39:38.259249Z","title":"The boundary of neural network trainability is fractal","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.04286","last_updated":"2025-02-15T01:26:37Z","snapshot_observed_at":"2026-08-12T11:48:36.826994Z","submitted_at":"2025-01-08T05:24:11Z","title":"Mapping the Edge of Chaos: Fractal-Like Boundaries in The Trainability of Decoder-Only Transformer Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:39:38.259249Z"},"links":{"cited_paper":"/paper/2402.06184","citing_paper":"/paper/2501.04286"},"observation_digest":"sha256:ea33a472db9748e4bd6753de0494d1e1194ba390578f39bf5ebe3f94382b9408","observation_id":"0de319b2-f0c5-4213-9eef-8af26bb01d74","resolution":{"observed_at":"2026-08-10T21:39:38.259249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal","version":1},"cited_work":{"arxiv_id":"2402.06184","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.06184","snapshot_observed_at":"2026-08-07T00:43:10.358066Z","title":"The boundary of neural network trainability is fractal","venue":"cs.LG","work_id":"86ab72df-55de-401b-abf0-2915a05f88a0","year":2024},"citing_paper":{"arxiv_id":"2506.13234","last_updated":"2025-06-16T08:35:16Z","snapshot_observed_at":"2026-08-17T06:48:19.330409Z","submitted_at":"2025-06-16T08:35:16Z","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T00:43:08.680044Z"},"links":{"cited_paper":"/paper/2402.06184","citing_paper":"/paper/2506.13234"},"observation_digest":"sha256:19b6f6dae9b355e7502e47b8c52fbcffe5d902e6038e14971d7953b1d0f9e521","observation_id":"ac025386-8e78-47e3-b420-663ccce4141c","resolution":{"observed_at":"2026-08-07T00:43:10.423646Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06184","snapshot_observed_at":"2026-07-12T01:11:50.444218Z","title":"arXiv preprint arXiv:2402.06184 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03613","last_updated":"2026-07-03T22:03:13Z","snapshot_observed_at":"2026-08-10T02:28:20.618211Z","submitted_at":"2026-07-03T22:03:13Z","title":"Implicit Bias of SGD in Multivariate ReLU Networks: Effective Width Collapse","version":1},"reference_index":120,"source":"arxiv_source","source_observed_at":"2026-07-12T01:11:50.444218Z"},"links":{"cited_paper":"/paper/2402.06184","citing_paper":"/paper/2607.03613"},"observation_digest":"sha256:32304ba5bf692daad19ef2987f394b475fd7623a101c19f7f39ada1b41d6fcbf","observation_id":"93310c06-d348-4dca-b722-4524c5a892f4","resolution":{"observed_at":"2026-07-12T01:11:50.444218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06184","snapshot_observed_at":"2026-07-31T07:42:46.557974Z","title":"Sohl-Dickstein, The boundary of neural network trainability is fractal, arXiv:2402.06184 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28428","last_updated":"2026-08-06T01:10:43Z","snapshot_observed_at":"2026-08-09T23:10:00.385611Z","submitted_at":"2026-07-30T16:05:51Z","title":"Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T07:42:46.557974Z"},"links":{"cited_paper":"/paper/2402.06184","citing_paper":"/paper/2607.28428"},"observation_digest":"sha256:7e750ce6e3d11fd977c2e9dc1ce19c2cca2c8dbf606ee812ff24e7b7fed09b14","observation_id":"2dd9f7be-b165-4543-805f-f9c7ca376a7b","resolution":{"observed_at":"2026-07-31T07:42:46.557974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06184","snapshot_observed_at":"2026-08-04T03:23:47.495003Z","title":"Sohl-Dickstein, The boundary of neural network trainability is fractal, arXiv:2402.06184 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.28428","last_updated":"2026-08-06T01:10:43Z","snapshot_observed_at":"2026-08-09T23:10:00.385611Z","submitted_at":"2026-07-30T16:05:51Z","title":"Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T03:23:47.495003Z"},"links":{"cited_paper":"/paper/2402.06184","citing_paper":"/paper/2607.28428"},"observation_digest":"sha256:0c1a69686fae7881e48895dbb2e3575ca5adb6b025b68c7f7bb2d20bc0733270","observation_id":"d208ca87-b1eb-4a30-a6fa-78f5ac66a57c","resolution":{"observed_at":"2026-08-04T03:23:47.495003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.06184/citation-record","integrity":"/paper/2402.06184/integrity","json":"/paper/2402.06184/citation-record.json","paper":"/paper/2402.06184"},"outbound":[],"paper":{"arxiv_id":"2402.06184","last_updated":"2024-02-09T04:46:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:20:00.878259Z","submitted_at":"2024-02-09T04:46:48Z","title":"The boundary of neural network trainability is fractal"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2402.06184."}