{"as_of":"2026-08-11T06:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1bd710eae3a4853de62b6086f874676c3279f7c5a6db1a22fde4dca8983788d","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:15:00.329382Z","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":"2026-08-07T13:44:37.263502Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.05802","last_updated":"2022-02-03T06:16:05Z","snapshot_observed_at":"2026-08-09T03:32:23.627884Z","submitted_at":"2021-07-13T01:29:24Z","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.05802","snapshot_observed_at":"2026-08-11T00:15:00.329382Z","title":"W.; Fort, S.; Becker, N.; and Ganguli, S","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19616","last_updated":"2025-01-05T07:12:27Z","snapshot_observed_at":"2026-08-11T03:47:51.024169Z","submitted_at":"2024-12-27T12:23:39Z","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T00:15:00.329382Z"},"links":{"cited_paper":"/paper/2107.05802","citing_paper":"/paper/2412.19616"},"observation_digest":"sha256:8193f2562da5841a3b250ea98b763f0405cc5107e82639b84c3aa31a502d1f6f","observation_id":"d9110df9-ad4f-4915-bf96-666ad9c581c8","resolution":{"observed_at":"2026-08-11T00:15:00.329382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.05802","last_updated":"2022-02-03T06:16:05Z","snapshot_observed_at":"2026-08-09T03:32:23.627884Z","submitted_at":"2021-07-13T01:29:24Z","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","version":2},"cited_work":{"arxiv_id":"2107.05802","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.05802","snapshot_observed_at":"2026-08-07T13:44:37.263502Z","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","venue":"cs.LG","work_id":"47010271-0eef-4cb7-8a6c-e1c1ea384f37","year":2021},"citing_paper":{"arxiv_id":"2505.21226","last_updated":"2025-06-03T14:43:50Z","snapshot_observed_at":"2026-08-09T03:32:40.483446Z","submitted_at":"2025-05-27T14:10:46Z","title":"Why Do More Experts Fail? A Theoretical Analysis of Model Merging","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:33.847753Z"},"links":{"cited_paper":"/paper/2107.05802","citing_paper":"/paper/2505.21226"},"observation_digest":"sha256:615970f36f86e147b8781d6d9ee3f76c5ef6a99422bb15d1bc55fd8d5b3f3742","observation_id":"45931957-3294-4814-9ff7-98b9280b7feb","resolution":{"observed_at":"2026-08-07T13:44:37.342378Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2107.05802/citation-record","integrity":"/paper/2107.05802/integrity","json":"/paper/2107.05802/citation-record.json","paper":"/paper/2107.05802"},"outbound":[],"paper":{"arxiv_id":"2107.05802","last_updated":"2022-02-03T06:16:05Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T03:32:23.627884Z","submitted_at":"2021-07-13T01:29:24Z","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2107.05802."}