{"as_of":"2026-08-07T19:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4315d759d3182e9648a18818db2b407bb330ad1cf824269b7cd4806bebd4af8d","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:14:26.536645Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T13:09:50.650340Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.09828","last_updated":"2023-05-16T22:12:25Z","snapshot_observed_at":"2026-08-05T20:29:14.196208Z","submitted_at":"2023-05-16T22:12:25Z","title":"Mimetic Initialization of Self-Attention Layers","version":1},"cited_work":{"arxiv_id":"2305.09828","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.09828","snapshot_observed_at":"2026-07-04T13:09:50.650340Z","title":"Mimetic initialization of self-attention layers","venue":null,"work_id":"2ae9be55-b786-4958-b25a-3c5dc4a29783","year":2023},"citing_paper":{"arxiv_id":"2405.13901","last_updated":"2026-05-15T17:05:43Z","snapshot_observed_at":"2026-07-06T18:18:07.839497Z","submitted_at":"2024-05-22T18:15:42Z","title":"Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers","version":6},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-24T00:33:22.959973Z"},"links":{"cited_paper":"/paper/2305.09828","citing_paper":"/paper/2405.13901"},"observation_digest":"sha256:8f2856384d03c7cbf9c327860bc80d3805337ce604602252fc4432af16007695","observation_id":"42993867-c768-4e6f-95b0-09f70b137391","resolution":{"observed_at":"2026-05-24T00:33:39.812038Z","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":"2305.09828","last_updated":"2023-05-16T22:12:25Z","snapshot_observed_at":"2026-08-05T20:29:14.196208Z","submitted_at":"2023-05-16T22:12:25Z","title":"Mimetic Initialization of Self-Attention Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.09828","snapshot_observed_at":"2026-08-07T13:14:26.536645Z","title":"and Kolter, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22308","last_updated":"2025-05-28T12:50:09Z","snapshot_observed_at":"2026-08-07T13:08:06.402787Z","submitted_at":"2025-05-28T12:50:09Z","title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:14:26.536645Z"},"links":{"cited_paper":"/paper/2305.09828","citing_paper":"/paper/2505.22308"},"observation_digest":"sha256:95586cc96bdc8892b639a503ae0e57c45baf833650804deabef70e255d8b3145","observation_id":"28d032f0-c492-4955-b7c8-7b66e8f9b5a1","resolution":{"observed_at":"2026-08-07T13:14:26.536645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09828","last_updated":"2023-05-16T22:12:25Z","snapshot_observed_at":"2026-08-05T20:29:14.196208Z","submitted_at":"2023-05-16T22:12:25Z","title":"Mimetic Initialization of Self-Attention Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.09828","snapshot_observed_at":"2026-08-03T06:55:10.112425Z","title":"Zico Kolter","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.21725","last_updated":"2026-05-27T19:52:53Z","snapshot_observed_at":"2026-08-04T21:23:57.701786Z","submitted_at":"2026-01-29T13:48:43Z","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T06:55:10.112425Z"},"links":{"cited_paper":"/paper/2305.09828","citing_paper":"/paper/2601.21725"},"observation_digest":"sha256:06f9f266d5dbf6c32696e48da9379a400484a02322dd7fb755123ea4401363dc","observation_id":"6022c5e8-d734-4a73-a274-ddff3e9d5d4f","resolution":{"observed_at":"2026-08-03T06:55:10.112425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09828","last_updated":"2023-05-16T22:12:25Z","snapshot_observed_at":"2026-08-05T20:29:14.196208Z","submitted_at":"2023-05-16T22:12:25Z","title":"Mimetic Initialization of Self-Attention Layers","version":1},"cited_work":{"arxiv_id":"2305.09828","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.09828","snapshot_observed_at":"2026-07-04T13:09:50.650340Z","title":"Mimetic initialization of self-attention layers","venue":null,"work_id":"2ae9be55-b786-4958-b25a-3c5dc4a29783","year":2023},"citing_paper":{"arxiv_id":"2606.26894","last_updated":"2026-06-25T11:26:57Z","snapshot_observed_at":"2026-07-07T00:01:10.711037Z","submitted_at":"2026-06-25T11:26:57Z","title":"Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-26T05:28:43.159404Z"},"links":{"cited_paper":"/paper/2305.09828","citing_paper":"/paper/2606.26894"},"observation_digest":"sha256:89a00545c80bd466853bfe6736df315eb86c15c34012573e40c841056b228a30","observation_id":"f6d4e78e-a597-4faf-ae9b-17a0e09e6826","resolution":{"observed_at":"2026-07-04T13:09:50.652233Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2305.09828/citation-record","integrity":"/paper/2305.09828/integrity","json":"/paper/2305.09828/citation-record.json","paper":"/paper/2305.09828"},"outbound":[],"paper":{"arxiv_id":"2305.09828","last_updated":"2023-05-16T22:12:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T20:29:14.196208Z","submitted_at":"2023-05-16T22:12:25Z","title":"Mimetic Initialization of Self-Attention Layers"},"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 4 inbound Pith citation observations for arXiv:2305.09828."}