{"as_of":"2026-08-09T06:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0498056febb52e1460c8a12a4358b2d5aa4ce8ee91c366316bf02dbeeb881039","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":"2026-08-08T06:32:00.761636+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":"2026-08-08T16:39:14.235842Z","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":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.13233","last_updated":"2024-10-15T04:11:19Z","snapshot_observed_at":"2026-07-06T19:05:14.227812Z","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13233","snapshot_observed_at":"2026-08-08T16:39:14.235842Z","title":"Multi-layer transformers gradient can be approximated in almost linear time","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06167","last_updated":"2025-02-10T05:36:30Z","snapshot_observed_at":"2026-08-09T01:42:08.911908Z","submitted_at":"2025-02-10T05:36:30Z","title":"Universal Approximation of Visual Autoregressive Transformers","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T16:39:14.235842Z"},"links":{"cited_paper":"/paper/2408.13233","citing_paper":"/paper/2502.06167"},"observation_digest":"sha256:bf066ebb67548cb7ef609f23af66c94ed2dd4a0e7178409451e9584eb0eb9fe3","observation_id":"c3f26e8f-2dc7-4dea-8940-3ad8ebe86040","resolution":{"observed_at":"2026-08-08T16:39:14.235842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13233","last_updated":"2024-10-15T04:11:19Z","snapshot_observed_at":"2026-07-06T19:05:14.227812Z","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13233","snapshot_observed_at":"2026-08-08T10:20:15.414553Z","title":"Multi-layer transformers gradient can be approximated in almost linear time","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.08150","last_updated":"2025-02-12T06:30:01Z","snapshot_observed_at":"2026-08-09T01:42:36.516995Z","submitted_at":"2025-02-12T06:30:01Z","title":"Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T10:20:15.414553Z"},"links":{"cited_paper":"/paper/2408.13233","citing_paper":"/paper/2502.08150"},"observation_digest":"sha256:5cd4db3794b5164105f6fb39785c5f6f7874784fc4c712b11901caea00592678","observation_id":"ff9ebee8-c2c2-40b2-88bf-cef2552a20cf","resolution":{"observed_at":"2026-08-08T10:20:15.414553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13233","last_updated":"2024-10-15T04:11:19Z","snapshot_observed_at":"2026-07-06T19:05:14.227812Z","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13233","snapshot_observed_at":"2026-08-07T15:11:01.085476Z","title":"Multi-layer transformers gradient can be approximated in almost linear time","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16284","last_updated":"2025-05-22T06:26:28Z","snapshot_observed_at":"2026-08-07T22:03:10.571335Z","submitted_at":"2025-05-22T06:26:28Z","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T15:11:01.085476Z"},"links":{"cited_paper":"/paper/2408.13233","citing_paper":"/paper/2505.16284"},"observation_digest":"sha256:09ba4285f5109eb38bcc8a002b33a908284765dc15853bc4716c7f2fc260ba2a","observation_id":"27335392-8eab-45ff-b9d4-e10df6807577","resolution":{"observed_at":"2026-08-07T15:11:01.085476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13233","last_updated":"2024-10-15T04:11:19Z","snapshot_observed_at":"2026-07-06T19:05:14.227812Z","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","version":2},"cited_work":{"arxiv_id":"2408.13233","doi":"10.48550/arxiv.2408.13233","metadata_source":"arxiv_reference","pith_arxiv_id":"2408.13233","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"5111fd8d-d6b9-4600-904a-0d373edf882a","year":2024},"citing_paper":{"arxiv_id":"2604.11810","last_updated":"2026-04-09T14:08:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-09T14:08:01Z","title":"GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T18:06:46.131725Z"},"links":{"cited_paper":"/paper/2408.13233","citing_paper":"/paper/2604.11810"},"observation_digest":"sha256:f3e1aa7259c468b5234504694343ee120433595eaf4f8d6e9b76857aa99e36cc","observation_id":"4c338d25-7b7a-48f0-9bde-7005007a57a1","resolution":{"observed_at":"2026-05-10T20:30:48.976461Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2408.13233/citation-record","integrity":"/paper/2408.13233/integrity","json":"/paper/2408.13233/citation-record.json","paper":"/paper/2408.13233"},"outbound":[],"paper":{"arxiv_id":"2408.13233","last_updated":"2024-10-15T04:11:19Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:05:14.227812Z","submitted_at":"2024-08-23T17:16:43Z","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2408.13233."}