{"as_of":"2026-08-05T01:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df6e78b97b12d1e1dc7fd060191a83b106c2a3c796fb5a9e765dca2634292e23","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":"2026-08-04T06:34:03.388597+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":"2026-06-28T23:29:02.457697Z","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":"2026-07-10T06:15:00.866473Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.08801","last_updated":"2024-04-16T07:27:58Z","snapshot_observed_at":"2026-07-06T17:59:38.202928Z","submitted_at":"2024-04-12T20:28:14Z","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","version":2},"cited_work":{"arxiv_id":"2404.08801","doi":"10.48550/arxiv.2404.08801","metadata_source":"arxiv_reference","pith_arxiv_id":"2404.08801","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Megalodon: Efficient llm pretraining and inference with unlimited context length","venue":null,"work_id":"2e07dedc-8e8c-466b-9b5a-d919c2f2ebd4","year":2024},"citing_paper":{"arxiv_id":"2407.08608","last_updated":"2024-07-12T22:15:02Z","snapshot_observed_at":"2026-07-06T18:44:53.587276Z","submitted_at":"2024-07-11T15:44:48Z","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-20T19:45:36.337956Z"},"links":{"cited_paper":"/paper/2404.08801","citing_paper":"/paper/2407.08608"},"observation_digest":"sha256:06d7ed472e8b9eb15291602adbe9637bb4a061f26ad3f63ea4f1359550b1ec26","observation_id":"6d2d3949-b278-4456-9897-4b2c998629c3","resolution":{"observed_at":"2026-05-20T19:45:36.488402Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08801","last_updated":"2024-04-16T07:27:58Z","snapshot_observed_at":"2026-07-06T17:59:38.202928Z","submitted_at":"2024-04-12T20:28:14Z","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","version":2},"cited_work":{"arxiv_id":"2404.08801","doi":"10.48550/arxiv.2404.08801","metadata_source":"arxiv_reference","pith_arxiv_id":"2404.08801","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Megalodon: Efficient llm pretraining and inference with unlimited context length","venue":null,"work_id":"2e07dedc-8e8c-466b-9b5a-d919c2f2ebd4","year":2024},"citing_paper":{"arxiv_id":"2606.07604","last_updated":"2026-05-29T09:40:38Z","snapshot_observed_at":"2026-08-03T04:00:50.272221Z","submitted_at":"2026-05-29T09:40:38Z","title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","version":1},"reference_index":138,"source":"arxiv_source","source_observed_at":"2026-06-28T23:29:02.457697Z"},"links":{"cited_paper":"/paper/2404.08801","citing_paper":"/paper/2606.07604"},"observation_digest":"sha256:f7b380727e1d745027c358d57890f95f74806362eeaf8c19bae906e13a2e7cf3","observation_id":"9b249aca-03dc-451b-bd9e-f95c98800d91","resolution":{"observed_at":"2026-06-28T23:32:46.466586Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.08801/citation-record","integrity":"/paper/2404.08801/integrity","json":"/paper/2404.08801/citation-record.json","paper":"/paper/2404.08801"},"outbound":[],"paper":{"arxiv_id":"2404.08801","last_updated":"2024-04-16T07:27:58Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:59:38.202928Z","submitted_at":"2024-04-12T20:28:14Z","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2404.08801."}