{"as_of":"2026-08-09T11:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6544b4e472cd0bfdb84942ce64c4edce527d6e86669aca9846b6789ff4fdde41","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T12:25:42.756424Z","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":"2026-05-20T17:46:47.082467Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.08124","last_updated":"2022-08-17T07:40:20Z","snapshot_observed_at":"2026-07-06T13:42:36.328169Z","submitted_at":"2022-08-17T07:40:20Z","title":"Boosting Distributed Training Performance of the Unpadded BERT Model","version":1},"cited_work":{"arxiv_id":"2208.08124","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.08124","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Boosting distributed training performance of the unpadded bert model","venue":null,"work_id":"44e0d4b5-9b6a-4b5b-93a9-cdde48689590","year":2022},"citing_paper":{"arxiv_id":"2405.21060","last_updated":"2024-05-31T17:50:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-05-31T17:50:01Z","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","version":1},"reference_index":110,"source":"pdf_text","source_observed_at":"2026-05-11T12:16:25.390683Z"},"links":{"cited_paper":"/paper/2208.08124","citing_paper":"/paper/2405.21060"},"observation_digest":"sha256:9c27bf79d46ab62e020e3124eb4ad518043afb136903ce53ccf216d8cd217ef7","observation_id":"e4ae31ce-bcb1-4a3e-8116-e6434251ee34","resolution":{"observed_at":"2026-05-11T12:16:26.010020Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.08124","last_updated":"2022-08-17T07:40:20Z","snapshot_observed_at":"2026-07-06T13:42:36.328169Z","submitted_at":"2022-08-17T07:40:20Z","title":"Boosting Distributed Training Performance of the Unpadded BERT Model","version":1},"cited_work":{"arxiv_id":"2208.08124","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.08124","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Boosting distributed training performance of the unpadded bert model","venue":null,"work_id":"44e0d4b5-9b6a-4b5b-93a9-cdde48689590","year":2022},"citing_paper":{"arxiv_id":"2412.13663","last_updated":"2024-12-19T06:32:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-18T09:39:44Z","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","version":2},"reference_index":209,"source":"arxiv_source","source_observed_at":"2026-05-20T17:46:46.845424Z"},"links":{"cited_paper":"/paper/2208.08124","citing_paper":"/paper/2412.13663"},"observation_digest":"sha256:74444ea97c5b77b02f056dc05222fe1cfd29c4fe0658f44b6efa644b0bd46daf","observation_id":"4ed4fc0d-507f-43a2-864f-8ca698d2eb3e","resolution":{"observed_at":"2026-05-20T17:46:47.084570Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.08124","last_updated":"2022-08-17T07:40:20Z","snapshot_observed_at":"2026-07-06T13:42:36.328169Z","submitted_at":"2022-08-17T07:40:20Z","title":"Boosting Distributed Training Performance of the Unpadded BERT Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.08124","snapshot_observed_at":"2026-08-08T12:25:42.756424Z","title":"Boosting distributed training performance of the un- padded bert model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07563","last_updated":"2025-02-11T14:01:39Z","snapshot_observed_at":"2026-08-08T12:15:35.512720Z","submitted_at":"2025-02-11T14:01:39Z","title":"LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T12:25:42.756424Z"},"links":{"cited_paper":"/paper/2208.08124","citing_paper":"/paper/2502.07563"},"observation_digest":"sha256:3b2fb4a3883d56206bd60e9cf4d6951c50975de4c99a9eed2352602fac77fb90","observation_id":"b7a65e53-4525-4a5c-b54c-566a1621e8df","resolution":{"observed_at":"2026-08-08T12:25:42.756424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2208.08124/citation-record","integrity":"/paper/2208.08124/integrity","json":"/paper/2208.08124/citation-record.json","paper":"/paper/2208.08124"},"outbound":[],"paper":{"arxiv_id":"2208.08124","last_updated":"2022-08-17T07:40:20Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-07-06T13:42:36.328169Z","submitted_at":"2022-08-17T07:40:20Z","title":"Boosting Distributed Training Performance of the Unpadded BERT Model"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2208.08124."}