{"as_of":"2026-08-09T11:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:511252b99d6f3f311767e081f928789af621249e82a30590c43ff7103a6c8965","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T15:15:46.529677Z","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":"2026-05-15T01:39:38.316104Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.06644","last_updated":"2021-09-09T23:08:29Z","snapshot_observed_at":"2026-08-09T06:35:26.842514Z","submitted_at":"2021-04-14T06:30:36Z","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.06644","snapshot_observed_at":"2026-08-07T15:15:46.529677Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15769","last_updated":"2025-05-21T17:18:51Z","snapshot_observed_at":"2026-08-07T15:09:44.885622Z","submitted_at":"2025-05-21T17:18:51Z","title":"Transfer of Structural Knowledge from Synthetic Languages","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T15:15:46.529677Z"},"links":{"cited_paper":"/paper/2104.06644","citing_paper":"/paper/2505.15769"},"observation_digest":"sha256:9498ef086f29290cc7cf8c73f88bbd2bce7fd3729a5072623323e35bc06817f5","observation_id":"fb8c5901-6a8c-4260-973d-647f5256ed96","resolution":{"observed_at":"2026-08-07T15:15:46.529677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.06644","last_updated":"2021-09-09T23:08:29Z","snapshot_observed_at":"2026-08-09T06:35:26.842514Z","submitted_at":"2021-04-14T06:30:36Z","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","version":2},"cited_work":{"arxiv_id":"2104.06644","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.06644","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2104.06644 , year=","venue":null,"work_id":"14f16fc6-a686-4e71-8dab-a554a5faea5a","year":null},"citing_paper":{"arxiv_id":"2605.14567","last_updated":"2026-05-14T08:37:28Z","snapshot_observed_at":"2026-08-03T00:46:36.800591Z","submitted_at":"2026-05-14T08:37:28Z","title":"Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-15T01:39:21.733359Z"},"links":{"cited_paper":"/paper/2104.06644","citing_paper":"/paper/2605.14567"},"observation_digest":"sha256:715a1c6be07880f78ad7abbf7f7a5fe6dbd928b1df6890d3a49176d8d071786e","observation_id":"736fd76c-6555-4191-8cc9-ccfcc88d454e","resolution":{"observed_at":"2026-05-15T01:39:38.318872Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2104.06644/citation-record","integrity":"/paper/2104.06644/integrity","json":"/paper/2104.06644/citation-record.json","paper":"/paper/2104.06644"},"outbound":[],"paper":{"arxiv_id":"2104.06644","last_updated":"2021-09-09T23:08:29Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T06:35:26.842514Z","submitted_at":"2021-04-14T06:30:36Z","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little"},"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 2 inbound Pith citation observations for arXiv:2104.06644."}