{"as_of":"2026-08-05T20:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:49498646dec1462c1a4ee0330d67b8fdb40bf83e731ea2d43987f72097be5de3","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":"2026-08-05T06:32:48.257954+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":"2026-06-30T18:36:56.248838Z","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":"2026-07-01T14:55:48.338931Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01906","last_updated":"2025-08-15T20:46:58Z","snapshot_observed_at":"2026-08-04T16:07:38.488370Z","submitted_at":"2025-02-04T00:46:11Z","title":"D-Attn: Decomposed Attention for Large Vision-and-Language Models","version":2},"cited_work":{"arxiv_id":"2502.01906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01906","snapshot_observed_at":"2026-07-01T14:55:48.338931Z","title":"Rethinking homogeneity of vision and text tokens in large vision-and-language models (D-Attn).arXiv preprint arXiv:2502.01906","venue":null,"work_id":"8403954b-0710-4439-a95a-d43f8989b89e","year":null},"citing_paper":{"arxiv_id":"2605.18359","last_updated":"2026-05-26T13:49:58Z","snapshot_observed_at":"2026-08-02T17:52:26.858372Z","submitted_at":"2026-05-18T13:12:50Z","title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-20T11:10:58.225078Z"},"links":{"cited_paper":"/paper/2502.01906","citing_paper":"/paper/2605.18359"},"observation_digest":"sha256:b16be9ae053f708410d462e09976735d3293d6f9d56fb9bc234642f1511902a5","observation_id":"5edf4a9f-7223-4950-9f63-3642631244a3","resolution":{"observed_at":"2026-05-20T11:13:13.456501Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01906","last_updated":"2025-08-15T20:46:58Z","snapshot_observed_at":"2026-08-04T16:07:38.488370Z","submitted_at":"2025-02-04T00:46:11Z","title":"D-Attn: Decomposed Attention for Large Vision-and-Language Models","version":2},"cited_work":{"arxiv_id":"2502.01906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01906","snapshot_observed_at":"2026-07-01T14:55:48.338931Z","title":"Rethinking homogeneity of vision and text tokens in large vision-and-language models (D-Attn).arXiv preprint arXiv:2502.01906","venue":null,"work_id":"8403954b-0710-4439-a95a-d43f8989b89e","year":null},"citing_paper":{"arxiv_id":"2605.18359","last_updated":"2026-05-26T13:49:58Z","snapshot_observed_at":"2026-08-02T17:52:26.858372Z","submitted_at":"2026-05-18T13:12:50Z","title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-30T18:36:56.248838Z"},"links":{"cited_paper":"/paper/2502.01906","citing_paper":"/paper/2605.18359"},"observation_digest":"sha256:1955501184d8167d0ff0b43a44c8680ff3d489e6419674cbd5574b269af9be38","observation_id":"6161ec78-0fa6-4416-991c-7ef33d749c76","resolution":{"observed_at":"2026-07-01T14:55:48.340671Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01906/citation-record","integrity":"/paper/2502.01906/integrity","json":"/paper/2502.01906/citation-record.json","paper":"/paper/2502.01906"},"outbound":[],"paper":{"arxiv_id":"2502.01906","last_updated":"2025-08-15T20:46:58Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T16:07:38.488370Z","submitted_at":"2025-02-04T00:46:11Z","title":"D-Attn: Decomposed Attention for Large Vision-and-Language Models"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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:2502.01906."}