{"as_of":"2026-08-08T00:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ea0505b6a86666401264f0467c9defa39da3f0d9bf74d8a1bcb94c5154b031df","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T06:03:19.353231Z","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":1,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.08553","last_updated":"2024-06-04T14:49:36Z","snapshot_observed_at":"2026-07-06T18:14:08.102261Z","submitted_at":"2024-05-14T12:41:11Z","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08553","snapshot_observed_at":"2026-08-07T06:03:19.353231Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11104","last_updated":"2025-06-06T20:24:36Z","snapshot_observed_at":"2026-08-07T20:41:32.031099Z","submitted_at":"2025-06-06T20:24:36Z","title":"DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T06:03:19.353231Z"},"links":{"cited_paper":"/paper/2405.08553","citing_paper":"/paper/2506.11104"},"observation_digest":"sha256:e62f8e0ceb92f82a310c3582afdaaf05cdcd24d9f160eb3ffd1790a32c18f62c","observation_id":"78a2e262-6928-4375-ae3e-d37f98c80da9","resolution":{"observed_at":"2026-08-07T06:03:19.353231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08553","last_updated":"2024-06-04T14:49:36Z","snapshot_observed_at":"2026-07-06T18:14:08.102261Z","submitted_at":"2024-05-14T12:41:11Z","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08553","snapshot_observed_at":"2026-08-06T17:47:40.252282Z","title":"Improving transformers with dynamically composable multi-head attention,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09955","last_updated":"2025-07-14T06:10:30Z","snapshot_observed_at":"2026-08-07T11:12:53.489576Z","submitted_at":"2025-07-14T06:10:30Z","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T17:47:40.252282Z"},"links":{"cited_paper":"/paper/2405.08553","citing_paper":"/paper/2507.09955"},"observation_digest":"sha256:079e4c42c2dc541050be416f0a6f493e33a9c1de2bac18a1b1db055f0ab7af62","observation_id":"a1c15df1-44df-4760-8fd7-c7bc65460b6e","resolution":{"observed_at":"2026-08-06T17:47:40.252282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08553","last_updated":"2024-06-04T14:49:36Z","snapshot_observed_at":"2026-07-06T18:14:08.102261Z","submitted_at":"2024-05-14T12:41:11Z","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","version":2},"cited_work":{"arxiv_id":"2405.08553","doi":"10.48550/arxiv.2405.08553","metadata_source":"arxiv_reference","pith_arxiv_id":"2405.08553","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Improving Transformers with Dynamically Composable Multi-Head Attention , url =","venue":"arXiv (Cornell University)","work_id":"37c481b9-5c86-423a-b4b4-540c0a483cb8","year":null},"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":135,"source":"arxiv_source","source_observed_at":"2026-06-28T23:29:02.457697Z"},"links":{"cited_paper":"/paper/2405.08553","citing_paper":"/paper/2606.07604"},"observation_digest":"sha256:304645ead5da43e38b41ec12fd3055ef4480439eeffd079ceab70adee18f5f27","observation_id":"6f90a1b9-e629-4ac6-bff4-7e4d0d4c2b0b","resolution":{"observed_at":"2026-06-28T23:32:46.651894Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.08553/citation-record","integrity":"/paper/2405.08553/integrity","json":"/paper/2405.08553/citation-record.json","paper":"/paper/2405.08553"},"outbound":[],"paper":{"arxiv_id":"2405.08553","last_updated":"2024-06-04T14:49:36Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T18:14:08.102261Z","submitted_at":"2024-05-14T12:41:11Z","title":"Improving Transformers with Dynamically Composable Multi-Head Attention"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.08553."}