{"as_of":"2026-08-14T02:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:406f8066842f2156a9f136016589a4221d3545201d1f85c09edda1b93eb1629b","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":"2026-08-13T06:32:02.005865+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":"2026-08-11T00:38:48.844998Z","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":"2026-07-01T22:36:17.259517Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.06567","last_updated":"2024-12-07T13:23:39Z","snapshot_observed_at":"2026-08-12T23:51:34.827651Z","submitted_at":"2024-06-03T13:28:43Z","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06567","snapshot_observed_at":"2026-08-11T00:38:48.844998Z","title":"Available: http://arxiv.org/abs/2406.06567","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19442","last_updated":"2025-07-30T05:24:46Z","snapshot_observed_at":"2026-08-11T00:33:34.388194Z","submitted_at":"2024-12-27T04:17:57Z","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","version":3},"reference_index":213,"source":"pdf_text","source_observed_at":"2026-08-11T00:38:48.844998Z"},"links":{"cited_paper":"/paper/2406.06567","citing_paper":"/paper/2412.19442"},"observation_digest":"sha256:7d14926fa027522d509afa933740642b08a7b7e521c7c3c25b68871787b258b5","observation_id":"7c3ec9b0-19d3-44b4-9da1-a7138d508484","resolution":{"observed_at":"2026-08-11T00:38:48.844998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06567","last_updated":"2024-12-07T13:23:39Z","snapshot_observed_at":"2026-08-12T23:51:34.827651Z","submitted_at":"2024-06-03T13:28:43Z","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06567","snapshot_observed_at":"2026-08-10T23:19:22.990805Z","title":"Dha: Learning decoupled-head attention from trans- former checkpoints via adaptive heads fusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.20677","last_updated":"2025-07-26T13:33:06Z","snapshot_observed_at":"2026-08-14T01:42:01.823068Z","submitted_at":"2024-12-30T03:05:45Z","title":"Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-10T23:19:22.990805Z"},"links":{"cited_paper":"/paper/2406.06567","citing_paper":"/paper/2412.20677"},"observation_digest":"sha256:8ecaac2da902f204e429e4992184b61c49f197ef2071b28587be1811fe2bb50e","observation_id":"b3067072-352b-47bb-8ca1-7faa285b5a07","resolution":{"observed_at":"2026-08-10T23:19:22.990805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06567","last_updated":"2024-12-07T13:23:39Z","snapshot_observed_at":"2026-08-12T23:51:34.827651Z","submitted_at":"2024-06-03T13:28:43Z","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion","version":2},"cited_work":{"arxiv_id":"2406.06567","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.06567","snapshot_observed_at":"2026-07-01T22:36:17.259517Z","title":"arXiv preprint arXiv:2406.06567 , year =","venue":null,"work_id":"194d212e-cc88-4e93-8fbe-7414631ed6eb","year":null},"citing_paper":{"arxiv_id":"2606.04032","last_updated":"2026-08-12T18:36:37Z","snapshot_observed_at":"2026-08-14T01:20:52.761773Z","submitted_at":"2026-06-01T20:59:05Z","title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-06-28T15:14:49.475561Z"},"links":{"cited_paper":"/paper/2406.06567","citing_paper":"/paper/2606.04032"},"observation_digest":"sha256:de0cbe4dae0b7f6a22621a577bbf72f6dfaaa7c0bc4cc53b8d8b55e3be32c48a","observation_id":"dd86d25f-ea9c-4a62-be9f-27dc4c157145","resolution":{"observed_at":"2026-07-01T22:36:17.261031Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.06567/citation-record","integrity":"/paper/2406.06567/integrity","json":"/paper/2406.06567/citation-record.json","paper":"/paper/2406.06567"},"outbound":[],"paper":{"arxiv_id":"2406.06567","last_updated":"2024-12-07T13:23:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T23:51:34.827651Z","submitted_at":"2024-06-03T13:28:43Z","title":"DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.06567."}