{"as_of":"2026-08-14T01:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5cddbbfde61e9127f62abf0939e8a2ac40848349ab2f8de0e99ed46d4736d426","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:37:07.599724Z","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":"2026-06-28T17:22:24.617610Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.09650","last_updated":"2021-06-17T16:53:22Z","snapshot_observed_at":"2026-08-13T19:02:00.655809Z","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09650","snapshot_observed_at":"2026-08-12T11:37:07.599724Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18077","last_updated":"2025-06-08T21:23:22Z","snapshot_observed_at":"2026-08-12T13:32:45.295519Z","submitted_at":"2024-11-27T06:10:49Z","title":"MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T11:37:07.599724Z"},"links":{"cited_paper":"/paper/2106.09650","citing_paper":"/paper/2411.18077"},"observation_digest":"sha256:b405b561d666e72de20483b232d50235666c8987a88d70f861deaf7652da6cae","observation_id":"4f7676d9-5061-4d50-a2a4-ea539a3a263e","resolution":{"observed_at":"2026-08-12T11:37:07.599724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09650","last_updated":"2021-06-17T16:53:22Z","snapshot_observed_at":"2026-08-13T19:02:00.655809Z","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09650","snapshot_observed_at":"2026-08-07T05:05:40.392429Z","title":"Multi-head or single-head? an empirical comparison for transformer training.arXiv preprint arXiv:2106.09650,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09101","last_updated":"2025-06-10T15:27:32Z","snapshot_observed_at":"2026-08-11T22:22:20.929181Z","submitted_at":"2025-06-10T15:27:32Z","title":"Feature Shift Localization Network","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T05:05:40.392429Z"},"links":{"cited_paper":"/paper/2106.09650","citing_paper":"/paper/2506.09101"},"observation_digest":"sha256:e847d3ddc62eba02c9e59a807bd2ab819a9137f72a9da45c7fd0a58369410085","observation_id":"1daddfc0-f8ee-445d-a807-df2846e9bba9","resolution":{"observed_at":"2026-08-07T05:05:40.392429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09650","last_updated":"2021-06-17T16:53:22Z","snapshot_observed_at":"2026-08-13T19:02:00.655809Z","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","version":1},"cited_work":{"arxiv_id":"2106.09650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.09650","snapshot_observed_at":"2026-06-28T17:22:24.617610Z","title":"Guided inte- grated gradients: An adaptive path method for removing noise","venue":null,"work_id":"88b1ca27-c8bc-4363-8b18-686ed95c5d7f","year":2021},"citing_paper":{"arxiv_id":"2604.25315","last_updated":"2026-04-28T07:25:07Z","snapshot_observed_at":"2026-07-06T23:11:11.827339Z","submitted_at":"2026-04-28T07:25:07Z","title":"SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-07T16:51:03.537142Z"},"links":{"cited_paper":"/paper/2106.09650","citing_paper":"/paper/2604.25315"},"observation_digest":"sha256:9778d96215ec8737c8cf65e10bb1f9b6bcdf721243b949fb71fe7d1d579b87ef","observation_id":"452d638f-0b85-4487-be8b-a00b94974db8","resolution":{"observed_at":"2026-05-11T23:31:16.097939Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09650","last_updated":"2021-06-17T16:53:22Z","snapshot_observed_at":"2026-08-13T19:02:00.655809Z","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training","version":1},"cited_work":{"arxiv_id":"2106.09650","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.09650","snapshot_observed_at":"2026-06-28T17:22:24.617610Z","title":"Guided inte- grated gradients: An adaptive path method for removing noise","venue":null,"work_id":"88b1ca27-c8bc-4363-8b18-686ed95c5d7f","year":2021},"citing_paper":{"arxiv_id":"2606.01432","last_updated":"2026-05-31T19:59:58Z","snapshot_observed_at":"2026-08-12T13:31:16.591782Z","submitted_at":"2026-05-31T19:59:58Z","title":"Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T17:20:02.824564Z"},"links":{"cited_paper":"/paper/2106.09650","citing_paper":"/paper/2606.01432"},"observation_digest":"sha256:ef07f2014434e82891a2e1dc001ee942a5567bcac97bfac89b8529b20bd87fd1","observation_id":"d294607d-9782-4cbc-84d4-2507ccb231c1","resolution":{"observed_at":"2026-06-28T17:22:24.619142Z","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/2106.09650/citation-record","integrity":"/paper/2106.09650/integrity","json":"/paper/2106.09650/citation-record.json","paper":"/paper/2106.09650"},"outbound":[],"paper":{"arxiv_id":"2106.09650","last_updated":"2021-06-17T16:53:22Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-13T19:02:00.655809Z","submitted_at":"2021-06-17T16:53:22Z","title":"Multi-head or Single-head? An Empirical Comparison for Transformer Training"},"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 4 inbound Pith citation observations for arXiv:2106.09650."}