{"as_of":"2026-08-07T21:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d4b4f70eeeeffd1ca75c81d270ccb6383508ed26b6633b64afb7f9069131de7e","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":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T21:05:02.502481Z","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":"2026-07-01T21:56:15.441801Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-08-05T20:59:36.897052Z","title":"Towards understanding how attention mechanism works in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09627","last_updated":"2025-08-13T08:59:04Z","snapshot_observed_at":"2026-08-06T15:53:16.127835Z","submitted_at":"2025-08-13T08:59:04Z","title":"Physics- and geometry-aware spatio-spectral graph neural operator for time-independent and time-dependent PDEs","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-05T20:59:36.897052Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2508.09627"},"observation_digest":"sha256:79592d276cc989c4a60835e15590a8ff41cec414d6dbdb600f27a9dbbe2a35e2","observation_id":"fe4b9dc8-3e46-43ed-9d3a-6f8ce3ca128e","resolution":{"observed_at":"2026-08-05T20:59:36.897052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-08-05T21:05:02.502481Z","title":"Towards understanding how attention mechanism works in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.09628","last_updated":"2025-08-13T08:59:13Z","snapshot_observed_at":"2026-08-06T15:53:16.388100Z","submitted_at":"2025-08-13T08:59:13Z","title":"Attention's forward pass and Frank-Wolfe","version":1},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-05T21:05:02.502481Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2508.09628"},"observation_digest":"sha256:662a4569f372e70db6815e11a2e5f498da65d932ac6af7b009e73dca3c7618ca","observation_id":"02f2568a-cf97-47ad-8fe9-c5fa3b1a24af","resolution":{"observed_at":"2026-08-05T21:05:02.502481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":"2412.18288","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-07-01T21:56:15.441801Z","title":"Towards understanding how attention mechanism works in deep learning","venue":null,"work_id":"acad5ae8-042d-4436-b6ba-a1df8aba5f9c","year":2024},"citing_paper":{"arxiv_id":"2509.04154","last_updated":"2026-07-16T05:43:33Z","snapshot_observed_at":"2026-08-05T10:25:10.943738Z","submitted_at":"2025-09-04T12:29:14Z","title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","version":5},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-05-18T18:56:48.722344Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2509.04154"},"observation_digest":"sha256:4bcd646c8e6dc73207b2d223c51fe2aa8edfccabd667755e761fcbee4f60b675","observation_id":"5745ca25-4c14-4d87-9b02-61d40e725aa0","resolution":{"observed_at":"2026-05-18T19:01:46.313882Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-08-05T10:25:17.199621Z","title":"Towards understanding how attention mechanism works in deep learning, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04154","last_updated":"2026-07-16T05:43:33Z","snapshot_observed_at":"2026-08-05T10:25:10.943738Z","submitted_at":"2025-09-04T12:29:14Z","title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","version":9},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-05T10:25:17.199621Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2509.04154"},"observation_digest":"sha256:04e9b825fcc7e7c9a3dd965a0d66dbb3004ed88e74fef28b0077f4ed6d2ea18b","observation_id":"bf9ec9b5-68dd-413d-ac48-f943d92837ce","resolution":{"observed_at":"2026-08-05T10:25:17.199621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":"2412.18288","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-07-01T21:56:15.441801Z","title":"Towards understanding how attention mechanism works in deep learning","venue":null,"work_id":"acad5ae8-042d-4436-b6ba-a1df8aba5f9c","year":2024},"citing_paper":{"arxiv_id":"2606.01563","last_updated":"2026-06-01T02:08:40Z","snapshot_observed_at":"2026-08-06T03:26:36.028360Z","submitted_at":"2026-06-01T02:08:40Z","title":"MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T16:07:22.196982Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2606.01563"},"observation_digest":"sha256:0095422f5395c978c5845c608c2f18cbcec24fb0dfd427521f3ac32ee8358118","observation_id":"d1740aba-fbd5-4a2a-bea8-58baccbf15cd","resolution":{"observed_at":"2026-07-01T21:56:15.443916Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18288","snapshot_observed_at":"2026-07-14T10:03:27.747512Z","title":"CoRR , volume =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.10677","last_updated":"2026-07-12T09:44:54Z","snapshot_observed_at":"2026-07-16T23:18:57.897239Z","submitted_at":"2026-07-12T09:44:54Z","title":"From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-14T10:03:27.747512Z"},"links":{"cited_paper":"/paper/2412.18288","citing_paper":"/paper/2607.10677"},"observation_digest":"sha256:074df669c8246efb3f84e8a4e2e576bbe44d75614c4d776aac6286ca9dbaa32e","observation_id":"4368ff3f-46d2-4554-b36c-331c141bbd05","resolution":{"observed_at":"2026-07-14T10:03:27.747512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.18288/citation-record","integrity":"/paper/2412.18288/integrity","json":"/paper/2412.18288/citation-record.json","paper":"/paper/2412.18288"},"outbound":[],"paper":{"arxiv_id":"2412.18288","last_updated":"2024-12-24T08:52:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:12:40.901520Z","submitted_at":"2024-12-24T08:52:06Z","title":"Towards understanding how attention mechanism works in deep learning"},"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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2412.18288."}