{"as_of":"2026-08-09T11:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2437c51a7d347473a6e59271bdcff40cccb743c15acbc01234c2dd91172d9cdb","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T14:03:49.048605Z","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":"2026-05-11T06:41:28.869282Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.16663","last_updated":"2024-10-22T03:29:33Z","snapshot_observed_at":"2026-08-07T00:29:14.945462Z","submitted_at":"2024-10-22T03:29:33Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16663","snapshot_observed_at":"2026-08-07T14:03:49.048605Z","title":"Fastattention: Extend flashattention2 to npus and low-resource gpus","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20155","last_updated":"2025-05-26T15:57:08Z","snapshot_observed_at":"2026-08-08T04:39:03.740360Z","submitted_at":"2025-05-26T15:57:08Z","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:03:49.048605Z"},"links":{"cited_paper":"/paper/2410.16663","citing_paper":"/paper/2505.20155"},"observation_digest":"sha256:b8edf7029e6a20c65d70aa0aae69eeb2e59b377d781d596f00c146629cb8c872","observation_id":"06a0d854-3cc7-498b-a52b-adeb1053b518","resolution":{"observed_at":"2026-08-07T14:03:49.048605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16663","last_updated":"2024-10-22T03:29:33Z","snapshot_observed_at":"2026-08-07T00:29:14.945462Z","submitted_at":"2024-10-22T03:29:33Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs","version":1},"cited_work":{"arxiv_id":"2410.16663","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.16663","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fastattention: Extend flashattention2 to npus and low-resource gpus","venue":null,"work_id":"543e63e4-d658-441e-8f91-866b2aba0cc9","year":2024},"citing_paper":{"arxiv_id":"2604.08250","last_updated":"2026-04-09T13:41:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-09T13:41:05Z","title":"SMC-AI: Scaling Monte Carlo Simulation to Four Trillion Atoms with AI Accelerators","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T17:30:25.240578Z"},"links":{"cited_paper":"/paper/2410.16663","citing_paper":"/paper/2604.08250"},"observation_digest":"sha256:cb1e9bfd214eb3639153c54aad1e9cb15a7e25d53a5124c60df9d288e9dab2a6","observation_id":"e938f172-ebbe-4365-949d-36af5168f827","resolution":{"observed_at":"2026-05-11T06:41:28.896017Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16663","last_updated":"2024-10-22T03:29:33Z","snapshot_observed_at":"2026-08-07T00:29:14.945462Z","submitted_at":"2024-10-22T03:29:33Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16663","snapshot_observed_at":"2026-07-13T03:24:08.548348Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.09385","last_updated":"2026-07-10T13:09:47Z","snapshot_observed_at":"2026-08-07T07:36:21.911087Z","submitted_at":"2026-07-10T13:09:47Z","title":"STEEL: Sparsity-Aware Fused Attention for Energy-Efficient Long-Sequence Inference on AMD's XDNA NPU","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-13T03:24:08.548348Z"},"links":{"cited_paper":"/paper/2410.16663","citing_paper":"/paper/2607.09385"},"observation_digest":"sha256:30367da109da8803bb28586b7425c62f8dc0cb608f1d50d7f6bdc041eca39520","observation_id":"791d64a9-ac84-444e-b942-900736d56b01","resolution":{"observed_at":"2026-07-13T03:24:08.548348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16663","last_updated":"2024-10-22T03:29:33Z","snapshot_observed_at":"2026-08-07T00:29:14.945462Z","submitted_at":"2024-10-22T03:29:33Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16663","snapshot_observed_at":"2026-08-01T10:49:29.307677Z","title":"Fastattention: Extend flashattention2 to npus and low-resource gpus.arXiv preprint arXiv:2410.16663, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20120","last_updated":"2026-07-22T13:23:52Z","snapshot_observed_at":"2026-08-03T05:50:15.230236Z","submitted_at":"2026-07-22T13:23:52Z","title":"Ascend to Science: Exploration of AI Chips for Scientific Computing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T10:49:29.307677Z"},"links":{"cited_paper":"/paper/2410.16663","citing_paper":"/paper/2607.20120"},"observation_digest":"sha256:5a557ca9ece779689ca9471c86513be3a3cbf3c9bd1d697a3be30fdc40f78649","observation_id":"2c338cb3-aa6a-48a5-9bae-d7a4217ed880","resolution":{"observed_at":"2026-08-01T10:49:29.307677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2410.16663/citation-record","integrity":"/paper/2410.16663/integrity","json":"/paper/2410.16663/citation-record.json","paper":"/paper/2410.16663"},"outbound":[],"paper":{"arxiv_id":"2410.16663","last_updated":"2024-10-22T03:29:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T00:29:14.945462Z","submitted_at":"2024-10-22T03:29:33Z","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2410.16663."}