{"as_of":"2026-08-13T10:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:718c1bc7891fb6bed7d039f38cf47f0d3df5bc6b78c621226c18621ca3058712","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":"2026-08-12T11:50:51.875561Z","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":"2026-07-01T23:26:21.839382Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.16442","last_updated":"2024-11-09T12:09:55Z","snapshot_observed_at":"2026-08-13T05:15:48.310655Z","submitted_at":"2023-11-28T02:44:59Z","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16442","snapshot_observed_at":"2026-08-12T11:50:51.875561Z","title":"Fast and efficient 2-bit llm inference on gpu: 2/4/16-bit in a weight matrix with asynchronous dequantization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.17847","last_updated":"2024-11-26T20:00:54Z","snapshot_observed_at":"2026-08-13T00:49:51.922606Z","submitted_at":"2024-11-26T20:00:54Z","title":"SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T11:50:51.875561Z"},"links":{"cited_paper":"/paper/2311.16442","citing_paper":"/paper/2411.17847"},"observation_digest":"sha256:8b54c4c3106974397e8039c2d8917a2a1ae21256a1b3f9f88915568d21869911","observation_id":"9a827f97-feef-4a80-b4e1-441fecc67ffd","resolution":{"observed_at":"2026-08-12T11:50:51.875561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16442","last_updated":"2024-11-09T12:09:55Z","snapshot_observed_at":"2026-08-13T05:15:48.310655Z","submitted_at":"2023-11-28T02:44:59Z","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16442","snapshot_observed_at":"2026-08-06T11:15:33.965632Z","title":"Fast and efficient 2-bit llm inference on gpu: 2/4/16-bit in a weight matrix with asynchronous dequantization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.23035","last_updated":"2026-06-02T03:48:06Z","snapshot_observed_at":"2026-08-12T07:42:40.315920Z","submitted_at":"2025-07-30T19:01:25Z","title":"OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T11:15:33.965632Z"},"links":{"cited_paper":"/paper/2311.16442","citing_paper":"/paper/2507.23035"},"observation_digest":"sha256:0ffb0f1065e605ce2c9b63a4e265d5268e7f8dd39462dd3b1b18e25551ed29b6","observation_id":"99348218-225c-4b9b-af02-865527d3b435","resolution":{"observed_at":"2026-08-06T11:15:33.965632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16442","last_updated":"2024-11-09T12:09:55Z","snapshot_observed_at":"2026-08-13T05:15:48.310655Z","submitted_at":"2023-11-28T02:44:59Z","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization","version":4},"cited_work":{"arxiv_id":"2311.16442","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.16442","snapshot_observed_at":"2026-07-01T23:26:21.839382Z","title":"Fast and efficient 2-bit LLM inference on GPU: 2/4/16-bit in a weight matrix with asynchronous dequantization, 2024","venue":null,"work_id":"7807157d-987d-405e-b4db-ff40a584eb91","year":2024},"citing_paper":{"arxiv_id":"2606.02011","last_updated":"2026-06-01T10:04:09Z","snapshot_observed_at":"2026-08-12T12:26:00.648436Z","submitted_at":"2026-06-01T10:04:09Z","title":"Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T14:26:41.243535Z"},"links":{"cited_paper":"/paper/2311.16442","citing_paper":"/paper/2606.02011"},"observation_digest":"sha256:2bd8dc7ea93a0ee3544f2b5533fd4bd44c43f4dd9aab98f2b5a5c80f8098b575","observation_id":"459ba414-7f05-4756-b880-862a980215ec","resolution":{"observed_at":"2026-07-01T23:26:21.841482Z","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/2311.16442/citation-record","integrity":"/paper/2311.16442/integrity","json":"/paper/2311.16442/citation-record.json","paper":"/paper/2311.16442"},"outbound":[],"paper":{"arxiv_id":"2311.16442","last_updated":"2024-11-09T12:09:55Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T05:15:48.310655Z","submitted_at":"2023-11-28T02:44:59Z","title":"Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization"},"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 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2311.16442."}