{"as_of":"2026-08-18T15:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6772cdfc0a823160fc5492020e44140b119ab4aa60e1902d589744c4f4061069","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":"2026-08-18T06:34:40.430872+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":"2026-08-14T04:46:37.190997Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T00:51:16.383367Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1804.01526","last_updated":"2018-12-02T15:11:18Z","snapshot_observed_at":"2026-08-14T19:29:26.763888Z","submitted_at":"2018-04-04T09:40:59Z","title":"Training DNNs with Hybrid Block Floating Point","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.01526","snapshot_observed_at":"2026-07-14T15:56:34.283388Z","title":"Training DNNs with Hybrid Block Floating Point,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.09775","last_updated":"2026-07-07T20:26:25Z","snapshot_observed_at":"2026-08-18T14:12:46.972982Z","submitted_at":"2026-07-07T20:26:25Z","title":"WINT: A Novel Weighted Integer Representation with Improved Error Characteristics","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-14T15:56:34.283388Z"},"links":{"cited_paper":"/paper/1804.01526","citing_paper":"/paper/2607.09775"},"observation_digest":"sha256:c92b9e3127280a3a5a268f48ca364e0724f0de074d793e7f7fa0f0dd2ebae27e","observation_id":"f0fb2e3f-6228-4ca0-be75-785f0edccea8","resolution":{"observed_at":"2026-07-14T15:56:34.283388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.01526","last_updated":"2018-12-02T15:11:18Z","snapshot_observed_at":"2026-08-14T19:29:26.763888Z","submitted_at":"2018-04-04T09:40:59Z","title":"Training DNNs with Hybrid Block Floating Point","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.01526","snapshot_observed_at":"2026-08-01T17:12:27.151541Z","title":"arXiv:1804.01526 [cs, stat] , author =","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17733","last_updated":"2026-07-20T09:23:10Z","snapshot_observed_at":"2026-08-14T14:35:49.965877Z","submitted_at":"2026-07-20T09:23:10Z","title":"MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-01T17:12:27.151541Z"},"links":{"cited_paper":"/paper/1804.01526","citing_paper":"/paper/2607.17733"},"observation_digest":"sha256:3d9a608f09824c619828cbd5efa006f483d447c858bbef864c970f26a607cfb0","observation_id":"b0389ef3-da40-46f6-b694-d9dd588926c7","resolution":{"observed_at":"2026-08-01T17:12:27.151541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.01526","last_updated":"2018-12-02T15:11:18Z","snapshot_observed_at":"2026-08-14T19:29:26.763888Z","submitted_at":"2018-04-04T09:40:59Z","title":"Training DNNs with Hybrid Block Floating Point","version":4},"cited_work":{"arxiv_id":"1804.01526","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.01526","snapshot_observed_at":"2026-08-12T00:51:16.383367Z","title":"Training DNNs with Hybrid Block Floating Point","venue":"cs.LG","work_id":"25f570c4-998f-43cd-a9d5-df1fb4a80820","year":2018},"citing_paper":{"arxiv_id":"2608.10010","last_updated":"2026-08-12T03:58:39Z","snapshot_observed_at":"2026-08-17T09:38:05.904832Z","submitted_at":"2026-08-08T01:55:46Z","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T00:51:15.522482Z"},"links":{"cited_paper":"/paper/1804.01526","citing_paper":"/paper/2608.10010"},"observation_digest":"sha256:af4152a9ae992f7ff46df6835aadc31cac1e8caf0cb3304b7d4a61590fed3bef","observation_id":"3f02524c-fdb1-466d-ad8a-c8f7b9f350ad","resolution":{"observed_at":"2026-08-12T00:51:16.389569Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.01526","last_updated":"2018-12-02T15:11:18Z","snapshot_observed_at":"2026-08-14T19:29:26.763888Z","submitted_at":"2018-04-04T09:40:59Z","title":"Training DNNs with Hybrid Block Floating Point","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.01526","snapshot_observed_at":"2026-08-14T04:46:37.190997Z","title":"Reena Elangovan, Charbel Sakr, Anand Raghunathan, and Brucek Khailany","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10010","last_updated":"2026-08-12T03:58:39Z","snapshot_observed_at":"2026-08-17T09:38:05.904832Z","submitted_at":"2026-08-08T01:55:46Z","title":"CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:46:37.190997Z"},"links":{"cited_paper":"/paper/1804.01526","citing_paper":"/paper/2608.10010"},"observation_digest":"sha256:0c50e169dc6fa56d159eef6768e9bf26e2684964e3620b7d085170e31c6e74a4","observation_id":"d9f5e11f-6cbc-4451-8e5d-f48617ef3d78","resolution":{"observed_at":"2026-08-14T04:46:37.190997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1804.01526/citation-record","integrity":"/paper/1804.01526/integrity","json":"/paper/1804.01526/citation-record.json","paper":"/paper/1804.01526"},"outbound":[],"paper":{"arxiv_id":"1804.01526","last_updated":"2018-12-02T15:11:18Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T19:29:26.763888Z","submitted_at":"2018-04-04T09:40:59Z","title":"Training DNNs with Hybrid Block Floating Point"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1804.01526."}