{"as_of":"2026-08-08T03:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6f90d7251cc1164d66b140ec444cd6ae339a1c6a4cfbe8771e232f81d7c43a32","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T14:56:44.277726Z","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":"2026-07-04T04:39:34.580127Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.03720","last_updated":"2020-10-05T17:35:44Z","snapshot_observed_at":"2026-07-06T09:10:48.901105Z","submitted_at":"2020-04-07T21:21:06Z","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.03720","snapshot_observed_at":"2026-08-07T14:56:44.277726Z","title":"Byte pair encoding is suboptimal for language model pretraining","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.16868","last_updated":"2025-05-22T16:24:37Z","snapshot_observed_at":"2026-08-07T14:51:41.178935Z","submitted_at":"2025-05-22T16:24:37Z","title":"Comparative analysis of subword tokenization approaches for Indian languages","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T14:56:44.277726Z"},"links":{"cited_paper":"/paper/2004.03720","citing_paper":"/paper/2505.16868"},"observation_digest":"sha256:48c97e5dba61ddfc42e1b00f27cf29d7def33c1516c52b3e31074f5b3f02a1e4","observation_id":"2354ad57-c2db-4543-93a7-5f74cd55ecca","resolution":{"observed_at":"2026-08-07T14:56:44.277726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.03720","last_updated":"2020-10-05T17:35:44Z","snapshot_observed_at":"2026-07-06T09:10:48.901105Z","submitted_at":"2020-04-07T21:21:06Z","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.03720","snapshot_observed_at":"2026-08-07T05:38:22.245808Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.11115","last_updated":"2025-06-09T04:59:13Z","snapshot_observed_at":"2026-08-07T05:31:50.556045Z","submitted_at":"2025-06-09T04:59:13Z","title":"Incorporating Domain Knowledge into Materials Tokenization","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T05:38:22.245808Z"},"links":{"cited_paper":"/paper/2004.03720","citing_paper":"/paper/2506.11115"},"observation_digest":"sha256:3636ab321bea99852b89278612d22d4df93dbb0e959f217ad7c0c0345ada9e76","observation_id":"59e3d09c-ba78-49d8-95dc-f471f4e5c919","resolution":{"observed_at":"2026-08-07T05:38:22.245808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.03720","last_updated":"2020-10-05T17:35:44Z","snapshot_observed_at":"2026-07-06T09:10:48.901105Z","submitted_at":"2020-04-07T21:21:06Z","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining","version":2},"cited_work":{"arxiv_id":"2004.03720","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2004.03720","snapshot_observed_at":"2026-07-04T04:39:34.580127Z","title":null,"venue":null,"work_id":"f90c6214-5075-4cc5-9d7c-2ace2ad3b09b","year":2020},"citing_paper":{"arxiv_id":"2606.20993","last_updated":"2026-06-18T23:50:54Z","snapshot_observed_at":"2026-08-05T09:19:18.829577Z","submitted_at":"2026-06-18T23:50:54Z","title":"Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-06-26T16:53:25.556222Z"},"links":{"cited_paper":"/paper/2004.03720","citing_paper":"/paper/2606.20993"},"observation_digest":"sha256:7b30c09ad0aca7545240502c469105e0740cec942ba474290e7a2b8406d446a8","observation_id":"fdc02c0f-a02b-40c0-ba19-93d4aec67cc8","resolution":{"observed_at":"2026-07-04T04:39:34.581473Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2004.03720/citation-record","integrity":"/paper/2004.03720/integrity","json":"/paper/2004.03720/citation-record.json","paper":"/paper/2004.03720"},"outbound":[],"paper":{"arxiv_id":"2004.03720","last_updated":"2020-10-05T17:35:44Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T09:10:48.901105Z","submitted_at":"2020-04-07T21:21:06Z","title":"Byte Pair Encoding is Suboptimal for Language Model Pretraining"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2004.03720."}