{"as_of":"2026-08-10T00:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7ed9d49cd99907ea596009e9b49f5e707efbe2d0bd4f43c2826d9218d28a3dda","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":"2026-08-09T17:26:11.270404Z","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":"2026-05-11T08:30:57.959347Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.07262","last_updated":"2024-02-03T05:42:54Z","snapshot_observed_at":"2026-08-09T10:09:14.065277Z","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07262","snapshot_observed_at":"2026-08-09T17:26:11.270404Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00894","last_updated":"2025-02-02T20:06:39Z","snapshot_observed_at":"2026-08-09T17:18:47.016847Z","submitted_at":"2025-02-02T20:06:39Z","title":"MorphBPE: A Morpho-Aware Tokenizer Bridging Linguistic Complexity for Efficient LLM Training Across Morphologies","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T17:26:11.270404Z"},"links":{"cited_paper":"/paper/2307.07262","citing_paper":"/paper/2502.00894"},"observation_digest":"sha256:4954d9adb2f68ddc5437ffc80dde2a62071f370bdf57996387302546a2008b27","observation_id":"8e7dc2d9-6bcc-4ba3-8d82-d9ada657e92e","resolution":{"observed_at":"2026-08-09T17:26:11.270404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07262","last_updated":"2024-02-03T05:42:54Z","snapshot_observed_at":"2026-08-09T10:09:14.065277Z","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07262","snapshot_observed_at":"2026-08-06T19:10:44.583977Z","title":"Poster presentation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.06378","last_updated":"2025-07-08T20:32:26Z","snapshot_observed_at":"2026-08-08T14:58:03.919110Z","submitted_at":"2025-07-08T20:32:26Z","title":"Evaluating Morphological Alignment of Tokenizers in 70 Languages","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T19:10:44.583977Z"},"links":{"cited_paper":"/paper/2307.07262","citing_paper":"/paper/2507.06378"},"observation_digest":"sha256:2c31afba2d317df5e09414e6fe482f28aa55c24b0611559ad2a00da7aa5bad3f","observation_id":"17400160-9dc4-4c75-a44c-71fe2c118723","resolution":{"observed_at":"2026-08-06T19:10:44.583977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07262","last_updated":"2024-02-03T05:42:54Z","snapshot_observed_at":"2026-08-09T10:09:14.065277Z","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.07262","snapshot_observed_at":"2026-08-04T20:10:16.718613Z","title":"Computational Linguistics, 48(3):673–732","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08812","last_updated":"2025-09-10T17:45:10Z","snapshot_observed_at":"2026-08-09T10:09:22.503392Z","submitted_at":"2025-09-10T17:45:10Z","title":"MoVoC: Morphology-Aware Subword Construction for Geez Script Languages","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-04T20:10:16.718613Z"},"links":{"cited_paper":"/paper/2307.07262","citing_paper":"/paper/2509.08812"},"observation_digest":"sha256:aa5fd6afa0de703db8c82ab1fcf7120b1a7412f27761cdfef63547696be984d9","observation_id":"09f2b853-959a-4b4f-8ad2-d500321ef1f5","resolution":{"observed_at":"2026-08-04T20:10:16.718613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.07262","last_updated":"2024-02-03T05:42:54Z","snapshot_observed_at":"2026-08-09T10:09:14.065277Z","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models","version":2},"cited_work":{"arxiv_id":"2307.07262","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.07262","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MorphPiece: A linguistic tokenizer for large language models","venue":null,"work_id":"3bb39879-3c16-48c0-819f-9744563768e2","year":2024},"citing_paper":{"arxiv_id":"2604.10665","last_updated":"2026-04-12T14:40:30Z","snapshot_observed_at":"2026-07-06T22:59:13.936436Z","submitted_at":"2026-04-12T14:40:30Z","title":"HeceTokenizer: A Syllable-Based Tokenization Approach for Turkish Retrieval","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T16:35:48.466402Z"},"links":{"cited_paper":"/paper/2307.07262","citing_paper":"/paper/2604.10665"},"observation_digest":"sha256:4ba59e760b1aaeed838c255b2e683bd11eec6dab1c6af73bbe971d397da07d84","observation_id":"f7eb0595-a721-45ea-bcfd-0f28a61b9d7c","resolution":{"observed_at":"2026-05-11T08:30:57.961112Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2307.07262/citation-record","integrity":"/paper/2307.07262/integrity","json":"/paper/2307.07262/citation-record.json","paper":"/paper/2307.07262"},"outbound":[],"paper":{"arxiv_id":"2307.07262","last_updated":"2024-02-03T05:42:54Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T10:09:14.065277Z","submitted_at":"2023-07-14T10:35:04Z","title":"MorphPiece : A Linguistic Tokenizer for Large Language Models"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2307.07262."}