{"as_of":"2026-08-08T21:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d35f50e5f8aa8effe7af5cfe9f17e08665bdd1803af4155d9720929786c3120e","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T11:06:27.856130Z","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":"2026-05-16T08:07:34.333897Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.16607","last_updated":"2024-11-30T19:31:38Z","snapshot_observed_at":"2026-08-06T17:20:45.836739Z","submitted_at":"2024-07-23T16:13:22Z","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.16607","snapshot_observed_at":"2026-08-07T11:06:27.856130Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03523","last_updated":"2025-06-04T03:15:57Z","snapshot_observed_at":"2026-08-08T02:49:07.968119Z","submitted_at":"2025-06-04T03:15:57Z","title":"TokAlign: Efficient Vocabulary Adaptation via Token Alignment","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T11:06:27.856130Z"},"links":{"cited_paper":"/paper/2407.16607","citing_paper":"/paper/2506.03523"},"observation_digest":"sha256:ff3f7858e92e62f3f3acd6bccba74a56c8e2f17c2e6ce134acc909f71463cd51","observation_id":"9df92565-2a41-47f7-bcb1-195a6c33393d","resolution":{"observed_at":"2026-08-07T11:06:27.856130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.16607","last_updated":"2024-11-30T19:31:38Z","snapshot_observed_at":"2026-08-06T17:20:45.836739Z","submitted_at":"2024-07-23T16:13:22Z","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.16607","snapshot_observed_at":"2026-08-04T17:09:22.668034Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.11141","last_updated":"2025-09-14T07:21:44Z","snapshot_observed_at":"2026-08-08T03:46:41.577374Z","submitted_at":"2025-09-14T07:21:44Z","title":"When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T17:09:22.668034Z"},"links":{"cited_paper":"/paper/2407.16607","citing_paper":"/paper/2509.11141"},"observation_digest":"sha256:323b3d043a8c7f4d4441910aad4953e50296ef019ae81bc48ff160c54b4bcb80","observation_id":"8eb38931-7a71-4cb8-bc87-e83f0f58b84f","resolution":{"observed_at":"2026-08-04T17:09:22.668034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.16607","last_updated":"2024-11-30T19:31:38Z","snapshot_observed_at":"2026-08-06T17:20:45.836739Z","submitted_at":"2024-07-23T16:13:22Z","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","version":4},"cited_work":{"arxiv_id":"2407.16607","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.16607","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hayase, J., Liu, A., Choi, Y ., Oh, S., and Smith, N","venue":null,"work_id":"84aa7d55-c8e9-41f1-ad6d-4540f181da50","year":2024},"citing_paper":{"arxiv_id":"2602.04289","last_updated":"2026-05-14T17:33:56Z","snapshot_observed_at":"2026-07-31T10:47:17.158641Z","submitted_at":"2026-02-04T07:36:46Z","title":"Proxy Compression for Language Modeling","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-16T08:03:01.274736Z"},"links":{"cited_paper":"/paper/2407.16607","citing_paper":"/paper/2602.04289"},"observation_digest":"sha256:ac242b76bf9727ba06c70747c87af2e22199e2d9ca2894d5b6d782a304cb6717","observation_id":"59aeb56a-efc9-4be8-9748-245687544735","resolution":{"observed_at":"2026-05-16T08:07:34.335710Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.16607","last_updated":"2024-11-30T19:31:38Z","snapshot_observed_at":"2026-08-06T17:20:45.836739Z","submitted_at":"2024-07-23T16:13:22Z","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","version":4},"cited_work":{"arxiv_id":"2407.16607","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.16607","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hayase, J., Liu, A., Choi, Y ., Oh, S., and Smith, N","venue":null,"work_id":"84aa7d55-c8e9-41f1-ad6d-4540f181da50","year":2024},"citing_paper":{"arxiv_id":"2605.13429","last_updated":"2026-05-13T12:23:24Z","snapshot_observed_at":"2026-08-04T16:47:45.553680Z","submitted_at":"2026-05-13T12:23:24Z","title":"TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-14T19:35:10.026293Z"},"links":{"cited_paper":"/paper/2407.16607","citing_paper":"/paper/2605.13429"},"observation_digest":"sha256:23a05cf0b28e67c26d5f7d734a227ef29ba9fec39375134ef6be4fc6b3e02104","observation_id":"ab158432-9aa0-4370-9329-649ec41d4444","resolution":{"observed_at":"2026-05-14T19:37:52.289945Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.16607/citation-record","integrity":"/paper/2407.16607/integrity","json":"/paper/2407.16607/citation-record.json","paper":"/paper/2407.16607"},"outbound":[],"paper":{"arxiv_id":"2407.16607","last_updated":"2024-11-30T19:31:38Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T17:20:45.836739Z","submitted_at":"2024-07-23T16:13:22Z","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2407.16607."}