{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VJKLNRINSFNQCSDWPPM627K7UQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db5ff4dc1f7ead0b4c38c4e440c609e92d75079b805feb193c0069b7a7db2e00","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-05-13T19:27:58Z","title_canon_sha256":"b4e29a5bb0af3c239ac2a2249f5b8cae3293be773a3673517c81f0cbce51e07c"},"schema_version":"1.0","source":{"id":"2505.08918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08918","created_at":"2026-07-05T11:02:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08918v1","created_at":"2026-07-05T11:02:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08918","created_at":"2026-07-05T11:02:47Z"},{"alias_kind":"pith_short_12","alias_value":"VJKLNRINSFNQ","created_at":"2026-07-05T11:02:47Z"},{"alias_kind":"pith_short_16","alias_value":"VJKLNRINSFNQCSDW","created_at":"2026-07-05T11:02:47Z"},{"alias_kind":"pith_short_8","alias_value":"VJKLNRIN","created_at":"2026-07-05T11:02:47Z"}],"graph_snapshots":[{"event_id":"sha256:14add85ed435fff110cbebd51f8f8381718cb4d1fae62eb600ff58ea01201bc4","target":"graph","created_at":"2026-07-05T11:02:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.08918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of telomere-to-telomere (T2T) genome assemblies has opened new avenues for comparative genomics, yet effective tokenization strategies for genomic sequences remain underexplored. In this pilot study, we apply Byte Pair Encoding (BPE) to nine T2T primate genomes including three human assemblies by training independent BPE tokenizers with a fixed vocabulary of 512,000 tokens using our custom tool, dnaBPE. Our analysis reveals that only 11,569 tokens are shared across all assemblies, while nearly 991,854 tokens are unique to a single genome, indicating a rapid decline in shared voca","authors_text":"Aleksey Komissarov, Iaroslav Chelombitko, Marina Popova","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-05-13T19:27:58Z","title":"When repeats drive the vocabulary: a Byte-Pair Encoding analysis of T2T primate genomes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08918","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9c43e2b6a3c154fceae4e324a26757ac205d0311361657269faf37537f0239d7","target":"record","created_at":"2026-07-05T11:02:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db5ff4dc1f7ead0b4c38c4e440c609e92d75079b805feb193c0069b7a7db2e00","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-05-13T19:27:58Z","title_canon_sha256":"b4e29a5bb0af3c239ac2a2249f5b8cae3293be773a3673517c81f0cbce51e07c"},"schema_version":"1.0","source":{"id":"2505.08918","kind":"arxiv","version":1}},"canonical_sha256":"aa54b6c50d915b0148767bd9ed7d5fa402975834cd9d148a2f4e44f8a106803d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa54b6c50d915b0148767bd9ed7d5fa402975834cd9d148a2f4e44f8a106803d","first_computed_at":"2026-07-05T11:02:47.189844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:47.189844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Fl2HNvj3s4g5eI8EEmax9BCQwJ5RtoinQT762J7GaJPx1VKf0uZEtsWvoWR1xQzBNhuaX+Fx3Z6NOIj+kYzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:47.190352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c43e2b6a3c154fceae4e324a26757ac205d0311361657269faf37537f0239d7","sha256:14add85ed435fff110cbebd51f8f8381718cb4d1fae62eb600ff58ea01201bc4"],"state_sha256":"650ff1c56bbd7464ba202c83e7d38048eeea59e6066c655e3a55e4592976591c"}