{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RRBTEL5UPJHM7VJIPWBSJWU4FF","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":"029df7d02de00b4102279d9820396e7bd693e8aa7af132ea291018b72e84bc00","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-06-26T18:43:46Z","title_canon_sha256":"ccc526cd6f38783172ac22776afa9e84c78a721f57ea0aefb643017f0dcb0283"},"schema_version":"1.0","source":{"id":"2306.15006","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15006","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15006v2","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15006","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"RRBTEL5UPJHM","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"RRBTEL5UPJHM7VJI","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"RRBTEL5U","created_at":"2026-07-05T07:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:b4f2b86c88ecbb7a8d7a6aa33c60f8a1d6163d7749a84eaf9bd4ec6de62ddf74","target":"graph","created_at":"2026-07-05T07:57:41Z","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/2306.15006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decoding the linguistic intricacies of the genome is a crucial problem in biology, and pre-trained foundational models such as DNABERT and Nucleotide Transformer have made significant strides in this area. Existing works have largely hinged on k-mer, fixed-length permutations of A, T, C, and G, as the token of the genome language due to its simplicity. However, we argue that the computation and sample inefficiencies introduced by k-mer tokenization are primary obstacles in developing large genome foundational models. We provide conceptual and empirical insights into genome tokenization, buildi","authors_text":"Han Liu, Pratik Dutta, Ramana Davuluri, Weijian Li, Yanrong Ji, Zhihan Zhou","cross_cats":["cs.AI","cs.CE","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-06-26T18:43:46Z","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15006","kind":"arxiv","version":2},"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":"sha256:2c2c46cf7ca05c54701791e387a1d38a215653ffbd61189e5a51989fd8595ef4","target":"record","created_at":"2026-07-05T07:57:41Z","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":"029df7d02de00b4102279d9820396e7bd693e8aa7af132ea291018b72e84bc00","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2023-06-26T18:43:46Z","title_canon_sha256":"ccc526cd6f38783172ac22776afa9e84c78a721f57ea0aefb643017f0dcb0283"},"schema_version":"1.0","source":{"id":"2306.15006","kind":"arxiv","version":2}},"canonical_sha256":"8c43322fb47a4ecfd5287d8324da9c296524658084b42dae213e110b4ae42753","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c43322fb47a4ecfd5287d8324da9c296524658084b42dae213e110b4ae42753","first_computed_at":"2026-07-05T07:57:41.362489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:41.362489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t9letc6GX0mfhVyTsx+tyfBnsX7MLmeEA6+EqjKcQoWv4xETjiQ4/5Q2HZ6HdlS/wtX6KPRANnnVFYdwqTwOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:41.362993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15006","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c2c46cf7ca05c54701791e387a1d38a215653ffbd61189e5a51989fd8595ef4","sha256:b4f2b86c88ecbb7a8d7a6aa33c60f8a1d6163d7749a84eaf9bd4ec6de62ddf74"],"state_sha256":"fbe696f2605bbbd3ddc1a1e77b0b4e49e973882491c31024c4e85163611eed63"}