{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ACVXAKX54VRW2XEF256WROTZSJ","short_pith_number":"pith:ACVXAKX5","canonical_record":{"source":{"id":"2405.10812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-13T20:15:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1faa40962aade450c668351b572c569dd02ddb74384b91fd817e3930b9cb1b41","abstract_canon_sha256":"0e3f99548e353202a0cacc408625ac800bbaeb46286316231b395bcd35593a26"},"schema_version":"1.0"},"canonical_sha256":"00ab702afde5636d5c85d77d68ba7992517d6a8fc34d063d09945aad634c3f1c","source":{"kind":"arxiv","id":"2405.10812","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10812","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10812v2","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10812","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"ACVXAKX54VRW","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"ACVXAKX54VRW2XEF","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"ACVXAKX5","created_at":"2026-07-05T08:26:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ACVXAKX54VRW2XEF256WROTZSJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.10812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-13T20:15:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1faa40962aade450c668351b572c569dd02ddb74384b91fd817e3930b9cb1b41","abstract_canon_sha256":"0e3f99548e353202a0cacc408625ac800bbaeb46286316231b395bcd35593a26"},"schema_version":"1.0"},"canonical_sha256":"00ab702afde5636d5c85d77d68ba7992517d6a8fc34d063d09945aad634c3f1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:25.172141Z","signature_b64":"7chDmgCoLyfaM3GoeZMB3bVoioi2/jP5TMXAib5kyG8wGy7PPh8DxD2KsFvI9Y4a8dzf+j2f9U/zPouJRqVRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ab702afde5636d5c85d77d68ba7992517d6a8fc34d063d09945aad634c3f1c","last_reissued_at":"2026-07-05T08:26:25.171665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:25.171665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.10812","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kqf95Z1BsQ4D9xChQGQV0RchwolY7U7jtXeFR+A+SP22j8ivXkCq05ZFowjjZxzMnhHRpkkUY5lnkg8cXXNOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:33:02.276195Z"},"content_sha256":"bf4f15980a88b4b42e48a692e6a3ba73b4a9e7e968aeb8060496998e52bf3dd4","schema_version":"1.0","event_id":"sha256:bf4f15980a88b4b42e48a692e6a3ba73b4a9e7e968aeb8060496998e52bf3dd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ACVXAKX54VRW2XEF256WROTZSJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.GN","authors_text":"Cheng Tan, Di Wu, Jiangbin Zheng, Siyuan Li, Stan Z. Li, Yufei Huang, Zedong Wang, Zicheng Liu","submitted_at":"2024-05-13T20:15:03Z","abstract_excerpt":"Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners in biology. However, the hand-crafted tokenization policies used in these models may not encode the most discriminative patterns from the limited vocabulary of genomic data. In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning. By leveraging vector-quantized code"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10812","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.10812/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ybPX+YHbG7dRFgEzxtw5sGq9Ngo+VCL0ak4Kp4qblHHvxYeuV+IbpvnRoHG+N4N0kPr6PsRegjcSKmzx3CTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:33:02.277066Z"},"content_sha256":"7daba5da9ca97161189ba276a44896c84e5cfc5f047d3d4cf7896c4003d6c78e","schema_version":"1.0","event_id":"sha256:7daba5da9ca97161189ba276a44896c84e5cfc5f047d3d4cf7896c4003d6c78e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACVXAKX54VRW2XEF256WROTZSJ/bundle.json","state_url":"https://pith.science/pith/ACVXAKX54VRW2XEF256WROTZSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACVXAKX54VRW2XEF256WROTZSJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T15:33:02Z","links":{"resolver":"https://pith.science/pith/ACVXAKX54VRW2XEF256WROTZSJ","bundle":"https://pith.science/pith/ACVXAKX54VRW2XEF256WROTZSJ/bundle.json","state":"https://pith.science/pith/ACVXAKX54VRW2XEF256WROTZSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACVXAKX54VRW2XEF256WROTZSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ACVXAKX54VRW2XEF256WROTZSJ","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":"0e3f99548e353202a0cacc408625ac800bbaeb46286316231b395bcd35593a26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-13T20:15:03Z","title_canon_sha256":"1faa40962aade450c668351b572c569dd02ddb74384b91fd817e3930b9cb1b41"},"schema_version":"1.0","source":{"id":"2405.10812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10812","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10812v2","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10812","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"ACVXAKX54VRW","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_16","alias_value":"ACVXAKX54VRW2XEF","created_at":"2026-07-05T08:26:25Z"},{"alias_kind":"pith_short_8","alias_value":"ACVXAKX5","created_at":"2026-07-05T08:26:25Z"}],"graph_snapshots":[{"event_id":"sha256:7daba5da9ca97161189ba276a44896c84e5cfc5f047d3d4cf7896c4003d6c78e","target":"graph","created_at":"2026-07-05T08:26:25Z","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/2405.10812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners in biology. However, the hand-crafted tokenization policies used in these models may not encode the most discriminative patterns from the limited vocabulary of genomic data. In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning. By leveraging vector-quantized code","authors_text":"Cheng Tan, Di Wu, Jiangbin Zheng, Siyuan Li, Stan Z. Li, Yufei Huang, Zedong Wang, Zicheng Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-13T20:15:03Z","title":"VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10812","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:bf4f15980a88b4b42e48a692e6a3ba73b4a9e7e968aeb8060496998e52bf3dd4","target":"record","created_at":"2026-07-05T08:26:25Z","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":"0e3f99548e353202a0cacc408625ac800bbaeb46286316231b395bcd35593a26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-05-13T20:15:03Z","title_canon_sha256":"1faa40962aade450c668351b572c569dd02ddb74384b91fd817e3930b9cb1b41"},"schema_version":"1.0","source":{"id":"2405.10812","kind":"arxiv","version":2}},"canonical_sha256":"00ab702afde5636d5c85d77d68ba7992517d6a8fc34d063d09945aad634c3f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00ab702afde5636d5c85d77d68ba7992517d6a8fc34d063d09945aad634c3f1c","first_computed_at":"2026-07-05T08:26:25.171665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:25.171665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7chDmgCoLyfaM3GoeZMB3bVoioi2/jP5TMXAib5kyG8wGy7PPh8DxD2KsFvI9Y4a8dzf+j2f9U/zPouJRqVRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:25.172141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4f15980a88b4b42e48a692e6a3ba73b4a9e7e968aeb8060496998e52bf3dd4","sha256:7daba5da9ca97161189ba276a44896c84e5cfc5f047d3d4cf7896c4003d6c78e"],"state_sha256":"69542f8a48be87ce5174171e6b0bc48f9b027a171fb0e780e4469f19e966a5d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoGP9X5S8uECwa7ypjM67Eq80F9lDaqYWEY2ONK8kpK4Q1GdQf1LJoqcvjbgsIjI0r0zLuFJw/h3RxAJvVuXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T15:33:02.282780Z","bundle_sha256":"960b8840e66eb9d1b1a7ca960e5b0dd82e0aa90d227753d01243788bbf603eb7"}}