{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3BGLX74HTWFKQN3KZHC5BLBW3Y","short_pith_number":"pith:3BGLX74H","canonical_record":{"source":{"id":"2412.13716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-12-18T10:55:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2376114e1721488522ffa09f8ac0795d7adceda2bdca0ed7df53dba28fbb52f","abstract_canon_sha256":"a87dfd100d8cb3b03ca6a9f87d09f10facf4fa31efd33fe1e3a0804d69ede48a"},"schema_version":"1.0"},"canonical_sha256":"d84cbbff879d8aa8376ac9c5d0ac36de1de7b93a3abc84396f9ca89e480b4210","source":{"kind":"arxiv","id":"2412.13716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13716","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13716v1","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13716","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"3BGLX74HTWFK","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"3BGLX74HTWFKQN3K","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"3BGLX74H","created_at":"2026-07-05T09:51:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3BGLX74HTWFKQN3KZHC5BLBW3Y","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-12-18T10:55:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b2376114e1721488522ffa09f8ac0795d7adceda2bdca0ed7df53dba28fbb52f","abstract_canon_sha256":"a87dfd100d8cb3b03ca6a9f87d09f10facf4fa31efd33fe1e3a0804d69ede48a"},"schema_version":"1.0"},"canonical_sha256":"d84cbbff879d8aa8376ac9c5d0ac36de1de7b93a3abc84396f9ca89e480b4210","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:07.004665Z","signature_b64":"L6GNn+Zv565GfNffZBqvIznKDwXoKOrw8Ey7hHzRvhRgMM4A576TrS5iRNKmPn4z0iRYPMD7qBDraT9+ft5jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d84cbbff879d8aa8376ac9c5d0ac36de1de7b93a3abc84396f9ca89e480b4210","last_reissued_at":"2026-07-05T09:51:07.004199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:07.004199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13716","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lleYxZCyEI+S5Sw4KZ9IVTiDYhjAkCH4tUOwJFPDJ51nFiIOPFZTqK08P1U40v/GveiCpaV+n2kwswKsUa+HCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:55:24.485655Z"},"content_sha256":"a7f696652a71c117b8d91050e1884768fb397c7a299f8841a708967ee3747998","schema_version":"1.0","event_id":"sha256:a7f696652a71c117b8d91050e1884768fb397c7a299f8841a708967ee3747998"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3BGLX74HTWFKQN3KZHC5BLBW3Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Chaoqi Liang, Lifeng Qiao, Nanqing Dong, Peng Ye, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","submitted_at":"2024-12-18T10:55:43Z","abstract_excerpt":"Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences due to their unique characteristics. In addition, the optimal approach to tokenize DNA remains largely under-explored, and may not be intuitively understood by humans even if discovered. To address these challenges, we introduce MxDNA, a novel framework where the model autonomously learns an effective DNA tokenization strategy through gradient decent. MxDNA "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13716","kind":"arxiv","version":1},"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/2412.13716/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":"2026-07-05T09:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0yq/WX1+JjhXYVzZBOdDr0UBbn0LNrp07L/pA+IGdrp2DubIjZvtLdAtP5H0hmCWaeJKw+8SOWwBReF9wroBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:55:24.486179Z"},"content_sha256":"c8401daa430fcc78910abfca48fa55df9a2d3eda5d9514299bd5a38135656ffc","schema_version":"1.0","event_id":"sha256:c8401daa430fcc78910abfca48fa55df9a2d3eda5d9514299bd5a38135656ffc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/bundle.json","state_url":"https://pith.science/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/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":"2026-08-08T14:55:24Z","links":{"resolver":"https://pith.science/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y","bundle":"https://pith.science/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/bundle.json","state":"https://pith.science/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BGLX74HTWFKQN3KZHC5BLBW3Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3BGLX74HTWFKQN3KZHC5BLBW3Y","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":"a87dfd100d8cb3b03ca6a9f87d09f10facf4fa31efd33fe1e3a0804d69ede48a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-12-18T10:55:43Z","title_canon_sha256":"b2376114e1721488522ffa09f8ac0795d7adceda2bdca0ed7df53dba28fbb52f"},"schema_version":"1.0","source":{"id":"2412.13716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13716","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13716v1","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13716","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"3BGLX74HTWFK","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"3BGLX74HTWFKQN3K","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"3BGLX74H","created_at":"2026-07-05T09:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:c8401daa430fcc78910abfca48fa55df9a2d3eda5d9514299bd5a38135656ffc","target":"graph","created_at":"2026-07-05T09:51:07Z","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/2412.13716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences due to their unique characteristics. In addition, the optimal approach to tokenize DNA remains largely under-explored, and may not be intuitively understood by humans even if discovered. To address these challenges, we introduce MxDNA, a novel framework where the model autonomously learns an effective DNA tokenization strategy through gradient decent. MxDNA ","authors_text":"Chaoqi Liang, Lifeng Qiao, Nanqing Dong, Peng Ye, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-12-18T10:55:43Z","title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13716","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:a7f696652a71c117b8d91050e1884768fb397c7a299f8841a708967ee3747998","target":"record","created_at":"2026-07-05T09:51:07Z","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":"a87dfd100d8cb3b03ca6a9f87d09f10facf4fa31efd33fe1e3a0804d69ede48a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2024-12-18T10:55:43Z","title_canon_sha256":"b2376114e1721488522ffa09f8ac0795d7adceda2bdca0ed7df53dba28fbb52f"},"schema_version":"1.0","source":{"id":"2412.13716","kind":"arxiv","version":1}},"canonical_sha256":"d84cbbff879d8aa8376ac9c5d0ac36de1de7b93a3abc84396f9ca89e480b4210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d84cbbff879d8aa8376ac9c5d0ac36de1de7b93a3abc84396f9ca89e480b4210","first_computed_at":"2026-07-05T09:51:07.004199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:07.004199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L6GNn+Zv565GfNffZBqvIznKDwXoKOrw8Ey7hHzRvhRgMM4A576TrS5iRNKmPn4z0iRYPMD7qBDraT9+ft5jAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:07.004665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7f696652a71c117b8d91050e1884768fb397c7a299f8841a708967ee3747998","sha256:c8401daa430fcc78910abfca48fa55df9a2d3eda5d9514299bd5a38135656ffc"],"state_sha256":"d900a73e23638151c49d95677778af12037392c2fe2cc179df078ff527040e83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aaYDnSIqVVqtwBZElX/4t5XAkNfF8PNI6EOY9yygP8br/flmQrrf2PzCywjmpFMK6EoDGYW4irDe+qpdZatMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:55:24.491540Z","bundle_sha256":"19571d74a5d8da5f07f4a46d93f27b8a6deba8dc54442f27d38f42b86d9c4ea1"}}