{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SZJ3S63RHN4NHTCV226Q3FDFFO","short_pith_number":"pith:SZJ3S63R","canonical_record":{"source":{"id":"2310.07644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cf8d7471ad1fa4b775022de9b1dfc9167bbf9eb746e79e60451beef4a28fada1","abstract_canon_sha256":"d3bf3b013bd2396a8f310af5c5d43d2c97bc251cf460cf202951515e5cb306cf"},"schema_version":"1.0"},"canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","source":{"kind":"arxiv","id":"2310.07644","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07644","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07644v3","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07644","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"SZJ3S63RHN4N","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"SZJ3S63RHN4NHTCV","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"SZJ3S63R","created_at":"2026-07-05T09:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SZJ3S63RHN4NHTCV226Q3FDFFO","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"cf8d7471ad1fa4b775022de9b1dfc9167bbf9eb746e79e60451beef4a28fada1","abstract_canon_sha256":"d3bf3b013bd2396a8f310af5c5d43d2c97bc251cf460cf202951515e5cb306cf"},"schema_version":"1.0"},"canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:29.813501Z","signature_b64":"kFM6Mn+Pq7CtRBsZhaM+9BkP+eu8/+xndxJc0sA9+KpbHioD2v7opR7DzxxnSvfvls9HWhZr1rztq3lS1iCiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","last_reissued_at":"2026-07-05T09:04:29.813014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:29.813014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07644","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+gwNzw7wWnsI5oLlz2/OmCv04tLLdSW4A0cqfEcgqyUq3F3XUrxuD2a/hLy2+kxDOuyW0Ibr3TyHO/OS1YYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:45:32.621206Z"},"content_sha256":"36f08b73f307faa7e9a3391dfe8a7c9efa87fb1f382e5f3c365ba81df65e5b91","schema_version":"1.0","event_id":"sha256:36f08b73f307faa7e9a3391dfe8a7c9efa87fb1f382e5f3c365ba81df65e5b91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SZJ3S63RHN4NHTCV226Q3FDFFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chaoqi Liang, Chunfeng Song, Hongliang Yan, Jianle Sun, Lifeng Qiao, Nanqing Dong, Peng Ye, Wangmeng Zuo, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","submitted_at":"2023-10-11T16:40:57Z","abstract_excerpt":"With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods based on DNA sequences have received increasing attention because of their potential to capture general information about genes. However, existing pre-training methods for DNA sequences largely rely on direct adoptions of BERT pre-training from NLP, lacking a comprehensive understanding and a specifically tailored approach. To address this research gap, we provide the first empirical study with three insightful observati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07644","kind":"arxiv","version":3},"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/2310.07644/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":"2026-07-05T09:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dU4JuOn/HrT+6IZOkpd7ozBfE1ZkooYJvxALY7zqYXkFLCxewhCi3823z7XR7w6Din9lx6DR+pW/MoHDfedUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:45:32.621717Z"},"content_sha256":"f3da282e4af61c3e13c8577af4785013e75c09481af324e7c31b242c91c8f33b","schema_version":"1.0","event_id":"sha256:f3da282e4af61c3e13c8577af4785013e75c09481af324e7c31b242c91c8f33b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/bundle.json","state_url":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/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":"2026-08-21T18:45:32Z","links":{"resolver":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO","bundle":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/bundle.json","state":"https://pith.science/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZJ3S63RHN4NHTCV226Q3FDFFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SZJ3S63RHN4NHTCV226Q3FDFFO","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":"d3bf3b013bd2396a8f310af5c5d43d2c97bc251cf460cf202951515e5cb306cf","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","title_canon_sha256":"cf8d7471ad1fa4b775022de9b1dfc9167bbf9eb746e79e60451beef4a28fada1"},"schema_version":"1.0","source":{"id":"2310.07644","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07644","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07644v3","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07644","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"SZJ3S63RHN4N","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"SZJ3S63RHN4NHTCV","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"SZJ3S63R","created_at":"2026-07-05T09:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:f3da282e4af61c3e13c8577af4785013e75c09481af324e7c31b242c91c8f33b","target":"graph","created_at":"2026-07-05T09:04:29Z","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/2310.07644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of large-scale pre-training in language tasks, there is an increasing trend of applying it to the domain of life sciences. In particular, pre-training methods based on DNA sequences have received increasing attention because of their potential to capture general information about genes. However, existing pre-training methods for DNA sequences largely rely on direct adoptions of BERT pre-training from NLP, lacking a comprehensive understanding and a specifically tailored approach. To address this research gap, we provide the first empirical study with three insightful observati","authors_text":"Chaoqi Liang, Chunfeng Song, Hongliang Yan, Jianle Sun, Lifeng Qiao, Nanqing Dong, Peng Ye, Wangmeng Zuo, Wanli Ouyang, Weiqiang Bai, Xinzhu Ma, Yuchen Ren","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07644","kind":"arxiv","version":3},"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":"sha256:36f08b73f307faa7e9a3391dfe8a7c9efa87fb1f382e5f3c365ba81df65e5b91","target":"record","created_at":"2026-07-05T09:04:29Z","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":"d3bf3b013bd2396a8f310af5c5d43d2c97bc251cf460cf202951515e5cb306cf","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-11T16:40:57Z","title_canon_sha256":"cf8d7471ad1fa4b775022de9b1dfc9167bbf9eb746e79e60451beef4a28fada1"},"schema_version":"1.0","source":{"id":"2310.07644","kind":"arxiv","version":3}},"canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9653b97b713b78d3cc55d6bd0d94652b96d0396e699f17c2c8c9752acb7bd3a5","first_computed_at":"2026-07-05T09:04:29.813014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:29.813014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kFM6Mn+Pq7CtRBsZhaM+9BkP+eu8/+xndxJc0sA9+KpbHioD2v7opR7DzxxnSvfvls9HWhZr1rztq3lS1iCiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:29.813501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07644","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36f08b73f307faa7e9a3391dfe8a7c9efa87fb1f382e5f3c365ba81df65e5b91","sha256:f3da282e4af61c3e13c8577af4785013e75c09481af324e7c31b242c91c8f33b"],"state_sha256":"72679c21ccbde21e467ad4d614485fe04a9f828279602417af730460115dc66d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rMGdqMNHRZVQbMB442dTfvCyFy1epV0n/FY0EtmoBjcJ3NmIhGbUSFIIwGKWG+zaIYrbZtWe+WQL1iPRtEGrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:45:32.627110Z","bundle_sha256":"bd494c9a1890e0f185048e5eaab6dac5af678da07f4ea72388f73401c0154737"}}