{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BBPGYVPPYAHN3PMPDGKV2G7H4P","short_pith_number":"pith:BBPGYVPP","canonical_record":{"source":{"id":"2502.18405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T17:56:25Z","cross_cats_sorted":[],"title_canon_sha256":"bfb75c1f79db80da5015d61762d81549c38d0c4586f2f360190a4ebcfdecae23","abstract_canon_sha256":"d11ba453d9b9a6dfe34a1cf13a56375f9fc6dd98e429380555371ac2f32c9ad9"},"schema_version":"1.0"},"canonical_sha256":"085e6c55efc00eddbd8f19955d1be7e3e56b11e2eda74cb009498af12b09eecc","source":{"kind":"arxiv","id":"2502.18405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18405","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18405v1","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18405","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"BBPGYVPPYAHN","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"BBPGYVPPYAHN3PMP","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"BBPGYVPP","created_at":"2026-07-05T10:19:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BBPGYVPPYAHN3PMPDGKV2G7H4P","target":"record","payload":{"canonical_record":{"source":{"id":"2502.18405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T17:56:25Z","cross_cats_sorted":[],"title_canon_sha256":"bfb75c1f79db80da5015d61762d81549c38d0c4586f2f360190a4ebcfdecae23","abstract_canon_sha256":"d11ba453d9b9a6dfe34a1cf13a56375f9fc6dd98e429380555371ac2f32c9ad9"},"schema_version":"1.0"},"canonical_sha256":"085e6c55efc00eddbd8f19955d1be7e3e56b11e2eda74cb009498af12b09eecc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:53.412660Z","signature_b64":"qc9dPHMqsSmHHGHhb+f9yIaLUJ3Ph6z4ZeqMrw7Dik6mXgGzDdXHiWVGiHC0B7tG7q9wC9dc1Vs5OTJL460vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085e6c55efc00eddbd8f19955d1be7e3e56b11e2eda74cb009498af12b09eecc","last_reissued_at":"2026-07-05T10:19:53.412244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:53.412244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.18405","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":"2026-07-05T10:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0xA3pF4ETD5Dxhn0KfeEXTapSQBy7zBAVMyh/p1ucgLTvXkEWxR/I2sKdsKVE0tEnHQJG2Uj3edeuOn0UBLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:23:24.339720Z"},"content_sha256":"41570788b0043ab9d0e4296ad068c25148d30f26f5b4e0920b7a37fd77ba21fb","schema_version":"1.0","event_id":"sha256:41570788b0043ab9d0e4296ad068c25148d30f26f5b4e0920b7a37fd77ba21fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BBPGYVPPYAHN3PMPDGKV2G7H4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing DNA Foundation Models to Address Masking Inefficiencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Angel X. Chang, Graham W. Taylor, Lila Kari, Monireh Safari, Pablo Millan Arias, Scott C. Lowe","submitted_at":"2025-02-25T17:56:25Z","abstract_excerpt":"Masked language modelling (MLM) as a pretraining objective has been widely adopted in genomic sequence modelling. While pretrained models can successfully serve as encoders for various downstream tasks, the distribution shift between pretraining and inference detrimentally impacts performance, as the pretraining task is to map [MASK] tokens to predictions, yet the [MASK] is absent during downstream applications. This means the encoder does not prioritize its encodings of non-[MASK] tokens, and expends parameters and compute on work only relevant to the MLM task, despite this being irrelevant a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18405","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/2502.18405/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":"2026-07-05T10:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nEvSbSj6/4pFZiU4fgy9dFu3lW0ybSe1NjW/ewFk0+ZGuCPwY2ug0+YWpFexWjALGWAo8jH3i2Hvrnn/wc9CAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:23:24.340243Z"},"content_sha256":"4966af37b40b2eb35119ea63123335cda2afc4bd416312ca963a7f06a8ad614b","schema_version":"1.0","event_id":"sha256:4966af37b40b2eb35119ea63123335cda2afc4bd416312ca963a7f06a8ad614b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/bundle.json","state_url":"https://pith.science/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/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":"2026-08-01T05:23:24Z","links":{"resolver":"https://pith.science/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P","bundle":"https://pith.science/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/bundle.json","state":"https://pith.science/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBPGYVPPYAHN3PMPDGKV2G7H4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BBPGYVPPYAHN3PMPDGKV2G7H4P","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":"d11ba453d9b9a6dfe34a1cf13a56375f9fc6dd98e429380555371ac2f32c9ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T17:56:25Z","title_canon_sha256":"bfb75c1f79db80da5015d61762d81549c38d0c4586f2f360190a4ebcfdecae23"},"schema_version":"1.0","source":{"id":"2502.18405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18405","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18405v1","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18405","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"BBPGYVPPYAHN","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"BBPGYVPPYAHN3PMP","created_at":"2026-07-05T10:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"BBPGYVPP","created_at":"2026-07-05T10:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:4966af37b40b2eb35119ea63123335cda2afc4bd416312ca963a7f06a8ad614b","target":"graph","created_at":"2026-07-05T10:19:53Z","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/2502.18405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked language modelling (MLM) as a pretraining objective has been widely adopted in genomic sequence modelling. While pretrained models can successfully serve as encoders for various downstream tasks, the distribution shift between pretraining and inference detrimentally impacts performance, as the pretraining task is to map [MASK] tokens to predictions, yet the [MASK] is absent during downstream applications. This means the encoder does not prioritize its encodings of non-[MASK] tokens, and expends parameters and compute on work only relevant to the MLM task, despite this being irrelevant a","authors_text":"Angel X. Chang, Graham W. Taylor, Lila Kari, Monireh Safari, Pablo Millan Arias, Scott C. Lowe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T17:56:25Z","title":"Enhancing DNA Foundation Models to Address Masking Inefficiencies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18405","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":"sha256:41570788b0043ab9d0e4296ad068c25148d30f26f5b4e0920b7a37fd77ba21fb","target":"record","created_at":"2026-07-05T10:19:53Z","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":"d11ba453d9b9a6dfe34a1cf13a56375f9fc6dd98e429380555371ac2f32c9ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-25T17:56:25Z","title_canon_sha256":"bfb75c1f79db80da5015d61762d81549c38d0c4586f2f360190a4ebcfdecae23"},"schema_version":"1.0","source":{"id":"2502.18405","kind":"arxiv","version":1}},"canonical_sha256":"085e6c55efc00eddbd8f19955d1be7e3e56b11e2eda74cb009498af12b09eecc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"085e6c55efc00eddbd8f19955d1be7e3e56b11e2eda74cb009498af12b09eecc","first_computed_at":"2026-07-05T10:19:53.412244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:53.412244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qc9dPHMqsSmHHGHhb+f9yIaLUJ3Ph6z4ZeqMrw7Dik6mXgGzDdXHiWVGiHC0B7tG7q9wC9dc1Vs5OTJL460vCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:53.412660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41570788b0043ab9d0e4296ad068c25148d30f26f5b4e0920b7a37fd77ba21fb","sha256:4966af37b40b2eb35119ea63123335cda2afc4bd416312ca963a7f06a8ad614b"],"state_sha256":"adacc40ff7f751d77f21335424fd5825659d86b9b88b826a8f408b4a1f826c5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kwhCoGuUEEdMJ7BsvS/sEo7AeY1f+nw7ha1SHqhXJg4MkRRzBzlB4HLrr2q6+CrIMGV0AMl8ChoaS66KHo6hCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:23:24.345020Z","bundle_sha256":"fad41f0a48fb5c670ae22de0f6172b5f1ef828a7d579b31a23965ce35f433654"}}