{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AL2EPAWLGQUJAP4YMUFYRPHQ7G","short_pith_number":"pith:AL2EPAWL","canonical_record":{"source":{"id":"2506.10271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-12T01:28:04Z","cross_cats_sorted":["cs.LG","q-bio.GN"],"title_canon_sha256":"a71a1a24f49af3446a6d19bf63fa9a17fd42ba35677e943765d58e6439cd02c1","abstract_canon_sha256":"92f17fc6296e1ee66d11407ec70363986ea4b4e20365e54b9213759afed00e69"},"schema_version":"1.0"},"canonical_sha256":"02f44782cb3428903f98650b88bcf0f98b23a1a533af980775702451527cf2ab","source":{"kind":"arxiv","id":"2506.10271","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10271","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10271v3","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10271","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"AL2EPAWLGQUJ","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"AL2EPAWLGQUJAP4Y","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"AL2EPAWL","created_at":"2026-07-05T11:59:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AL2EPAWLGQUJAP4YMUFYRPHQ7G","target":"record","payload":{"canonical_record":{"source":{"id":"2506.10271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-12T01:28:04Z","cross_cats_sorted":["cs.LG","q-bio.GN"],"title_canon_sha256":"a71a1a24f49af3446a6d19bf63fa9a17fd42ba35677e943765d58e6439cd02c1","abstract_canon_sha256":"92f17fc6296e1ee66d11407ec70363986ea4b4e20365e54b9213759afed00e69"},"schema_version":"1.0"},"canonical_sha256":"02f44782cb3428903f98650b88bcf0f98b23a1a533af980775702451527cf2ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:15.740500Z","signature_b64":"xC3bCF8DXFdAesl1KriUtAlWKENoesN8uP3CLY6fXYcah6ooHE27foIr2M35xgzhtTwCxAGUGf2tPZz7k7V+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02f44782cb3428903f98650b88bcf0f98b23a1a533af980775702451527cf2ab","last_reissued_at":"2026-07-05T11:59:15.740028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:15.740028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.10271","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":"2026-07-05T11:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5XEVB/HVBHp+Hz24GDi/+iEOdvMpO8EOPgk3zMgUKXr2kfS3kOK1ie/LJzQwVTzkkTlbOe8YU+DmBBg3AQvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:51:28.519658Z"},"content_sha256":"183f589dfd543840ac97615074e1373bd8e60f078ca1a54ff71a9afcf48e259d","schema_version":"1.0","event_id":"sha256:183f589dfd543840ac97615074e1373bd8e60f078ca1a54ff71a9afcf48e259d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AL2EPAWLGQUJAP4YMUFYRPHQ7G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.GN"],"primary_cat":"q-bio.QM","authors_text":"Shiyu Jiang, Xuyin Liu, Zitong Jerry Wang","submitted_at":"2025-06-12T01:28:04Z","abstract_excerpt":"Genomic language models (gLMs) hold promise for generating novel, functional DNA sequences for synthetic biology. However, realizing this potential requires models to go beyond evolutionary plausibility and understand how DNA sequence encodes gene expression and regulation. We introduce a benchmark called Nullsettes, which assesses how well models can predict in silico loss-of-function (LOF) mutations, in synthetic expression cassettes with little evolutionary precedent. Testing 12 state-of-the-art gLMs, we find that most fail to consistently detect these strong LOF mutations. All models show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10271","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/2506.10271/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":"2026-07-05T11:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ql9P2dqwtrIjRHocNGAXrAJI6J2erZ1lRsf4leczK60Hi+VPwjzasiGJ+ISrF7FAhACB7H6SHP2y/KbvQ6soDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:51:28.520148Z"},"content_sha256":"52255ae5be1ef7ef5dfcd3f52454da5720b871e27a84fbbd5e1a2d772371b2e1","schema_version":"1.0","event_id":"sha256:52255ae5be1ef7ef5dfcd3f52454da5720b871e27a84fbbd5e1a2d772371b2e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/bundle.json","state_url":"https://pith.science/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/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":"2026-08-06T22:51:28Z","links":{"resolver":"https://pith.science/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G","bundle":"https://pith.science/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/bundle.json","state":"https://pith.science/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AL2EPAWLGQUJAP4YMUFYRPHQ7G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AL2EPAWLGQUJAP4YMUFYRPHQ7G","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":"92f17fc6296e1ee66d11407ec70363986ea4b4e20365e54b9213759afed00e69","cross_cats_sorted":["cs.LG","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-12T01:28:04Z","title_canon_sha256":"a71a1a24f49af3446a6d19bf63fa9a17fd42ba35677e943765d58e6439cd02c1"},"schema_version":"1.0","source":{"id":"2506.10271","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10271","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10271v3","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10271","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"AL2EPAWLGQUJ","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"AL2EPAWLGQUJAP4Y","created_at":"2026-07-05T11:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"AL2EPAWL","created_at":"2026-07-05T11:59:15Z"}],"graph_snapshots":[{"event_id":"sha256:52255ae5be1ef7ef5dfcd3f52454da5720b871e27a84fbbd5e1a2d772371b2e1","target":"graph","created_at":"2026-07-05T11:59:15Z","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/2506.10271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Genomic language models (gLMs) hold promise for generating novel, functional DNA sequences for synthetic biology. However, realizing this potential requires models to go beyond evolutionary plausibility and understand how DNA sequence encodes gene expression and regulation. We introduce a benchmark called Nullsettes, which assesses how well models can predict in silico loss-of-function (LOF) mutations, in synthetic expression cassettes with little evolutionary precedent. Testing 12 state-of-the-art gLMs, we find that most fail to consistently detect these strong LOF mutations. All models show ","authors_text":"Shiyu Jiang, Xuyin Liu, Zitong Jerry Wang","cross_cats":["cs.LG","q-bio.GN"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-12T01:28:04Z","title":"Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10271","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":"sha256:183f589dfd543840ac97615074e1373bd8e60f078ca1a54ff71a9afcf48e259d","target":"record","created_at":"2026-07-05T11:59:15Z","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":"92f17fc6296e1ee66d11407ec70363986ea4b4e20365e54b9213759afed00e69","cross_cats_sorted":["cs.LG","q-bio.GN"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-12T01:28:04Z","title_canon_sha256":"a71a1a24f49af3446a6d19bf63fa9a17fd42ba35677e943765d58e6439cd02c1"},"schema_version":"1.0","source":{"id":"2506.10271","kind":"arxiv","version":3}},"canonical_sha256":"02f44782cb3428903f98650b88bcf0f98b23a1a533af980775702451527cf2ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02f44782cb3428903f98650b88bcf0f98b23a1a533af980775702451527cf2ab","first_computed_at":"2026-07-05T11:59:15.740028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:15.740028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xC3bCF8DXFdAesl1KriUtAlWKENoesN8uP3CLY6fXYcah6ooHE27foIr2M35xgzhtTwCxAGUGf2tPZz7k7V+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:15.740500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10271","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:183f589dfd543840ac97615074e1373bd8e60f078ca1a54ff71a9afcf48e259d","sha256:52255ae5be1ef7ef5dfcd3f52454da5720b871e27a84fbbd5e1a2d772371b2e1"],"state_sha256":"4996a2c63b50cb8be996efc413e008768b11c7a18bd6ba82e1e25bf38b99027f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hMpRHErqdld8kUGd08HBdPWd9VJfYOegMEajH+J8O3eQDs0urmAyHSZaoXB4fdbfndSgwF/7R0H8o+rQEpyYAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:51:28.524337Z","bundle_sha256":"f06f856c32959e074f914e1611d9b05e7703c6f3a42be6ee6659e08db0edabae"}}