{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TUJDSZPQ5XQ3UOG5AMGD2FJ22X","short_pith_number":"pith:TUJDSZPQ","canonical_record":{"source":{"id":"2110.14746","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2021-10-27T20:17:35Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"c6d7febff263679092d2e36000cddf82d4dbdc344f0ea3b464117c0ab3589c8c","abstract_canon_sha256":"274ee1efafd0632ca61b91f61304c6abc5ff5254ad66a0cd44e79ebf5dd771a2"},"schema_version":"1.0"},"canonical_sha256":"9d123965f0ede1ba38dd030c3d153ad5f883db5ef395bf67c19079693b179dd2","source":{"kind":"arxiv","id":"2110.14746","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14746","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14746v4","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14746","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"TUJDSZPQ5XQ3","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"TUJDSZPQ5XQ3UOG5","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"TUJDSZPQ","created_at":"2026-07-05T05:40:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TUJDSZPQ5XQ3UOG5AMGD2FJ22X","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14746","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2021-10-27T20:17:35Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"c6d7febff263679092d2e36000cddf82d4dbdc344f0ea3b464117c0ab3589c8c","abstract_canon_sha256":"274ee1efafd0632ca61b91f61304c6abc5ff5254ad66a0cd44e79ebf5dd771a2"},"schema_version":"1.0"},"canonical_sha256":"9d123965f0ede1ba38dd030c3d153ad5f883db5ef395bf67c19079693b179dd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:20.012217Z","signature_b64":"WcE0CXNSHkBCO/KvYCu+nu+e5PiG8uim21RzvRlwzt1mQnVf5SX3dbWBksOzmKq5oywoqxoUUEPtUQfdSxC5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d123965f0ede1ba38dd030c3d153ad5f883db5ef395bf67c19079693b179dd2","last_reissued_at":"2026-07-05T05:40:20.011817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:20.011817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14746","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAwPd2tBMPpMg23mypVUaT6KLeCPqb43yBN40gwXS9wPjQLsyKtXrcuIH7zIthm1IEoyZn9Gg1ce/zItB9k2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:28:35.816831Z"},"content_sha256":"1efe26901335e5578bc95c30153a782c23d7a22bf7839c64d70bb85072e924ae","schema_version":"1.0","event_id":"sha256:1efe26901335e5578bc95c30153a782c23d7a22bf7839c64d70bb85072e924ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TUJDSZPQ5XQ3UOG5AMGD2FJ22X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"q-bio.GN","authors_text":"Kai Wang, Li Fang, Theodore Jiang","submitted_at":"2021-10-27T20:17:35Z","abstract_excerpt":"Various machine-learning models, including deep neural network models, have already been developed to predict deleteriousness of missense (non-synonymous) mutations. Potential improvements to the current state of the art, however, may still benefit from a fresh look at the biological problem using more sophisticated self-adaptive machine-learning approaches. Recent advances in the natural language processing field show transformer models-a type of deep neural network-to be particularly powerful at modeling sequence information with context dependence. In this study, we introduce MutFormer, a t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14746","kind":"arxiv","version":4},"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/2110.14746/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":"2026-07-05T05:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y+WcsFZ84ybuqSVDGwsaH8z5ZmMNhm6RTbMNkdr/Awkp8q85g9SekJ6MQIomYP6zaAbmch+uevA3EBZ36BYrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:28:35.817245Z"},"content_sha256":"3e4a35a4e3933ee854817e2b056c7b5e571281945d46b11e18b92c1b9d400b97","schema_version":"1.0","event_id":"sha256:3e4a35a4e3933ee854817e2b056c7b5e571281945d46b11e18b92c1b9d400b97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/bundle.json","state_url":"https://pith.science/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/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":"2026-07-07T11:28:35Z","links":{"resolver":"https://pith.science/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X","bundle":"https://pith.science/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/bundle.json","state":"https://pith.science/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUJDSZPQ5XQ3UOG5AMGD2FJ22X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TUJDSZPQ5XQ3UOG5AMGD2FJ22X","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":"274ee1efafd0632ca61b91f61304c6abc5ff5254ad66a0cd44e79ebf5dd771a2","cross_cats_sorted":["cs.LG","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2021-10-27T20:17:35Z","title_canon_sha256":"c6d7febff263679092d2e36000cddf82d4dbdc344f0ea3b464117c0ab3589c8c"},"schema_version":"1.0","source":{"id":"2110.14746","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14746","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14746v4","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14746","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"TUJDSZPQ5XQ3","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"TUJDSZPQ5XQ3UOG5","created_at":"2026-07-05T05:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"TUJDSZPQ","created_at":"2026-07-05T05:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:3e4a35a4e3933ee854817e2b056c7b5e571281945d46b11e18b92c1b9d400b97","target":"graph","created_at":"2026-07-05T05:40:20Z","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/2110.14746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Various machine-learning models, including deep neural network models, have already been developed to predict deleteriousness of missense (non-synonymous) mutations. Potential improvements to the current state of the art, however, may still benefit from a fresh look at the biological problem using more sophisticated self-adaptive machine-learning approaches. Recent advances in the natural language processing field show transformer models-a type of deep neural network-to be particularly powerful at modeling sequence information with context dependence. In this study, we introduce MutFormer, a t","authors_text":"Kai Wang, Li Fang, Theodore Jiang","cross_cats":["cs.LG","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2021-10-27T20:17:35Z","title":"Deciphering the Language of Nature: A transformer-based language model for deleterious mutations in proteins"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14746","kind":"arxiv","version":4},"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":"sha256:1efe26901335e5578bc95c30153a782c23d7a22bf7839c64d70bb85072e924ae","target":"record","created_at":"2026-07-05T05:40:20Z","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":"274ee1efafd0632ca61b91f61304c6abc5ff5254ad66a0cd44e79ebf5dd771a2","cross_cats_sorted":["cs.LG","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2021-10-27T20:17:35Z","title_canon_sha256":"c6d7febff263679092d2e36000cddf82d4dbdc344f0ea3b464117c0ab3589c8c"},"schema_version":"1.0","source":{"id":"2110.14746","kind":"arxiv","version":4}},"canonical_sha256":"9d123965f0ede1ba38dd030c3d153ad5f883db5ef395bf67c19079693b179dd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d123965f0ede1ba38dd030c3d153ad5f883db5ef395bf67c19079693b179dd2","first_computed_at":"2026-07-05T05:40:20.011817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:20.011817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WcE0CXNSHkBCO/KvYCu+nu+e5PiG8uim21RzvRlwzt1mQnVf5SX3dbWBksOzmKq5oywoqxoUUEPtUQfdSxC5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:20.012217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14746","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1efe26901335e5578bc95c30153a782c23d7a22bf7839c64d70bb85072e924ae","sha256:3e4a35a4e3933ee854817e2b056c7b5e571281945d46b11e18b92c1b9d400b97"],"state_sha256":"9ab0a9ff8c14828355956ca06a7f59896b780a5f1a72c94205a21379a6f8e557"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKTsiJgXmf0IsvNAcoIqCYJTxEK0Uy5oi684lNFLBmGu42vBQEcgTqF4GCxfJF2wctyogxebic4rCdxfVvfwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:28:35.819239Z","bundle_sha256":"d51685a87546826f831128896a86ba8871b44d7df13d8477d904c15541c31c77"}}