{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AT4LCNZW35FS6NCOEIGWMPMUYT","short_pith_number":"pith:AT4LCNZW","canonical_record":{"source":{"id":"2112.07571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"8e794bb34d717208ee2bf8f607482487f3fcc48a1f5d0463cdeb46504dc49c09","abstract_canon_sha256":"6de44e8e4c6cf5bc9bf535561f60a00cabb32dc05c76d7feb78b3e3934bbcab8"},"schema_version":"1.0"},"canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","source":{"kind":"arxiv","id":"2112.07571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07571","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07571v1","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07571","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"AT4LCNZW35FS","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"AT4LCNZW35FS6NCO","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"AT4LCNZW","created_at":"2026-07-05T03:40:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AT4LCNZW35FS6NCOEIGWMPMUYT","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","cross_cats_sorted":["q-bio.GN"],"title_canon_sha256":"8e794bb34d717208ee2bf8f607482487f3fcc48a1f5d0463cdeb46504dc49c09","abstract_canon_sha256":"6de44e8e4c6cf5bc9bf535561f60a00cabb32dc05c76d7feb78b3e3934bbcab8"},"schema_version":"1.0"},"canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:59.672609Z","signature_b64":"FyUJrC8wKyCnHuulXF2u2HaLI/ZE3NY/m5XmdJycWSOtXU1mrK2K1TekA2kupb4Ecj9D9uPM2Oxf/hIuH9xZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","last_reissued_at":"2026-07-05T03:40:59.672161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:59.672161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07571","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":"2026-07-05T03:40:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yt01Z1Z5odsRATy3wddme/KLHvpLaib9Wto4l48IA0TJb5qFqdl/SpscmVUmhJRadEdaxh7si/G2g+yVHyndBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:37:27.243534Z"},"content_sha256":"86a265b8ce3554cb3518d6a9ae8e6bc3b1aae2d47694342179cd281ef103fa91","schema_version":"1.0","event_id":"sha256:86a265b8ce3554cb3518d6a9ae8e6bc3b1aae2d47694342179cd281ef103fa91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AT4LCNZW35FS6NCOEIGWMPMUYT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Epigenomic language models powered by Cerebras","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["q-bio.GN"],"primary_cat":"cs.LG","authors_text":"Cuong Q. Nguyen, Kim M. Branson, Meredith V. Trotter, Rob T. Woodruff, Stephen Young","submitted_at":"2021-12-14T17:23:42Z","abstract_excerpt":"Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective representations of DNA sequences using large genomic sequence corpuses may accelerate the development of models of gene regulation and function through transfer learning. However, to accurately model cell type-specific gene regulation and function, it is necessary to consider not only the information contained in DNA nucleotide sequences, which is mostly invarian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07571","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/2112.07571/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":"2026-07-05T03:40:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cwt3HcB8ZiOumO1YTuLKGzA+25UHA4WCM5G7zhyQvHpYCE241QWy/KG5grugYmi9G/eSVhb+KbfUr2kue55+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:37:27.244339Z"},"content_sha256":"ca093b2ad7eb5728e1919ccef67d13c6cab8936bd8b655342f7a81fb3b28c185","schema_version":"1.0","event_id":"sha256:ca093b2ad7eb5728e1919ccef67d13c6cab8936bd8b655342f7a81fb3b28c185"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/bundle.json","state_url":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/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":"2026-07-07T04:37:27Z","links":{"resolver":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT","bundle":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/bundle.json","state":"https://pith.science/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AT4LCNZW35FS6NCOEIGWMPMUYT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AT4LCNZW35FS6NCOEIGWMPMUYT","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":"6de44e8e4c6cf5bc9bf535561f60a00cabb32dc05c76d7feb78b3e3934bbcab8","cross_cats_sorted":["q-bio.GN"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","title_canon_sha256":"8e794bb34d717208ee2bf8f607482487f3fcc48a1f5d0463cdeb46504dc49c09"},"schema_version":"1.0","source":{"id":"2112.07571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07571","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07571v1","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07571","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"AT4LCNZW35FS","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"AT4LCNZW35FS6NCO","created_at":"2026-07-05T03:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"AT4LCNZW","created_at":"2026-07-05T03:40:59Z"}],"graph_snapshots":[{"event_id":"sha256:ca093b2ad7eb5728e1919ccef67d13c6cab8936bd8b655342f7a81fb3b28c185","target":"graph","created_at":"2026-07-05T03:40:59Z","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/2112.07571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective representations of DNA sequences using large genomic sequence corpuses may accelerate the development of models of gene regulation and function through transfer learning. However, to accurately model cell type-specific gene regulation and function, it is necessary to consider not only the information contained in DNA nucleotide sequences, which is mostly invarian","authors_text":"Cuong Q. Nguyen, Kim M. Branson, Meredith V. Trotter, Rob T. Woodruff, Stephen Young","cross_cats":["q-bio.GN"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","title":"Epigenomic language models powered by Cerebras"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07571","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":"sha256:86a265b8ce3554cb3518d6a9ae8e6bc3b1aae2d47694342179cd281ef103fa91","target":"record","created_at":"2026-07-05T03:40:59Z","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":"6de44e8e4c6cf5bc9bf535561f60a00cabb32dc05c76d7feb78b3e3934bbcab8","cross_cats_sorted":["q-bio.GN"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T17:23:42Z","title_canon_sha256":"8e794bb34d717208ee2bf8f607482487f3fcc48a1f5d0463cdeb46504dc49c09"},"schema_version":"1.0","source":{"id":"2112.07571","kind":"arxiv","version":1}},"canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04f8b13736df4b2f344e220d663d94c4d4f9e34b3e3290fcd7fc6e24b823169b","first_computed_at":"2026-07-05T03:40:59.672161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:59.672161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FyUJrC8wKyCnHuulXF2u2HaLI/ZE3NY/m5XmdJycWSOtXU1mrK2K1TekA2kupb4Ecj9D9uPM2Oxf/hIuH9xZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:59.672609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86a265b8ce3554cb3518d6a9ae8e6bc3b1aae2d47694342179cd281ef103fa91","sha256:ca093b2ad7eb5728e1919ccef67d13c6cab8936bd8b655342f7a81fb3b28c185"],"state_sha256":"8b69e33a0649517da63cbf497d34b70a63b351fc68de5a4f81b9b7cc22bcfb2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDMvx+wfyhIXEdu7KJ+zagxCLYTjNzQOX+pEB5NbV8QtYD6nTVFlD3+GM6MBnOQJUt6h7ZTUP88++LhsRJoMBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:37:27.248152Z","bundle_sha256":"90f9c3a5050d46b570a6cde8b48c73ce87b159e9ddbb861cff25239228169de4"}}