{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:RT4QMPONMJ7DQEBD5X5C6ZJ3HY","short_pith_number":"pith:RT4QMPON","canonical_record":{"source":{"id":"1507.05720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-07-21T06:37:35Z","cross_cats_sorted":["cs.DC","q-bio.GN","stat.ML"],"title_canon_sha256":"6d0953a7162e5980d0618a1868b874084c58c97ad2cbf3ce1389def4b74a430b","abstract_canon_sha256":"d855f0413268e4994f63cfa3b27ccd9e84a709da2d5d9e3060175763bbc83fba"},"schema_version":"1.0"},"canonical_sha256":"8cf9063dcd627e381023edfa2f653b3e377bf40eb6890ef2577e8ebb5dc4cd30","source":{"kind":"arxiv","id":"1507.05720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05720","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05720v1","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05720","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"RT4QMPONMJ7D","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RT4QMPONMJ7DQEBD","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RT4QMPON","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:RT4QMPONMJ7DQEBD5X5C6ZJ3HY","target":"record","payload":{"canonical_record":{"source":{"id":"1507.05720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-07-21T06:37:35Z","cross_cats_sorted":["cs.DC","q-bio.GN","stat.ML"],"title_canon_sha256":"6d0953a7162e5980d0618a1868b874084c58c97ad2cbf3ce1389def4b74a430b","abstract_canon_sha256":"d855f0413268e4994f63cfa3b27ccd9e84a709da2d5d9e3060175763bbc83fba"},"schema_version":"1.0"},"canonical_sha256":"8cf9063dcd627e381023edfa2f653b3e377bf40eb6890ef2577e8ebb5dc4cd30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:57.753670Z","signature_b64":"E0a4vLeaU07lmvOmgYTwuQMKXebV9b4mIOzFL79ycfZyK4I6FynSSuLpeRtcBMkCMRfyZVMtUXdIwFXcAEwkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf9063dcd627e381023edfa2f653b3e377bf40eb6890ef2577e8ebb5dc4cd30","last_reissued_at":"2026-05-18T00:50:57.753090Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:57.753090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.05720","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":"2026-05-18T00:50:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Q0c4BZkuO49XFzaz+jiI2zUHvfGjxJ6JaODlnmuc2Ap8ntJzocOfwxyb5sgWFaer4sdHYu7QXAc4/P1FfOXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:06:10.138245Z"},"content_sha256":"7518bbf9a130337adc06e70f7cfc4d3fcbc426e8a4705d85725e03d6ded8a309","schema_version":"1.0","event_id":"sha256:7518bbf9a130337adc06e70f7cfc4d3fcbc426e8a4705d85725e03d6ded8a309"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:RT4QMPONMJ7DQEBD5X5C6ZJ3HY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gene expression modelling across multiple cell-lines with MapReduce","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","q-bio.GN","stat.ML"],"primary_cat":"q-bio.QM","authors_text":"David M. Budden, Edmund J. Crampin","submitted_at":"2015-07-21T06:37:35Z","abstract_excerpt":"With the wealth of high-throughput sequencing data generated by recent large-scale consortia, predictive gene expression modelling has become an important tool for integrative analysis of transcriptomic and epigenetic data. However, sequencing data-sets are characteristically large, and previously modelling frameworks are typically inefficient and unable to leverage multi-core or distributed processing architectures. In this study, we detail an efficient and parallelised MapReduce implementation of gene expression modelling. We leverage the computational efficiency of this framework to provide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05720","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":""},"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":"2026-05-18T00:50:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWr/aqfQl1QKkvhjKBc8qKYhbDItBNZJExDIzsQ3U29NwbP4jXPx87Jh7IM+JO5+MCChsAxRi2xclz1YBt1vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:06:10.138611Z"},"content_sha256":"7729957cfff66468252a018e3c2c4004fee5c5f39043e5402c6ff1815a69b40b","schema_version":"1.0","event_id":"sha256:7729957cfff66468252a018e3c2c4004fee5c5f39043e5402c6ff1815a69b40b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/bundle.json","state_url":"https://pith.science/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/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":"2026-06-29T21:06:10Z","links":{"resolver":"https://pith.science/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY","bundle":"https://pith.science/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/bundle.json","state":"https://pith.science/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RT4QMPONMJ7DQEBD5X5C6ZJ3HY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:RT4QMPONMJ7DQEBD5X5C6ZJ3HY","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":"d855f0413268e4994f63cfa3b27ccd9e84a709da2d5d9e3060175763bbc83fba","cross_cats_sorted":["cs.DC","q-bio.GN","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-07-21T06:37:35Z","title_canon_sha256":"6d0953a7162e5980d0618a1868b874084c58c97ad2cbf3ce1389def4b74a430b"},"schema_version":"1.0","source":{"id":"1507.05720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.05720","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"1507.05720v1","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05720","created_at":"2026-05-18T00:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"RT4QMPONMJ7D","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"RT4QMPONMJ7DQEBD","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"RT4QMPON","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:7729957cfff66468252a018e3c2c4004fee5c5f39043e5402c6ff1815a69b40b","target":"graph","created_at":"2026-05-18T00:50:57Z","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"},"paper":{"abstract_excerpt":"With the wealth of high-throughput sequencing data generated by recent large-scale consortia, predictive gene expression modelling has become an important tool for integrative analysis of transcriptomic and epigenetic data. However, sequencing data-sets are characteristically large, and previously modelling frameworks are typically inefficient and unable to leverage multi-core or distributed processing architectures. In this study, we detail an efficient and parallelised MapReduce implementation of gene expression modelling. We leverage the computational efficiency of this framework to provide","authors_text":"David M. Budden, Edmund J. Crampin","cross_cats":["cs.DC","q-bio.GN","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-07-21T06:37:35Z","title":"Gene expression modelling across multiple cell-lines with MapReduce"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05720","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":"sha256:7518bbf9a130337adc06e70f7cfc4d3fcbc426e8a4705d85725e03d6ded8a309","target":"record","created_at":"2026-05-18T00:50:57Z","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":"d855f0413268e4994f63cfa3b27ccd9e84a709da2d5d9e3060175763bbc83fba","cross_cats_sorted":["cs.DC","q-bio.GN","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2015-07-21T06:37:35Z","title_canon_sha256":"6d0953a7162e5980d0618a1868b874084c58c97ad2cbf3ce1389def4b74a430b"},"schema_version":"1.0","source":{"id":"1507.05720","kind":"arxiv","version":1}},"canonical_sha256":"8cf9063dcd627e381023edfa2f653b3e377bf40eb6890ef2577e8ebb5dc4cd30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cf9063dcd627e381023edfa2f653b3e377bf40eb6890ef2577e8ebb5dc4cd30","first_computed_at":"2026-05-18T00:50:57.753090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:57.753090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E0a4vLeaU07lmvOmgYTwuQMKXebV9b4mIOzFL79ycfZyK4I6FynSSuLpeRtcBMkCMRfyZVMtUXdIwFXcAEwkCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:57.753670Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.05720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7518bbf9a130337adc06e70f7cfc4d3fcbc426e8a4705d85725e03d6ded8a309","sha256:7729957cfff66468252a018e3c2c4004fee5c5f39043e5402c6ff1815a69b40b"],"state_sha256":"72b66dd19f8b409c4946f99176f25480e3d3b76e722334a73c0a5b8739e67750"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKZwep55rrsgAsyCbUSlQ8LNCVM/SWqvdSXUiPXRn+06NpmIV2aJIbaK8F6fjeyWiVZ/cLD4Z4o5wueWk5PaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T21:06:10.140536Z","bundle_sha256":"655ac14d02dd209876828455ddf04ccc7afc91f14e92c248e97903e0a1dd20d4"}}