{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3Y7MPQGL3WJ2YRF6YCKA7ILUBJ","short_pith_number":"pith:3Y7MPQGL","schema_version":"1.0","canonical_sha256":"de3ec7c0cbdd93ac44bec0940fa1740a5b9eef39cc161d94ab088b33e95c6157","source":{"kind":"arxiv","id":"1503.01624","version":1},"attestation_state":"computed","paper":{"title":"GDC 2: Compression of large collections of genomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","q-bio.GN"],"primary_cat":"cs.DS","authors_text":"Agnieszka Danek, Marcin Niemiec, Sebastian Deorowicz","submitted_at":"2015-03-05T12:38:32Z","abstract_excerpt":"The fall of prices of the high-throughput genome sequencing changes the landscape of modern genomics. A number of large scale projects aimed at sequencing many human genomes are in progress. Genome sequencing also becomes an important aid in the personalized medicine. One of the significant side effects of this change is a necessity of storage and transfer of huge amounts of genomic data. In this paper we deal with the problem of compression of large collections of complete genomic sequences. We propose an algorithm that is able to compress the collection of 1092 human diploid genomes about 9,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1503.01624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-03-05T12:38:32Z","cross_cats_sorted":["cs.CE","q-bio.GN"],"title_canon_sha256":"df59d900b5779ca05d8531a99f1c8d43a3dd599fcf229b02821fa9dc99e3d602","abstract_canon_sha256":"649e3e9013fe58b22ad731a963a19cb3e248406ca796e79c6f0906a3d3064fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:42.762129Z","signature_b64":"0C3EOO0KK2+9mlg9NLSp2a/aF0wGgrnRYtQWmiffp5lSKi7akEilOHFUqKBj9muKbZX+vwKiPbKPzSn9gMJqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de3ec7c0cbdd93ac44bec0940fa1740a5b9eef39cc161d94ab088b33e95c6157","last_reissued_at":"2026-05-18T00:49:42.761529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:42.761529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GDC 2: Compression of large collections of genomes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","q-bio.GN"],"primary_cat":"cs.DS","authors_text":"Agnieszka Danek, Marcin Niemiec, Sebastian Deorowicz","submitted_at":"2015-03-05T12:38:32Z","abstract_excerpt":"The fall of prices of the high-throughput genome sequencing changes the landscape of modern genomics. A number of large scale projects aimed at sequencing many human genomes are in progress. Genome sequencing also becomes an important aid in the personalized medicine. One of the significant side effects of this change is a necessity of storage and transfer of huge amounts of genomic data. In this paper we deal with the problem of compression of large collections of complete genomic sequences. We propose an algorithm that is able to compress the collection of 1092 human diploid genomes about 9,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.01624","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.01624","created_at":"2026-05-18T00:49:42.761638+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.01624v1","created_at":"2026-05-18T00:49:42.761638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.01624","created_at":"2026-05-18T00:49:42.761638+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Y7MPQGL3WJ2","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Y7MPQGL3WJ2YRF6","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Y7MPQGL","created_at":"2026-05-18T12:29:02.477457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ","json":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ.json","graph_json":"https://pith.science/api/pith-number/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/graph.json","events_json":"https://pith.science/api/pith-number/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/events.json","paper":"https://pith.science/paper/3Y7MPQGL"},"agent_actions":{"view_html":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ","download_json":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ.json","view_paper":"https://pith.science/paper/3Y7MPQGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.01624&json=true","fetch_graph":"https://pith.science/api/pith-number/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/action/storage_attestation","attest_author":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/action/author_attestation","sign_citation":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/action/citation_signature","submit_replication":"https://pith.science/pith/3Y7MPQGL3WJ2YRF6YCKA7ILUBJ/action/replication_record"}},"created_at":"2026-05-18T00:49:42.761638+00:00","updated_at":"2026-05-18T00:49:42.761638+00:00"}