{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UZ7RGSE3VF7PY7YUUPZDS5EFP6","short_pith_number":"pith:UZ7RGSE3","schema_version":"1.0","canonical_sha256":"a67f13489ba97efc7f14a3f23974857f9a7fb6e3d9a603fc94960d536ad1f75c","source":{"kind":"arxiv","id":"1707.05364","version":1},"attestation_state":"computed","paper":{"title":"Modern Data Formats for Big Bioinformatics Data Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.DC"],"primary_cat":"cs.DB","authors_text":"Abbas Rehman, Atif Mehmood, Javed Ferzund, Muhammad Atif Sarwar, M. Usman Ali, Shahzad Ahmed","submitted_at":"2017-05-05T11:35:53Z","abstract_excerpt":"Next Generation Sequencing (NGS) technology has resulted in massive amounts of proteomics and genomics data. This data is of no use if it is not properly analyzed. ETL (Extraction, Transformation, Loading) is an important step in designing data analytics applications. ETL requires proper understanding of features of data. Data format plays a key role in understanding of data, representation of data, space required to store data, data I/O during processing of data, intermediate results of processing, in-memory analysis of data and overall time required to process data. Different data mining and"},"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":"1707.05364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2017-05-05T11:35:53Z","cross_cats_sorted":["cs.CY","cs.DC"],"title_canon_sha256":"800ba27f571bdb451d3903b6055c8f55399e85e5c3507ddab80b518ae576bddc","abstract_canon_sha256":"6230f17da4b8c761ff922236e5f0078406114e24ef7339114198ee0657008b5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:45.648424Z","signature_b64":"txfFAoirJZ74NRaEbx4HVUIBsP49GZ4RBmHBg+ovjraqwzdmLzr9rX/pu6ElIoa9LqmKmwog4jWBHjPWe5DYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a67f13489ba97efc7f14a3f23974857f9a7fb6e3d9a603fc94960d536ad1f75c","last_reissued_at":"2026-05-18T00:39:45.647744Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:45.647744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modern Data Formats for Big Bioinformatics Data Analytics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.DC"],"primary_cat":"cs.DB","authors_text":"Abbas Rehman, Atif Mehmood, Javed Ferzund, Muhammad Atif Sarwar, M. Usman Ali, Shahzad Ahmed","submitted_at":"2017-05-05T11:35:53Z","abstract_excerpt":"Next Generation Sequencing (NGS) technology has resulted in massive amounts of proteomics and genomics data. This data is of no use if it is not properly analyzed. ETL (Extraction, Transformation, Loading) is an important step in designing data analytics applications. ETL requires proper understanding of features of data. Data format plays a key role in understanding of data, representation of data, space required to store data, data I/O during processing of data, intermediate results of processing, in-memory analysis of data and overall time required to process data. Different data mining and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05364","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":"1707.05364","created_at":"2026-05-18T00:39:45.647834+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05364v1","created_at":"2026-05-18T00:39:45.647834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05364","created_at":"2026-05-18T00:39:45.647834+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ7RGSE3VF7P","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ7RGSE3VF7PY7YU","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ7RGSE3","created_at":"2026-05-18T12:31:49.984773+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/UZ7RGSE3VF7PY7YUUPZDS5EFP6","json":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6.json","graph_json":"https://pith.science/api/pith-number/UZ7RGSE3VF7PY7YUUPZDS5EFP6/graph.json","events_json":"https://pith.science/api/pith-number/UZ7RGSE3VF7PY7YUUPZDS5EFP6/events.json","paper":"https://pith.science/paper/UZ7RGSE3"},"agent_actions":{"view_html":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6","download_json":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6.json","view_paper":"https://pith.science/paper/UZ7RGSE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05364&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ7RGSE3VF7PY7YUUPZDS5EFP6/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ7RGSE3VF7PY7YUUPZDS5EFP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6/action/storage_attestation","attest_author":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6/action/author_attestation","sign_citation":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6/action/citation_signature","submit_replication":"https://pith.science/pith/UZ7RGSE3VF7PY7YUUPZDS5EFP6/action/replication_record"}},"created_at":"2026-05-18T00:39:45.647834+00:00","updated_at":"2026-05-18T00:39:45.647834+00:00"}