{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CY454U5PBAVRSHDURSV4GGH6IJ","short_pith_number":"pith:CY454U5P","schema_version":"1.0","canonical_sha256":"1639de53af082b191c748cabc318fe42775f5b34186b6c9abf47f1d4791ef4b3","source":{"kind":"arxiv","id":"1704.00878","version":1},"attestation_state":"computed","paper":{"title":"HAlign-II: efficient ultra-large multiple sequence alignment and phylogenetic tree reconstruction with distributed and parallel computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.DC","authors_text":"Quan Zou, Shixiang Wan","submitted_at":"2017-04-04T05:49:04Z","abstract_excerpt":"Multiple sequence alignment (MSA) plays a key role in biological sequence analyses, especially in phylogenetic tree construction. Extreme increase in next-generation sequencing results in shortage of efficient ultra-large biological sequence alignment approaches for coping with different sequence types. Distributed and parallel computing represents a crucial technique for accelerating ultra-large sequence analyses. Based on HAlign and Spark distributed computing system, we implement a highly cost-efficient and time-efficient HAlign-II tool to address ultra-large multiple biological sequence al"},"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":"1704.00878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-04-04T05:49:04Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"96ab7949a109db73d5de606a937ac0ff322b43e23684e52871c284bad4fdd0c0","abstract_canon_sha256":"38c44920701ae562972c9a0e46a9b9b4fea0746d63183b9d2a27f4bd70518215"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:00.445005Z","signature_b64":"dHIMG2p+GSLJawxDEqpXObl6PC7bQ4xq88cGuETRJzf1RQX3Zi+YYvcGP16QGVio42ykoUFfoTJorL+IK8LrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1639de53af082b191c748cabc318fe42775f5b34186b6c9abf47f1d4791ef4b3","last_reissued_at":"2026-05-18T00:47:00.444493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:00.444493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAlign-II: efficient ultra-large multiple sequence alignment and phylogenetic tree reconstruction with distributed and parallel computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.DC","authors_text":"Quan Zou, Shixiang Wan","submitted_at":"2017-04-04T05:49:04Z","abstract_excerpt":"Multiple sequence alignment (MSA) plays a key role in biological sequence analyses, especially in phylogenetic tree construction. Extreme increase in next-generation sequencing results in shortage of efficient ultra-large biological sequence alignment approaches for coping with different sequence types. Distributed and parallel computing represents a crucial technique for accelerating ultra-large sequence analyses. Based on HAlign and Spark distributed computing system, we implement a highly cost-efficient and time-efficient HAlign-II tool to address ultra-large multiple biological sequence al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.00878","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":"1704.00878","created_at":"2026-05-18T00:47:00.444558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.00878v1","created_at":"2026-05-18T00:47:00.444558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.00878","created_at":"2026-05-18T00:47:00.444558+00:00"},{"alias_kind":"pith_short_12","alias_value":"CY454U5PBAVR","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CY454U5PBAVRSHDU","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CY454U5P","created_at":"2026-05-18T12:31:10.602751+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/CY454U5PBAVRSHDURSV4GGH6IJ","json":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ.json","graph_json":"https://pith.science/api/pith-number/CY454U5PBAVRSHDURSV4GGH6IJ/graph.json","events_json":"https://pith.science/api/pith-number/CY454U5PBAVRSHDURSV4GGH6IJ/events.json","paper":"https://pith.science/paper/CY454U5P"},"agent_actions":{"view_html":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ","download_json":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ.json","view_paper":"https://pith.science/paper/CY454U5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.00878&json=true","fetch_graph":"https://pith.science/api/pith-number/CY454U5PBAVRSHDURSV4GGH6IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CY454U5PBAVRSHDURSV4GGH6IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ/action/storage_attestation","attest_author":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ/action/author_attestation","sign_citation":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ/action/citation_signature","submit_replication":"https://pith.science/pith/CY454U5PBAVRSHDURSV4GGH6IJ/action/replication_record"}},"created_at":"2026-05-18T00:47:00.444558+00:00","updated_at":"2026-05-18T00:47:00.444558+00:00"}