{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DNG2OMPMHG6UQPAAXTONODY6ND","short_pith_number":"pith:DNG2OMPM","schema_version":"1.0","canonical_sha256":"1b4da731ec39bd483c00bcdcd70f1e68e702e332b1dfff8d32a3bf28b4dae1f2","source":{"kind":"arxiv","id":"2507.12805","version":1},"attestation_state":"computed","paper":{"title":"PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Cheng Zhong, Gang Wang, Huidong Ma, Hui Sun, Liping Yi, Wentong Cai, Xiaoguang Liu, Yanfeng Ding","submitted_at":"2025-07-17T05:46:08Z","abstract_excerpt":"Learning-based lossless compressors play a crucial role in large-scale genomic database backup, storage, transmission, and management. However, their 1) inadequate compression ratio, 2) low compression \\& decompression throughput, and 3) poor compression robustness limit their widespread adoption and application in both industry and academia. To solve those challenges, we propose a novel \\underline{P}arallel \\underline{M}ulti-\\underline{K}nowledge \\underline{L}earning-based \\underline{C}ompressor (PMKLC) with four crucial designs: 1) We propose an automated multi-knowledge learning-based compr"},"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":"2507.12805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T05:46:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"3c5528e6b076785a52ec7f4429885783f4794e034196068c4e8defdc184b2bad","abstract_canon_sha256":"cbb1c7058d6689fbd36b6d2092df909100b06e132fd5805c75bf06ad17d3ddc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:39.610900Z","signature_b64":"rYvjljWp4mgLoJqXAxmKMDvov0os219Dka+Fc9b447qeS65NOg8WMmGQb5ntWWdZPja138k9RivRonNn408qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4da731ec39bd483c00bcdcd70f1e68e702e332b1dfff8d32a3bf28b4dae1f2","last_reissued_at":"2026-07-05T11:38:39.610398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:39.610398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Cheng Zhong, Gang Wang, Huidong Ma, Hui Sun, Liping Yi, Wentong Cai, Xiaoguang Liu, Yanfeng Ding","submitted_at":"2025-07-17T05:46:08Z","abstract_excerpt":"Learning-based lossless compressors play a crucial role in large-scale genomic database backup, storage, transmission, and management. However, their 1) inadequate compression ratio, 2) low compression \\& decompression throughput, and 3) poor compression robustness limit their widespread adoption and application in both industry and academia. To solve those challenges, we propose a novel \\underline{P}arallel \\underline{M}ulti-\\underline{K}nowledge \\underline{L}earning-based \\underline{C}ompressor (PMKLC) with four crucial designs: 1) We propose an automated multi-knowledge learning-based compr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12805","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/2507.12805/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.12805","created_at":"2026-07-05T11:38:39.610455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12805v1","created_at":"2026-07-05T11:38:39.610455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12805","created_at":"2026-07-05T11:38:39.610455+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNG2OMPMHG6U","created_at":"2026-07-05T11:38:39.610455+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNG2OMPMHG6UQPAA","created_at":"2026-07-05T11:38:39.610455+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNG2OMPM","created_at":"2026-07-05T11:38:39.610455+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/DNG2OMPMHG6UQPAAXTONODY6ND","json":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND.json","graph_json":"https://pith.science/api/pith-number/DNG2OMPMHG6UQPAAXTONODY6ND/graph.json","events_json":"https://pith.science/api/pith-number/DNG2OMPMHG6UQPAAXTONODY6ND/events.json","paper":"https://pith.science/paper/DNG2OMPM"},"agent_actions":{"view_html":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND","download_json":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND.json","view_paper":"https://pith.science/paper/DNG2OMPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12805&json=true","fetch_graph":"https://pith.science/api/pith-number/DNG2OMPMHG6UQPAAXTONODY6ND/graph.json","fetch_events":"https://pith.science/api/pith-number/DNG2OMPMHG6UQPAAXTONODY6ND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND/action/storage_attestation","attest_author":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND/action/author_attestation","sign_citation":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND/action/citation_signature","submit_replication":"https://pith.science/pith/DNG2OMPMHG6UQPAAXTONODY6ND/action/replication_record"}},"created_at":"2026-07-05T11:38:39.610455+00:00","updated_at":"2026-07-05T11:38:39.610455+00:00"}