{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PXL72CDF2H5F2TJT5PZPMKLGSB","short_pith_number":"pith:PXL72CDF","schema_version":"1.0","canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","source":{"kind":"arxiv","id":"2401.01786","version":1},"attestation_state":"computed","paper":{"title":"An experimental sorting method for improving metagenomic data encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT","q-bio.GN"],"primary_cat":"cs.IT","authors_text":"Armando J. Pinho, Diogo Pratas","submitted_at":"2024-01-03T15:27:10Z","abstract_excerpt":"Minimizing data storage poses a significant challenge in large-scale metagenomic projects. In this paper, we present a new method for improving the encoding of FASTQ files generated by metagenomic sequencing. This method incorporates metagenomic classification followed by a recursive filter for clustering reads by DNA sequence similarity to improve the overall reference-free compression. In the results, we show an overall improvement in the compression of several datasets. As hypothesized, we show a progressive compression gain for higher coverage depth and number of identified species. Additi"},"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":"2401.01786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2024-01-03T15:27:10Z","cross_cats_sorted":["math.IT","q-bio.GN"],"title_canon_sha256":"976478b8c6cef17a0cf5287e1c112110f388a564066ec41ab498847dcfccfbcb","abstract_canon_sha256":"875d4222b1c3244a8b7d73c70e5ec6cdf601870848882606fc543b0c102a66bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:57.210643Z","signature_b64":"IN85gfZWMqXCzipskLsGhjc+8EQOofjEWoTKIionmwY9av68IHtigA5Zr1GcsiR9LtRHmkPCjFoj24yo3PIAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dd7fd0865d1fa5d4d33ebf2f62966904c538dd32ba760a8cb63a41112b0c92f","last_reissued_at":"2026-07-05T07:29:57.210267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:57.210267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An experimental sorting method for improving metagenomic data encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT","q-bio.GN"],"primary_cat":"cs.IT","authors_text":"Armando J. Pinho, Diogo Pratas","submitted_at":"2024-01-03T15:27:10Z","abstract_excerpt":"Minimizing data storage poses a significant challenge in large-scale metagenomic projects. In this paper, we present a new method for improving the encoding of FASTQ files generated by metagenomic sequencing. This method incorporates metagenomic classification followed by a recursive filter for clustering reads by DNA sequence similarity to improve the overall reference-free compression. In the results, we show an overall improvement in the compression of several datasets. As hypothesized, we show a progressive compression gain for higher coverage depth and number of identified species. Additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01786","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/2401.01786/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":"2401.01786","created_at":"2026-07-05T07:29:57.210323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.01786v1","created_at":"2026-07-05T07:29:57.210323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01786","created_at":"2026-07-05T07:29:57.210323+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXL72CDF2H5F","created_at":"2026-07-05T07:29:57.210323+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXL72CDF2H5F2TJT","created_at":"2026-07-05T07:29:57.210323+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXL72CDF","created_at":"2026-07-05T07:29:57.210323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18116","citing_title":"Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB","json":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB.json","graph_json":"https://pith.science/api/pith-number/PXL72CDF2H5F2TJT5PZPMKLGSB/graph.json","events_json":"https://pith.science/api/pith-number/PXL72CDF2H5F2TJT5PZPMKLGSB/events.json","paper":"https://pith.science/paper/PXL72CDF"},"agent_actions":{"view_html":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB","download_json":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB.json","view_paper":"https://pith.science/paper/PXL72CDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.01786&json=true","fetch_graph":"https://pith.science/api/pith-number/PXL72CDF2H5F2TJT5PZPMKLGSB/graph.json","fetch_events":"https://pith.science/api/pith-number/PXL72CDF2H5F2TJT5PZPMKLGSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/action/storage_attestation","attest_author":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/action/author_attestation","sign_citation":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/action/citation_signature","submit_replication":"https://pith.science/pith/PXL72CDF2H5F2TJT5PZPMKLGSB/action/replication_record"}},"created_at":"2026-07-05T07:29:57.210323+00:00","updated_at":"2026-07-05T07:29:57.210323+00:00"}