{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KC3SR3DEAWLKVJ7LLUBXQ7LALT","short_pith_number":"pith:KC3SR3DE","schema_version":"1.0","canonical_sha256":"50b728ec640596aaa7eb5d03787d605cf63870722ee590471fd07111ce61bd8e","source":{"kind":"arxiv","id":"2406.19113","version":1},"attestation_state":"computed","paper":{"title":"MegIS: High-Performance, Energy-Efficient, and Low-Cost Metagenomic Analysis with In-Storage Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","q-bio.GN"],"primary_cat":"cs.AR","authors_text":"Arvid Gollwitzer, Can Firtina, Haiyu Mao, Harun Mustafa, Jisung Park, Jo\\\"el Lindegger, Julien Eudine, Meryem Banu Cavlak, Mohammad Sadrosadati, Mohammed Alser, Nika Mansouri Ghiasi, Onur Mutlu","submitted_at":"2024-06-27T11:52:17Z","abstract_excerpt":"Metagenomics has led to significant advances in many fields. Metagenomic analysis commonly involves the key tasks of determining the species present in a sample and their relative abundances. These tasks require searching large metagenomic databases. Metagenomic analysis suffers from significant data movement overhead due to moving large amounts of low-reuse data from the storage system. In-storage processing can be a fundamental solution for reducing this overhead. However, designing an in-storage processing system for metagenomics is challenging because existing approaches to metagenomic ana"},"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":"2406.19113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2024-06-27T11:52:17Z","cross_cats_sorted":["cs.DC","q-bio.GN"],"title_canon_sha256":"e19d7084ebc44af14c8bfe1cd3b0791df09f29bab90a57fb4837a27310485bd0","abstract_canon_sha256":"2864a4c69a8c815d2140228408a452df69155c026a372930af5da5e4969fdeb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:30.313872Z","signature_b64":"JvIl2pF7tx21KsSM7PQW7GQkXXvgtDs55g20CKZQXEt3birA82UMcTfE4TcnRz/07ttZQmGY/h/W7PTW625oBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50b728ec640596aaa7eb5d03787d605cf63870722ee590471fd07111ce61bd8e","last_reissued_at":"2026-07-05T08:37:30.313378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:30.313378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegIS: High-Performance, Energy-Efficient, and Low-Cost Metagenomic Analysis with In-Storage Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","q-bio.GN"],"primary_cat":"cs.AR","authors_text":"Arvid Gollwitzer, Can Firtina, Haiyu Mao, Harun Mustafa, Jisung Park, Jo\\\"el Lindegger, Julien Eudine, Meryem Banu Cavlak, Mohammad Sadrosadati, Mohammed Alser, Nika Mansouri Ghiasi, Onur Mutlu","submitted_at":"2024-06-27T11:52:17Z","abstract_excerpt":"Metagenomics has led to significant advances in many fields. Metagenomic analysis commonly involves the key tasks of determining the species present in a sample and their relative abundances. These tasks require searching large metagenomic databases. Metagenomic analysis suffers from significant data movement overhead due to moving large amounts of low-reuse data from the storage system. In-storage processing can be a fundamental solution for reducing this overhead. However, designing an in-storage processing system for metagenomics is challenging because existing approaches to metagenomic ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19113","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/2406.19113/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":"2406.19113","created_at":"2026-07-05T08:37:30.313440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19113v1","created_at":"2026-07-05T08:37:30.313440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19113","created_at":"2026-07-05T08:37:30.313440+00:00"},{"alias_kind":"pith_short_12","alias_value":"KC3SR3DEAWLK","created_at":"2026-07-05T08:37:30.313440+00:00"},{"alias_kind":"pith_short_16","alias_value":"KC3SR3DEAWLKVJ7L","created_at":"2026-07-05T08:37:30.313440+00:00"},{"alias_kind":"pith_short_8","alias_value":"KC3SR3DE","created_at":"2026-07-05T08:37:30.313440+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/KC3SR3DEAWLKVJ7LLUBXQ7LALT","json":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT.json","graph_json":"https://pith.science/api/pith-number/KC3SR3DEAWLKVJ7LLUBXQ7LALT/graph.json","events_json":"https://pith.science/api/pith-number/KC3SR3DEAWLKVJ7LLUBXQ7LALT/events.json","paper":"https://pith.science/paper/KC3SR3DE"},"agent_actions":{"view_html":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT","download_json":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT.json","view_paper":"https://pith.science/paper/KC3SR3DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19113&json=true","fetch_graph":"https://pith.science/api/pith-number/KC3SR3DEAWLKVJ7LLUBXQ7LALT/graph.json","fetch_events":"https://pith.science/api/pith-number/KC3SR3DEAWLKVJ7LLUBXQ7LALT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT/action/storage_attestation","attest_author":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT/action/author_attestation","sign_citation":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT/action/citation_signature","submit_replication":"https://pith.science/pith/KC3SR3DEAWLKVJ7LLUBXQ7LALT/action/replication_record"}},"created_at":"2026-07-05T08:37:30.313440+00:00","updated_at":"2026-07-05T08:37:30.313440+00:00"}