{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KLBM6MAVG4C2IO73CZTNPXCZ6I","short_pith_number":"pith:KLBM6MAV","schema_version":"1.0","canonical_sha256":"52c2cf30153705a43bfb1666d7dc59f2347cb8993d6cc1f75bb1576ec273910a","source":{"kind":"arxiv","id":"2505.21194","version":1},"attestation_state":"computed","paper":{"title":"Vectorized Sequence-Based Chunking for Data Deduplication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Samer Al-Kiswany, Sreeharsha Udayashankar","submitted_at":"2025-05-27T13:42:33Z","abstract_excerpt":"Data deduplication has gained wide acclaim as a mechanism to improve storage efficiency and conserve network bandwidth. Its most critical phase, data chunking, is responsible for the overall space savings achieved via the deduplication process. However, modern data chunking algorithms are slow and compute-intensive because they scan large amounts of data while simultaneously making data-driven boundary decisions.\n  We present SeqCDC, a novel chunking algorithm that leverages lightweight boundary detection, content-defined skipping, and SSE/AVX acceleration to improve chunking throughput for la"},"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":"2505.21194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-05-27T13:42:33Z","cross_cats_sorted":[],"title_canon_sha256":"d4792d2429582c2d323729fa7024936671273c8ab03ac84faf9c588093a085b4","abstract_canon_sha256":"85834c65109c7f268b73b2d5cc1ec9ea28ef66efb0b1fcad9227acb1bf0a1d42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:38.559299Z","signature_b64":"VZB/4zLjfql4KcphZ8/gDVhBofjBGNJ6z6v/Ia0VXK7MYN0sz1FYdlGxp8JS3BHvl4YbSsskxUsKSeyTudiXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52c2cf30153705a43bfb1666d7dc59f2347cb8993d6cc1f75bb1576ec273910a","last_reissued_at":"2026-07-05T11:10:38.558827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:38.558827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vectorized Sequence-Based Chunking for Data Deduplication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Samer Al-Kiswany, Sreeharsha Udayashankar","submitted_at":"2025-05-27T13:42:33Z","abstract_excerpt":"Data deduplication has gained wide acclaim as a mechanism to improve storage efficiency and conserve network bandwidth. Its most critical phase, data chunking, is responsible for the overall space savings achieved via the deduplication process. However, modern data chunking algorithms are slow and compute-intensive because they scan large amounts of data while simultaneously making data-driven boundary decisions.\n  We present SeqCDC, a novel chunking algorithm that leverages lightweight boundary detection, content-defined skipping, and SSE/AVX acceleration to improve chunking throughput for la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21194","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/2505.21194/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":"2505.21194","created_at":"2026-07-05T11:10:38.558877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21194v1","created_at":"2026-07-05T11:10:38.558877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21194","created_at":"2026-07-05T11:10:38.558877+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLBM6MAVG4C2","created_at":"2026-07-05T11:10:38.558877+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLBM6MAVG4C2IO73","created_at":"2026-07-05T11:10:38.558877+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLBM6MAV","created_at":"2026-07-05T11:10:38.558877+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/KLBM6MAVG4C2IO73CZTNPXCZ6I","json":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I.json","graph_json":"https://pith.science/api/pith-number/KLBM6MAVG4C2IO73CZTNPXCZ6I/graph.json","events_json":"https://pith.science/api/pith-number/KLBM6MAVG4C2IO73CZTNPXCZ6I/events.json","paper":"https://pith.science/paper/KLBM6MAV"},"agent_actions":{"view_html":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I","download_json":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I.json","view_paper":"https://pith.science/paper/KLBM6MAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21194&json=true","fetch_graph":"https://pith.science/api/pith-number/KLBM6MAVG4C2IO73CZTNPXCZ6I/graph.json","fetch_events":"https://pith.science/api/pith-number/KLBM6MAVG4C2IO73CZTNPXCZ6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I/action/storage_attestation","attest_author":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I/action/author_attestation","sign_citation":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I/action/citation_signature","submit_replication":"https://pith.science/pith/KLBM6MAVG4C2IO73CZTNPXCZ6I/action/replication_record"}},"created_at":"2026-07-05T11:10:38.558877+00:00","updated_at":"2026-07-05T11:10:38.558877+00:00"}