{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NTII7W6JHNZMRAPH4Y2QXZJYPI","short_pith_number":"pith:NTII7W6J","schema_version":"1.0","canonical_sha256":"6cd08fdbc93b72c881e7e6350be5387a2eac56780b66fe17e31174a64286d8d0","source":{"kind":"arxiv","id":"2606.10896","version":1},"attestation_state":"computed","paper":{"title":"Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB","cs.IR","cs.PF"],"primary_cat":"cs.LG","authors_text":"Ariel Gera, Assaf Toledo, Gal Bloch, Matan Orbach, Ohad Eytan","submitted_at":"2026-06-09T14:07:18Z","abstract_excerpt":"We present \\textbf{Flash-GMM}, a fused Triton kernel for efficient computation of Gaussian Mixture Models (GMMs) over large-scale data in a single GPU pass. By eliminating the need to materialize the full responsibility matrix in GPU memory, Flash-GMM achieves a \\textbf{20$\\times$} speedup over existing implementations and enables training on datasets more than \\textbf{100$\\times$} larger than previously feasible on one device. To demonstrate its impact, we integrate Flash-GMM into the IVF coarse quantizer for approximate nearest-neighbor (ANN) search. We show that soft GMM clustering is now a"},"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":"2606.10896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T14:07:18Z","cross_cats_sorted":["cs.DB","cs.IR","cs.PF"],"title_canon_sha256":"9f50fc67dc309ac1a9b16cee1210bbbe7775fc290b64075d0c9a0cfaf1fdcb29","abstract_canon_sha256":"2fba491549e664aedbe6b29424b674b916b658600de009f4060b7a5a1dfb700a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:46.659765Z","signature_b64":"WrQrBc1Bjge569kR3VJFQ6YI9u2rz9ebnfCOytmPERP5eA3dlq4V0U6lD5sZWQFUb1Be8lu6TAU1oa802NarCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd08fdbc93b72c881e7e6350be5387a2eac56780b66fe17e31174a64286d8d0","last_reissued_at":"2026-06-10T01:10:46.659111Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:46.659111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DB","cs.IR","cs.PF"],"primary_cat":"cs.LG","authors_text":"Ariel Gera, Assaf Toledo, Gal Bloch, Matan Orbach, Ohad Eytan","submitted_at":"2026-06-09T14:07:18Z","abstract_excerpt":"We present \\textbf{Flash-GMM}, a fused Triton kernel for efficient computation of Gaussian Mixture Models (GMMs) over large-scale data in a single GPU pass. By eliminating the need to materialize the full responsibility matrix in GPU memory, Flash-GMM achieves a \\textbf{20$\\times$} speedup over existing implementations and enables training on datasets more than \\textbf{100$\\times$} larger than previously feasible on one device. To demonstrate its impact, we integrate Flash-GMM into the IVF coarse quantizer for approximate nearest-neighbor (ANN) search. We show that soft GMM clustering is now a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10896","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/2606.10896/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":"2606.10896","created_at":"2026-06-10T01:10:46.659227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10896v1","created_at":"2026-06-10T01:10:46.659227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10896","created_at":"2026-06-10T01:10:46.659227+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTII7W6JHNZM","created_at":"2026-06-10T01:10:46.659227+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTII7W6JHNZMRAPH","created_at":"2026-06-10T01:10:46.659227+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTII7W6J","created_at":"2026-06-10T01:10:46.659227+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/NTII7W6JHNZMRAPH4Y2QXZJYPI","json":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI.json","graph_json":"https://pith.science/api/pith-number/NTII7W6JHNZMRAPH4Y2QXZJYPI/graph.json","events_json":"https://pith.science/api/pith-number/NTII7W6JHNZMRAPH4Y2QXZJYPI/events.json","paper":"https://pith.science/paper/NTII7W6J"},"agent_actions":{"view_html":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI","download_json":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI.json","view_paper":"https://pith.science/paper/NTII7W6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10896&json=true","fetch_graph":"https://pith.science/api/pith-number/NTII7W6JHNZMRAPH4Y2QXZJYPI/graph.json","fetch_events":"https://pith.science/api/pith-number/NTII7W6JHNZMRAPH4Y2QXZJYPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI/action/storage_attestation","attest_author":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI/action/author_attestation","sign_citation":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI/action/citation_signature","submit_replication":"https://pith.science/pith/NTII7W6JHNZMRAPH4Y2QXZJYPI/action/replication_record"}},"created_at":"2026-06-10T01:10:46.659227+00:00","updated_at":"2026-06-10T01:10:46.659227+00:00"}