{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZWRX7VFTGJB3Y4NTW7AD7QVTZY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe92a3d4d8cf182042ef7f006ff01c14fa92dbf55bbe82380e82aeb0a831df08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T16:49:42Z","title_canon_sha256":"adc0518ab00064d3ee9fba728745a6e1ed18330032f1ff43cd5223f30e01a1c9"},"schema_version":"1.0","source":{"id":"2508.17083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17083","created_at":"2026-07-05T11:58:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17083v1","created_at":"2026-07-05T11:58:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17083","created_at":"2026-07-05T11:58:09Z"},{"alias_kind":"pith_short_12","alias_value":"ZWRX7VFTGJB3","created_at":"2026-07-05T11:58:09Z"},{"alias_kind":"pith_short_16","alias_value":"ZWRX7VFTGJB3Y4NT","created_at":"2026-07-05T11:58:09Z"},{"alias_kind":"pith_short_8","alias_value":"ZWRX7VFT","created_at":"2026-07-05T11:58:09Z"}],"graph_snapshots":[{"event_id":"sha256:e04369c98b4c0fb2146d89d1bb98594a24b85998f59b5bb7b7e2da9d5a03e7c9","target":"graph","created_at":"2026-07-05T11:58:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.17083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This thesis develops computational methods in similarity-preserving hashing, classification, and cancer genomics. Standard space partitioning-based hashing relies on Binary Search Trees (BSTs), but their exponential growth and sparsity hinder efficiency. To overcome this, we introduce Compressed BST of Inverted hash tables (ComBI), which enables fast approximate nearest-neighbor search with reduced memory. On datasets of up to one billion samples, ComBI achieves 0.90 precision with 4X-296X speed-ups over Multi-Index Hashing, and also outperforms Cellfishing.jl on single-cell RNA-seq searches w","authors_text":"Prashant Gupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T16:49:42Z","title":"Learning ON Large Datasets Using Bit-String Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17083","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5ee5a34c4e4f95d7b11b84a66f5d1fb9aeb5bfd8276dcdb7f770c3330d5f233d","target":"record","created_at":"2026-07-05T11:58:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe92a3d4d8cf182042ef7f006ff01c14fa92dbf55bbe82380e82aeb0a831df08","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T16:49:42Z","title_canon_sha256":"adc0518ab00064d3ee9fba728745a6e1ed18330032f1ff43cd5223f30e01a1c9"},"schema_version":"1.0","source":{"id":"2508.17083","kind":"arxiv","version":1}},"canonical_sha256":"cda37fd4b33243bc71b3b7c03fc2b3ce29a47440c4fd9411639b41279b39e903","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cda37fd4b33243bc71b3b7c03fc2b3ce29a47440c4fd9411639b41279b39e903","first_computed_at":"2026-07-05T11:58:09.250902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:09.250902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TrO73KqI5d/9yXMfE56FjftjO04Yl0J7rsra28I7lX1lrFbtyHmDgc/lIvuutNUVGFS9iiIurQDPbLsZHyZxDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:09.251291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ee5a34c4e4f95d7b11b84a66f5d1fb9aeb5bfd8276dcdb7f770c3330d5f233d","sha256:e04369c98b4c0fb2146d89d1bb98594a24b85998f59b5bb7b7e2da9d5a03e7c9"],"state_sha256":"03b6222d7e3e108f9fa6db98ac9891c10d5fc353b2db30235847c69cf4adf181"}