{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O2UTVV5YCF7UTOX7LWIAHQR6DL","short_pith_number":"pith:O2UTVV5Y","schema_version":"1.0","canonical_sha256":"76a93ad7b8117f49baff5d9003c23e1aca511f168a115752731894e6b5e867a0","source":{"kind":"arxiv","id":"2605.28034","version":1},"attestation_state":"computed","paper":{"title":"Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Clark Labs Inc, Stanislav Kirdey","submitted_at":"2026-05-27T06:38:41Z","abstract_excerpt":"Clark Hash is a small method for storing neural embeddings in less space. It normalizes each database vector, applies a deterministic sparse signed Johnson-Lindenstrauss projection, clips the result, and stores a fixed-width scalar-quantized code. Queries stay in floating point and are scored against the stored sketches. In the default 384-dimensional sentence-embedding setting, Clark Hash stores a cosine-search vector in 48 bytes instead of 1536 bytes for dense f32 storage. This is 32x smaller. The method does not need a training pass, learned codebooks, rotations, or corpus statistics before"},"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":"2605.28034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T06:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"8ddad28f1f925c1c1b2070bbc810724415ff808e379fe5ba959e21d6037d030e","abstract_canon_sha256":"e4a76064656c343959a4a6f539e989a69cfe584e649632190e94ead31ee5e3d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:56.584893Z","signature_b64":"MeqVy1CKryZSFok+9QU1r0cGR1CmP0h8V0ZYu/5QNZ3vKLARr1/E0pddiyEtcPAHCge5gOJ1CV4RR5l1mHJuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a93ad7b8117f49baff5d9003c23e1aca511f168a115752731894e6b5e867a0","last_reissued_at":"2026-05-28T01:04:56.584442Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:56.584442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clark Hash: Stateless Sparse Johnson-Lindenstrauss Quantization for Neural Embeddings","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Clark Labs Inc, Stanislav Kirdey","submitted_at":"2026-05-27T06:38:41Z","abstract_excerpt":"Clark Hash is a small method for storing neural embeddings in less space. It normalizes each database vector, applies a deterministic sparse signed Johnson-Lindenstrauss projection, clips the result, and stores a fixed-width scalar-quantized code. Queries stay in floating point and are scored against the stored sketches. In the default 384-dimensional sentence-embedding setting, Clark Hash stores a cosine-search vector in 48 bytes instead of 1536 bytes for dense f32 storage. This is 32x smaller. The method does not need a training pass, learned codebooks, rotations, or corpus statistics before"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28034","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/2605.28034/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":"2605.28034","created_at":"2026-05-28T01:04:56.584510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28034v1","created_at":"2026-05-28T01:04:56.584510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28034","created_at":"2026-05-28T01:04:56.584510+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2UTVV5YCF7U","created_at":"2026-05-28T01:04:56.584510+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2UTVV5YCF7UTOX7","created_at":"2026-05-28T01:04:56.584510+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2UTVV5Y","created_at":"2026-05-28T01:04:56.584510+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/O2UTVV5YCF7UTOX7LWIAHQR6DL","json":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL.json","graph_json":"https://pith.science/api/pith-number/O2UTVV5YCF7UTOX7LWIAHQR6DL/graph.json","events_json":"https://pith.science/api/pith-number/O2UTVV5YCF7UTOX7LWIAHQR6DL/events.json","paper":"https://pith.science/paper/O2UTVV5Y"},"agent_actions":{"view_html":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL","download_json":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL.json","view_paper":"https://pith.science/paper/O2UTVV5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28034&json=true","fetch_graph":"https://pith.science/api/pith-number/O2UTVV5YCF7UTOX7LWIAHQR6DL/graph.json","fetch_events":"https://pith.science/api/pith-number/O2UTVV5YCF7UTOX7LWIAHQR6DL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL/action/storage_attestation","attest_author":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL/action/author_attestation","sign_citation":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL/action/citation_signature","submit_replication":"https://pith.science/pith/O2UTVV5YCF7UTOX7LWIAHQR6DL/action/replication_record"}},"created_at":"2026-05-28T01:04:56.584510+00:00","updated_at":"2026-05-28T01:04:56.584510+00:00"}