{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PESX7YAZNUTAEMIOME5L5ZU2GD","short_pith_number":"pith:PESX7YAZ","schema_version":"1.0","canonical_sha256":"79257fe0196d2602310e613abee69a30e810de3b37cfa51cd594745c69c64aee","source":{"kind":"arxiv","id":"2306.14809","version":2},"attestation_state":"computed","paper":{"title":"Tanimoto Random Features for Scalable Molecular Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato, Sergio Bacallado, Sukriti Singh","submitted_at":"2023-06-26T16:11:11Z","abstract_excerpt":"The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kernel. While many kernel methods can be accelerated using random feature approximations, at present there is a lack of such approximations for the Tanimoto kernel. In this paper we propose two kinds of novel random features to allow this kernel to scale to large datasets, and in the process discover a novel extension of the kernel to real-valued vectors. We theoretically characterize these random features, and provide er"},"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":"2306.14809","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T16:11:11Z","cross_cats_sorted":[],"title_canon_sha256":"88e46a05ddc680e052c8898aefc1184345fec5a94ebb33f887d4e520abfd650d","abstract_canon_sha256":"1bea7468c1139e31f71b671d112864eb644d0ef03f2fadea14d270a81657f7f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:17.285052Z","signature_b64":"gWLC1/hztI57SRCNw6f8x+8BhQ+TY82Y0P8MadnoZy7SAIytp4p2L0UzSwHkxqAR2NepPuSrsy37NcQMSrwWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79257fe0196d2602310e613abee69a30e810de3b37cfa51cd594745c69c64aee","last_reissued_at":"2026-07-05T07:12:17.284586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:17.284586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tanimoto Random Features for Scalable Molecular Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin Tripp, Jos\\'e Miguel Hern\\'andez-Lobato, Sergio Bacallado, Sukriti Singh","submitted_at":"2023-06-26T16:11:11Z","abstract_excerpt":"The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kernel. While many kernel methods can be accelerated using random feature approximations, at present there is a lack of such approximations for the Tanimoto kernel. In this paper we propose two kinds of novel random features to allow this kernel to scale to large datasets, and in the process discover a novel extension of the kernel to real-valued vectors. We theoretically characterize these random features, and provide er"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14809","kind":"arxiv","version":2},"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/2306.14809/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":"2306.14809","created_at":"2026-07-05T07:12:17.284645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14809v2","created_at":"2026-07-05T07:12:17.284645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14809","created_at":"2026-07-05T07:12:17.284645+00:00"},{"alias_kind":"pith_short_12","alias_value":"PESX7YAZNUTA","created_at":"2026-07-05T07:12:17.284645+00:00"},{"alias_kind":"pith_short_16","alias_value":"PESX7YAZNUTAEMIO","created_at":"2026-07-05T07:12:17.284645+00:00"},{"alias_kind":"pith_short_8","alias_value":"PESX7YAZ","created_at":"2026-07-05T07:12:17.284645+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/PESX7YAZNUTAEMIOME5L5ZU2GD","json":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD.json","graph_json":"https://pith.science/api/pith-number/PESX7YAZNUTAEMIOME5L5ZU2GD/graph.json","events_json":"https://pith.science/api/pith-number/PESX7YAZNUTAEMIOME5L5ZU2GD/events.json","paper":"https://pith.science/paper/PESX7YAZ"},"agent_actions":{"view_html":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD","download_json":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD.json","view_paper":"https://pith.science/paper/PESX7YAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14809&json=true","fetch_graph":"https://pith.science/api/pith-number/PESX7YAZNUTAEMIOME5L5ZU2GD/graph.json","fetch_events":"https://pith.science/api/pith-number/PESX7YAZNUTAEMIOME5L5ZU2GD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD/action/storage_attestation","attest_author":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD/action/author_attestation","sign_citation":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD/action/citation_signature","submit_replication":"https://pith.science/pith/PESX7YAZNUTAEMIOME5L5ZU2GD/action/replication_record"}},"created_at":"2026-07-05T07:12:17.284645+00:00","updated_at":"2026-07-05T07:12:17.284645+00:00"}