{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XXPRDDIQRXQ3WI7XODVT2MAHD5","short_pith_number":"pith:XXPRDDIQ","schema_version":"1.0","canonical_sha256":"bddf118d108de1bb23f770eb3d30071f426c870440abe051e19f738b1c4431b8","source":{"kind":"arxiv","id":"2208.08910","version":2},"attestation_state":"computed","paper":{"title":"Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jaroslav O\\v{l}ha, Martin Gendiar, Matej Antol, Ter\\'ezia Slanin\\'akov\\'a, Vlastislav Dohnal","submitted_at":"2022-08-18T15:22:42Z","abstract_excerpt":"Despite the constant evolution of similarity searching research, it continues to face the same challenges stemming from the complexity of the data, such as the curse of dimensionality and computationally expensive distance functions. Various machine learning techniques have proven capable of replacing elaborate mathematical models with combinations of simple linear functions, often gaining speed and simplicity at the cost of formal guarantees of accuracy and correctness of querying.\n  The authors explore the potential of this research trend by presenting a lightweight solution for the complex "},"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":"2208.08910","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-08-18T15:22:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb7ebd7d0d5fe26ed8a9b09c15b7a93ffd504940288d4d44285c63f165422e2d","abstract_canon_sha256":"d26ce2437c62d094d294c4f82c6ff54d4716ea71ad979c51bcabe46ceb75d39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:39.094902Z","signature_b64":"SvTm1mTooX2PIZ/a0l23uhe0ecBTg+8Cqn8x/6mlTM5UP3t0B47FAG27UKXvUshnEmAVtA6B4fI6nYyYkWpZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bddf118d108de1bb23f770eb3d30071f426c870440abe051e19f738b1c4431b8","last_reissued_at":"2026-07-05T05:03:39.094568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:39.094568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Indexing in Proteins: Extended Work on Substituting Complex Distance Calculations with Embedding and Clustering Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jaroslav O\\v{l}ha, Martin Gendiar, Matej Antol, Ter\\'ezia Slanin\\'akov\\'a, Vlastislav Dohnal","submitted_at":"2022-08-18T15:22:42Z","abstract_excerpt":"Despite the constant evolution of similarity searching research, it continues to face the same challenges stemming from the complexity of the data, such as the curse of dimensionality and computationally expensive distance functions. Various machine learning techniques have proven capable of replacing elaborate mathematical models with combinations of simple linear functions, often gaining speed and simplicity at the cost of formal guarantees of accuracy and correctness of querying.\n  The authors explore the potential of this research trend by presenting a lightweight solution for the complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08910","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/2208.08910/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":"2208.08910","created_at":"2026-07-05T05:03:39.094624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08910v2","created_at":"2026-07-05T05:03:39.094624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08910","created_at":"2026-07-05T05:03:39.094624+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXPRDDIQRXQ3","created_at":"2026-07-05T05:03:39.094624+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXPRDDIQRXQ3WI7X","created_at":"2026-07-05T05:03:39.094624+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXPRDDIQ","created_at":"2026-07-05T05:03:39.094624+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/XXPRDDIQRXQ3WI7XODVT2MAHD5","json":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5.json","graph_json":"https://pith.science/api/pith-number/XXPRDDIQRXQ3WI7XODVT2MAHD5/graph.json","events_json":"https://pith.science/api/pith-number/XXPRDDIQRXQ3WI7XODVT2MAHD5/events.json","paper":"https://pith.science/paper/XXPRDDIQ"},"agent_actions":{"view_html":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5","download_json":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5.json","view_paper":"https://pith.science/paper/XXPRDDIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08910&json=true","fetch_graph":"https://pith.science/api/pith-number/XXPRDDIQRXQ3WI7XODVT2MAHD5/graph.json","fetch_events":"https://pith.science/api/pith-number/XXPRDDIQRXQ3WI7XODVT2MAHD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5/action/storage_attestation","attest_author":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5/action/author_attestation","sign_citation":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5/action/citation_signature","submit_replication":"https://pith.science/pith/XXPRDDIQRXQ3WI7XODVT2MAHD5/action/replication_record"}},"created_at":"2026-07-05T05:03:39.094624+00:00","updated_at":"2026-07-05T05:03:39.094624+00:00"}