{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ADPTDLPT2ZUJEQSNN7STO6KKUE","short_pith_number":"pith:ADPTDLPT","schema_version":"1.0","canonical_sha256":"00df31adf3d66892424d6fe537794aa135ddd1b364473d9ca3e513bb20c4aaaf","source":{"kind":"arxiv","id":"2505.19001","version":2},"attestation_state":"computed","paper":{"title":"DARTH: Declarative Recall Through Early Termination for Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Manos Chatzakis, Themis Palpanas, Yannis Papakonstantinou","submitted_at":"2025-05-25T06:45:53Z","abstract_excerpt":"Approximate Nearest Neighbor Search (ANNS) presents an inherent tradeoff between performance and recall (i.e., result quality). Each ANNS algorithm provides its own algorithm-dependent parameters to allow applications to influence the recall/performance tradeoff of their searches. This situation is doubly problematic. First, the application developers have to experiment with these algorithm-dependent parameters to fine-tune the parameters that produce the desired recall for each use case. This process usually takes a lot of effort. Even worse, the chosen parameters may produce good recall for "},"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":"2505.19001","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-25T06:45:53Z","cross_cats_sorted":[],"title_canon_sha256":"a01049c1200307d1cdb90f2b3dbfdfd146270a291c34dac694d360285481d6e3","abstract_canon_sha256":"c73dc9ebc022f74986183cccda1e3a7a77c1eeddb4cacbd4aa682d4922720041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:19.561143Z","signature_b64":"ORg5lJZ/+w0GQr5Lk4ga/C8GfGE0NtM5ZqtV1PEb6mYAKoz5lqM54V6OITTwr8A5XAYIfC5yA7sAitdxVldyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00df31adf3d66892424d6fe537794aa135ddd1b364473d9ca3e513bb20c4aaaf","last_reissued_at":"2026-07-05T11:55:19.560730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:19.560730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARTH: Declarative Recall Through Early Termination for Approximate Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Manos Chatzakis, Themis Palpanas, Yannis Papakonstantinou","submitted_at":"2025-05-25T06:45:53Z","abstract_excerpt":"Approximate Nearest Neighbor Search (ANNS) presents an inherent tradeoff between performance and recall (i.e., result quality). Each ANNS algorithm provides its own algorithm-dependent parameters to allow applications to influence the recall/performance tradeoff of their searches. This situation is doubly problematic. First, the application developers have to experiment with these algorithm-dependent parameters to fine-tune the parameters that produce the desired recall for each use case. This process usually takes a lot of effort. Even worse, the chosen parameters may produce good recall for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19001","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/2505.19001/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":"2505.19001","created_at":"2026-07-05T11:55:19.560783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19001v2","created_at":"2026-07-05T11:55:19.560783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19001","created_at":"2026-07-05T11:55:19.560783+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADPTDLPT2ZUJ","created_at":"2026-07-05T11:55:19.560783+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADPTDLPT2ZUJEQSN","created_at":"2026-07-05T11:55:19.560783+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADPTDLPT","created_at":"2026-07-05T11:55:19.560783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10090","citing_title":"CCD-Level and Load-Aware Thread Orchestration for In-Memory Vector ANNS on Multi-Core CPUs","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE","json":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE.json","graph_json":"https://pith.science/api/pith-number/ADPTDLPT2ZUJEQSNN7STO6KKUE/graph.json","events_json":"https://pith.science/api/pith-number/ADPTDLPT2ZUJEQSNN7STO6KKUE/events.json","paper":"https://pith.science/paper/ADPTDLPT"},"agent_actions":{"view_html":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE","download_json":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE.json","view_paper":"https://pith.science/paper/ADPTDLPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19001&json=true","fetch_graph":"https://pith.science/api/pith-number/ADPTDLPT2ZUJEQSNN7STO6KKUE/graph.json","fetch_events":"https://pith.science/api/pith-number/ADPTDLPT2ZUJEQSNN7STO6KKUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE/action/storage_attestation","attest_author":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE/action/author_attestation","sign_citation":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE/action/citation_signature","submit_replication":"https://pith.science/pith/ADPTDLPT2ZUJEQSNN7STO6KKUE/action/replication_record"}},"created_at":"2026-07-05T11:55:19.560783+00:00","updated_at":"2026-07-05T11:55:19.560783+00:00"}