{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P52I7TCYLL6O22ADDYCXPP2Z2W","short_pith_number":"pith:P52I7TCY","schema_version":"1.0","canonical_sha256":"7f748fcc585afced68031e0577bf59d58154ebb67b825616d2f02e6d84feec64","source":{"kind":"arxiv","id":"2606.04610","version":1},"attestation_state":"computed","paper":{"title":"Selectivity Estimation for Semantic Filters on Image Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Carsten Binnig, Gabriele Sanmartino, Matthias Urban, Paolo Papotti, Vu Huy Nguyen","submitted_at":"2026-06-03T08:48:21Z","abstract_excerpt":"Semantic data systems integrate Large Language Models (LLMs) and Vision-Language Models (VLMs) directly into database query execution, enabling expressive queries on multi-modal data. However, optimizing these queries requires accurate selectivity estimates to determine the most efficient operator execution order. Contemporary systems rely on online sample-based profiling, a process that incurs severe latency overheads and struggles with low-selectivity queries. In this paper, we introduce Semantic Histograms, a novel selectivity estimator for semantic filters on image data that leverages shar"},"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":"2606.04610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-03T08:48:21Z","cross_cats_sorted":[],"title_canon_sha256":"d64e8820d91416ced926d92ced45783688e9285a0d31f893d3567e9a11291b75","abstract_canon_sha256":"0637a98771fdc5882e7b56813acbe7014c17de39d8605fadac85999da3b496d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:21.220560Z","signature_b64":"lt0eVKAyG0hn9SeAgK7osrXm/dy0A1cAzAilc3H11DKVdrk0IszwZWWyP8iJq2ZRsSaxDFtygyufs6F3/gUfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f748fcc585afced68031e0577bf59d58154ebb67b825616d2f02e6d84feec64","last_reissued_at":"2026-06-04T01:09:21.219991Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:21.219991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selectivity Estimation for Semantic Filters on Image Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Carsten Binnig, Gabriele Sanmartino, Matthias Urban, Paolo Papotti, Vu Huy Nguyen","submitted_at":"2026-06-03T08:48:21Z","abstract_excerpt":"Semantic data systems integrate Large Language Models (LLMs) and Vision-Language Models (VLMs) directly into database query execution, enabling expressive queries on multi-modal data. However, optimizing these queries requires accurate selectivity estimates to determine the most efficient operator execution order. Contemporary systems rely on online sample-based profiling, a process that incurs severe latency overheads and struggles with low-selectivity queries. In this paper, we introduce Semantic Histograms, a novel selectivity estimator for semantic filters on image data that leverages shar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04610","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/2606.04610/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":"2606.04610","created_at":"2026-06-04T01:09:21.220071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04610v1","created_at":"2026-06-04T01:09:21.220071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04610","created_at":"2026-06-04T01:09:21.220071+00:00"},{"alias_kind":"pith_short_12","alias_value":"P52I7TCYLL6O","created_at":"2026-06-04T01:09:21.220071+00:00"},{"alias_kind":"pith_short_16","alias_value":"P52I7TCYLL6O22AD","created_at":"2026-06-04T01:09:21.220071+00:00"},{"alias_kind":"pith_short_8","alias_value":"P52I7TCY","created_at":"2026-06-04T01:09:21.220071+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/P52I7TCYLL6O22ADDYCXPP2Z2W","json":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W.json","graph_json":"https://pith.science/api/pith-number/P52I7TCYLL6O22ADDYCXPP2Z2W/graph.json","events_json":"https://pith.science/api/pith-number/P52I7TCYLL6O22ADDYCXPP2Z2W/events.json","paper":"https://pith.science/paper/P52I7TCY"},"agent_actions":{"view_html":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W","download_json":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W.json","view_paper":"https://pith.science/paper/P52I7TCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04610&json=true","fetch_graph":"https://pith.science/api/pith-number/P52I7TCYLL6O22ADDYCXPP2Z2W/graph.json","fetch_events":"https://pith.science/api/pith-number/P52I7TCYLL6O22ADDYCXPP2Z2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W/action/storage_attestation","attest_author":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W/action/author_attestation","sign_citation":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W/action/citation_signature","submit_replication":"https://pith.science/pith/P52I7TCYLL6O22ADDYCXPP2Z2W/action/replication_record"}},"created_at":"2026-06-04T01:09:21.220071+00:00","updated_at":"2026-06-04T01:09:21.220071+00:00"}