{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UPX63FWDF6LTOSGIOU6WODLQY4","short_pith_number":"pith:UPX63FWD","schema_version":"1.0","canonical_sha256":"a3efed96c32f973748c8753d670d70c730f02ecf91945ecf5bf9b46d6a046856","source":{"kind":"arxiv","id":"2509.00303","version":3},"attestation_state":"computed","paper":{"title":"Access Paths for Efficient Ordering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Amr El Abbadi, Anupam Datta, Dimitris Tsirogiannis, Divyakant Agrawal, Fuheng Zhao, Jiayue Chen, Paritosh Aggarwal, Sohaib, Tahseen Rabbani, Yiming Pan","submitted_at":"2025-08-30T01:44:36Z","abstract_excerpt":"In this work, we present the \\texttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical implementations. First, we propose several improvements to existing semantic sorting algorithms and introduce a semantic-aware external merge sort algorithm. Our extensive evaluation reveals that no single implementation offers universal optimality on all datasets. From our evaluations, we observe a general test-time scaling relationship between sorting cost and the ordering quality for comparison-based algorithms. Building on these insights, we design a "},"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":"2509.00303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-30T01:44:36Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"110126384606aa09a170f53540e1d4c5bac620f099790374c3100e1a5e853bf7","abstract_canon_sha256":"b8fff4542e00a98650b7e3ae0fede4366fa102aa29d6534b9da0b5ff80ebd79a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:16.375492Z","signature_b64":"WzjcDUg3u50zusffNjClBgsZlt6QVHpONTQsOLia5R8AmqHco/Pa5rjOpBKaPFUA9xMbSRZGT+n6BDazvLaYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3efed96c32f973748c8753d670d70c730f02ecf91945ecf5bf9b46d6a046856","last_reissued_at":"2026-05-21T01:04:16.374543Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:16.374543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Access Paths for Efficient Ordering with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Amr El Abbadi, Anupam Datta, Dimitris Tsirogiannis, Divyakant Agrawal, Fuheng Zhao, Jiayue Chen, Paritosh Aggarwal, Sohaib, Tahseen Rabbani, Yiming Pan","submitted_at":"2025-08-30T01:44:36Z","abstract_excerpt":"In this work, we present the \\texttt{LLM ORDER BY} semantic operator as a logical abstraction and conduct a systematic study of its physical implementations. First, we propose several improvements to existing semantic sorting algorithms and introduce a semantic-aware external merge sort algorithm. Our extensive evaluation reveals that no single implementation offers universal optimality on all datasets. From our evaluations, we observe a general test-time scaling relationship between sorting cost and the ordering quality for comparison-based algorithms. Building on these insights, we design a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00303","kind":"arxiv","version":3},"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/2509.00303/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":"2509.00303","created_at":"2026-05-21T01:04:16.374677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00303v3","created_at":"2026-05-21T01:04:16.374677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00303","created_at":"2026-05-21T01:04:16.374677+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPX63FWDF6LT","created_at":"2026-05-21T01:04:16.374677+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPX63FWDF6LTOSGI","created_at":"2026-05-21T01:04:16.374677+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPX63FWD","created_at":"2026-05-21T01:04:16.374677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17632","citing_title":"Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4","json":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4.json","graph_json":"https://pith.science/api/pith-number/UPX63FWDF6LTOSGIOU6WODLQY4/graph.json","events_json":"https://pith.science/api/pith-number/UPX63FWDF6LTOSGIOU6WODLQY4/events.json","paper":"https://pith.science/paper/UPX63FWD"},"agent_actions":{"view_html":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4","download_json":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4.json","view_paper":"https://pith.science/paper/UPX63FWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00303&json=true","fetch_graph":"https://pith.science/api/pith-number/UPX63FWDF6LTOSGIOU6WODLQY4/graph.json","fetch_events":"https://pith.science/api/pith-number/UPX63FWDF6LTOSGIOU6WODLQY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4/action/storage_attestation","attest_author":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4/action/author_attestation","sign_citation":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4/action/citation_signature","submit_replication":"https://pith.science/pith/UPX63FWDF6LTOSGIOU6WODLQY4/action/replication_record"}},"created_at":"2026-05-21T01:04:16.374677+00:00","updated_at":"2026-05-21T01:04:16.374677+00:00"}