{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EG2K2LUTGVDNNI4PGZIPYGIXVV","short_pith_number":"pith:EG2K2LUT","schema_version":"1.0","canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","source":{"kind":"arxiv","id":"2505.05122","version":2},"attestation_state":"computed","paper":{"title":"Text2Cypher: Data Pruning using Hard Example Selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Makbule Gulcin Ozsoy","submitted_at":"2025-05-08T10:51:13Z","abstract_excerpt":"Database query languages such as SQL for relational databases and Cypher for graph databases have been widely adopted. Recent advancements in large language models (LLMs) enable natural language interactions with databases through models like Text2SQL and Text2Cypher. Fine-tuning these models typically requires large, diverse datasets containing non-trivial examples. However, as dataset size increases, the cost of fine-tuning also rises. This makes smaller, high-quality datasets essential for reducing costs for the same or better performance. In this paper, we propose five hard-example selecti"},"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":"2505.05122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-08T10:51:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb4f7a17ea0385616fdc8a61f3dc0e71c5bbbe0525489f90b4d482a1d4e07ff5","abstract_canon_sha256":"94faabb99c4928df547943ac2d095d90c02dc0e51506fea1b20955b093e6d156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:03.899376Z","signature_b64":"IccnfF0Z9seryizPA+vnl2BkWXa+TK0MvkSGe3z6jPNlNeUmOcm8av3m5M+5YbbQg+G5rBlSpCiBTPofD8b3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","last_reissued_at":"2026-07-05T12:05:03.898857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:03.898857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2Cypher: Data Pruning using Hard Example Selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Makbule Gulcin Ozsoy","submitted_at":"2025-05-08T10:51:13Z","abstract_excerpt":"Database query languages such as SQL for relational databases and Cypher for graph databases have been widely adopted. Recent advancements in large language models (LLMs) enable natural language interactions with databases through models like Text2SQL and Text2Cypher. Fine-tuning these models typically requires large, diverse datasets containing non-trivial examples. However, as dataset size increases, the cost of fine-tuning also rises. This makes smaller, high-quality datasets essential for reducing costs for the same or better performance. In this paper, we propose five hard-example selecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05122","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/2505.05122/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":"2505.05122","created_at":"2026-07-05T12:05:03.898921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05122v2","created_at":"2026-07-05T12:05:03.898921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05122","created_at":"2026-07-05T12:05:03.898921+00:00"},{"alias_kind":"pith_short_12","alias_value":"EG2K2LUTGVDN","created_at":"2026-07-05T12:05:03.898921+00:00"},{"alias_kind":"pith_short_16","alias_value":"EG2K2LUTGVDNNI4P","created_at":"2026-07-05T12:05:03.898921+00:00"},{"alias_kind":"pith_short_8","alias_value":"EG2K2LUT","created_at":"2026-07-05T12:05:03.898921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21575","citing_title":"STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV","json":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV.json","graph_json":"https://pith.science/api/pith-number/EG2K2LUTGVDNNI4PGZIPYGIXVV/graph.json","events_json":"https://pith.science/api/pith-number/EG2K2LUTGVDNNI4PGZIPYGIXVV/events.json","paper":"https://pith.science/paper/EG2K2LUT"},"agent_actions":{"view_html":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV","download_json":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV.json","view_paper":"https://pith.science/paper/EG2K2LUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05122&json=true","fetch_graph":"https://pith.science/api/pith-number/EG2K2LUTGVDNNI4PGZIPYGIXVV/graph.json","fetch_events":"https://pith.science/api/pith-number/EG2K2LUTGVDNNI4PGZIPYGIXVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/action/storage_attestation","attest_author":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/action/author_attestation","sign_citation":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/action/citation_signature","submit_replication":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/action/replication_record"}},"created_at":"2026-07-05T12:05:03.898921+00:00","updated_at":"2026-07-05T12:05:03.898921+00:00"}