{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EG2K2LUTGVDNNI4PGZIPYGIXVV","short_pith_number":"pith:EG2K2LUT","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"},"canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","source":{"kind":"arxiv","id":"2505.05122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05122","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05122v2","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05122","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"EG2K2LUTGVDN","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"EG2K2LUTGVDNNI4P","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"EG2K2LUT","created_at":"2026-07-05T12:05:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EG2K2LUTGVDNNI4PGZIPYGIXVV","target":"record","payload":{"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"},"canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","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"},"source_kind":"arxiv","source_id":"2505.05122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1kIKgX6TLe7DW+697S+9i6vO1YAWTTVGAnqW/tdgfccGfa0oUQKsOyj29e17iAWYRS1eWYp3+9vAh92JnJ4nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:50:46.431930Z"},"content_sha256":"d294e83dba7a9ebe21c286dd3ef01939cd8670a4f6e432ea43bcf38a6dd98bcb","schema_version":"1.0","event_id":"sha256:d294e83dba7a9ebe21c286dd3ef01939cd8670a4f6e432ea43bcf38a6dd98bcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EG2K2LUTGVDNNI4PGZIPYGIXVV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jghJVkH8JY5qcVMZIsH+4Svjj14zw/ZE/Djo7WTv6Q9ouNRn+/CXG1f9h26PzRpKTHwSD6mjk/DunXbOeY7EDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:50:46.432508Z"},"content_sha256":"b8478958663ed8e68484d3fd868d79f165e9043d7a92c1b3f5869b1b1de03c7c","schema_version":"1.0","event_id":"sha256:b8478958663ed8e68484d3fd868d79f165e9043d7a92c1b3f5869b1b1de03c7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/bundle.json","state_url":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T11:50:46Z","links":{"resolver":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV","bundle":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/bundle.json","state":"https://pith.science/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EG2K2LUTGVDNNI4PGZIPYGIXVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EG2K2LUTGVDNNI4PGZIPYGIXVV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"94faabb99c4928df547943ac2d095d90c02dc0e51506fea1b20955b093e6d156","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-08T10:51:13Z","title_canon_sha256":"cb4f7a17ea0385616fdc8a61f3dc0e71c5bbbe0525489f90b4d482a1d4e07ff5"},"schema_version":"1.0","source":{"id":"2505.05122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05122","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05122v2","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05122","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_12","alias_value":"EG2K2LUTGVDN","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_16","alias_value":"EG2K2LUTGVDNNI4P","created_at":"2026-07-05T12:05:03Z"},{"alias_kind":"pith_short_8","alias_value":"EG2K2LUT","created_at":"2026-07-05T12:05:03Z"}],"graph_snapshots":[{"event_id":"sha256:b8478958663ed8e68484d3fd868d79f165e9043d7a92c1b3f5869b1b1de03c7c","target":"graph","created_at":"2026-07-05T12:05:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.05122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Makbule Gulcin Ozsoy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-08T10:51:13Z","title":"Text2Cypher: Data Pruning using Hard Example Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05122","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d294e83dba7a9ebe21c286dd3ef01939cd8670a4f6e432ea43bcf38a6dd98bcb","target":"record","created_at":"2026-07-05T12:05:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"94faabb99c4928df547943ac2d095d90c02dc0e51506fea1b20955b093e6d156","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-08T10:51:13Z","title_canon_sha256":"cb4f7a17ea0385616fdc8a61f3dc0e71c5bbbe0525489f90b4d482a1d4e07ff5"},"schema_version":"1.0","source":{"id":"2505.05122","kind":"arxiv","version":2}},"canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21b4ad2e933546d6a38f3650fc1917ad43c97ce0610691fe3d8412e633da2349","first_computed_at":"2026-07-05T12:05:03.898857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:03.898857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IccnfF0Z9seryizPA+vnl2BkWXa+TK0MvkSGe3z6jPNlNeUmOcm8av3m5M+5YbbQg+G5rBlSpCiBTPofD8b3BA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:03.899376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d294e83dba7a9ebe21c286dd3ef01939cd8670a4f6e432ea43bcf38a6dd98bcb","sha256:b8478958663ed8e68484d3fd868d79f165e9043d7a92c1b3f5869b1b1de03c7c"],"state_sha256":"fad2244a4bac691ae01cf6212d996188c23c531cc83a9d38bf3718a8d8dbe4c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I21Ug5qwxJ0cgclA050xBuXJLt2Ixq4zYRDIPvZed+FWxy8pOxzonqMVJJ90cYz5Cqmi1FUsevmo0cvXny6yBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:50:46.438126Z","bundle_sha256":"cf287447cf34f3df785f95340d0e713a915e92f99165abe9223298dbef67488e"}}