{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XT3OEG2FEBJ6MBF4WYKFRD23AM","short_pith_number":"pith:XT3OEG2F","canonical_record":{"source":{"id":"2508.19807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-27T11:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2816f8e957255e949f0b682155ab965172007b9db8e7f700f012ef3557c1d2a3","abstract_canon_sha256":"db6d80c22cdae1e8b2f749156dca0cee46b217c2f5641dfcbbd9ecc91ac09f83"},"schema_version":"1.0"},"canonical_sha256":"bcf6e21b452053e604bcb614588f5b0307d23b8de8e502090a166fed6e8bb697","source":{"kind":"arxiv","id":"2508.19807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19807","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19807v1","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19807","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"XT3OEG2FEBJ6","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"XT3OEG2FEBJ6MBF4","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"XT3OEG2F","created_at":"2026-07-05T12:00:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XT3OEG2FEBJ6MBF4WYKFRD23AM","target":"record","payload":{"canonical_record":{"source":{"id":"2508.19807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-27T11:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2816f8e957255e949f0b682155ab965172007b9db8e7f700f012ef3557c1d2a3","abstract_canon_sha256":"db6d80c22cdae1e8b2f749156dca0cee46b217c2f5641dfcbbd9ecc91ac09f83"},"schema_version":"1.0"},"canonical_sha256":"bcf6e21b452053e604bcb614588f5b0307d23b8de8e502090a166fed6e8bb697","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:18.087747Z","signature_b64":"T0o3oHZfTpWEagZSheMlYstXdyKOr88BKzVn4Ewr6PgwQIf4QIfzBoul+fa+c9CUYjUNph2A92m5tNS9tvcgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcf6e21b452053e604bcb614588f5b0307d23b8de8e502090a166fed6e8bb697","last_reissued_at":"2026-07-05T12:00:18.087355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:18.087355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.19807","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSM27X7hyQT2bdNGx030mHafQBq01/iE4vQ+ZekXjhflckVp5JtE1fcw26rjPiuchyue7/FQr/W27Ij0twfJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:51.918830Z"},"content_sha256":"d7f23c9e02ca6c08e5e538b408f01b920c925f22099fe85a23f5cd7195d1fef2","schema_version":"1.0","event_id":"sha256:d7f23c9e02ca6c08e5e538b408f01b920c925f22099fe85a23f5cd7195d1fef2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XT3OEG2FEBJ6MBF4WYKFRD23AM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bootstrapping Learned Cost Models with Synthetic SQL Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Andrea Giovannini, Christoph Miksovic, Francesco Fusco, Ioana Giurgiu, Michael Nidd, Thomas Gschwind","submitted_at":"2025-08-27T11:50:42Z","abstract_excerpt":"Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and performance. Recent advances in learned cost models have shown that when enough diverse SQL queries are available, one can effectively and efficiently predict the cost of running a given query against a specific database engine. In this paper, we describe our experience in exploiting modern synthetic data generation techniques, inspired by the generative AI and LLM community, to create high-quality datasets enabling the effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19807","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/2508.19807/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":"2026-07-05T12:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"19bSSEDF/kFl5H37UmkqMXq7I/dNGhqnDYwC040Mvx063p4Mhqm+a+OJYu3P0cHCLoI+Ldz2FdoCfQfi3N1kBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:51.919552Z"},"content_sha256":"072ee380386c15510c177d3371a2d05ac7636e2a75dda0e373e80fb8df6e1d98","schema_version":"1.0","event_id":"sha256:072ee380386c15510c177d3371a2d05ac7636e2a75dda0e373e80fb8df6e1d98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/bundle.json","state_url":"https://pith.science/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/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":"2026-07-09T05:56:51Z","links":{"resolver":"https://pith.science/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM","bundle":"https://pith.science/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/bundle.json","state":"https://pith.science/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XT3OEG2FEBJ6MBF4WYKFRD23AM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XT3OEG2FEBJ6MBF4WYKFRD23AM","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":"db6d80c22cdae1e8b2f749156dca0cee46b217c2f5641dfcbbd9ecc91ac09f83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-27T11:50:42Z","title_canon_sha256":"2816f8e957255e949f0b682155ab965172007b9db8e7f700f012ef3557c1d2a3"},"schema_version":"1.0","source":{"id":"2508.19807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19807","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19807v1","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19807","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"XT3OEG2FEBJ6","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"XT3OEG2FEBJ6MBF4","created_at":"2026-07-05T12:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"XT3OEG2F","created_at":"2026-07-05T12:00:18Z"}],"graph_snapshots":[{"event_id":"sha256:072ee380386c15510c177d3371a2d05ac7636e2a75dda0e373e80fb8df6e1d98","target":"graph","created_at":"2026-07-05T12:00:18Z","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/2508.19807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and performance. Recent advances in learned cost models have shown that when enough diverse SQL queries are available, one can effectively and efficiently predict the cost of running a given query against a specific database engine. In this paper, we describe our experience in exploiting modern synthetic data generation techniques, inspired by the generative AI and LLM community, to create high-quality datasets enabling the effect","authors_text":"Andrea Giovannini, Christoph Miksovic, Francesco Fusco, Ioana Giurgiu, Michael Nidd, Thomas Gschwind","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-27T11:50:42Z","title":"Bootstrapping Learned Cost Models with Synthetic SQL Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19807","kind":"arxiv","version":1},"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:d7f23c9e02ca6c08e5e538b408f01b920c925f22099fe85a23f5cd7195d1fef2","target":"record","created_at":"2026-07-05T12:00:18Z","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":"db6d80c22cdae1e8b2f749156dca0cee46b217c2f5641dfcbbd9ecc91ac09f83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-08-27T11:50:42Z","title_canon_sha256":"2816f8e957255e949f0b682155ab965172007b9db8e7f700f012ef3557c1d2a3"},"schema_version":"1.0","source":{"id":"2508.19807","kind":"arxiv","version":1}},"canonical_sha256":"bcf6e21b452053e604bcb614588f5b0307d23b8de8e502090a166fed6e8bb697","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcf6e21b452053e604bcb614588f5b0307d23b8de8e502090a166fed6e8bb697","first_computed_at":"2026-07-05T12:00:18.087355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:18.087355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T0o3oHZfTpWEagZSheMlYstXdyKOr88BKzVn4Ewr6PgwQIf4QIfzBoul+fa+c9CUYjUNph2A92m5tNS9tvcgDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:18.087747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7f23c9e02ca6c08e5e538b408f01b920c925f22099fe85a23f5cd7195d1fef2","sha256:072ee380386c15510c177d3371a2d05ac7636e2a75dda0e373e80fb8df6e1d98"],"state_sha256":"2a540cef7eaded72f01daa956a57400c04824119ec73de13e81351f781f80b44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZv27Q7NlKBPA8cR9H2mpSjAQAAbHsR4t09gTkJR0y45qwefJOA18GXTGU9z2BX98WxSG/zoic1qzpg4OSAiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:51.923519Z","bundle_sha256":"efe50dd7e5e49dfef956991a822890de1cafea5d8d99dbe765de2207df4f7529"}}