{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UR73JUF56DOVVF7D2Q6NFVZ3ML","short_pith_number":"pith:UR73JUF5","schema_version":"1.0","canonical_sha256":"a47fb4d0bdf0dd5a97e3d43cd2d73b62d385d8588e696e29a42a5339e0ee4c30","source":{"kind":"arxiv","id":"2607.06133","version":1},"attestation_state":"computed","paper":{"title":"Property-Driven Synthetic Data Engineering for Data-Scarce Software Systems: Reflections from the Breast Cancer Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alberto Zambelli, Andrea Bombarda, Aurora Francesca Zanenga, Claudio Menghi, Marsha Chechik, Rita De Sanctis, Saverio D'Amico","submitted_at":"2026-07-07T10:49:46Z","abstract_excerpt":"Modern software systems increasingly depend on data for analysis, prediction, testing, and decision-making. Yet many important domains, including medicine, safety-critical systems, and regulated industries, lack abundant, shareable, or representative data. Synthetic data generation is often proposed as a remedy, but our experience engineering software for intraoperative radiotherapy (IORT) in breast cancer treatment suggests that synthetic data shifts rather than solves the central engineering problem. The key challenge becomes deciding which properties synthetic data must preserve, how these "},"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":"2607.06133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-07T10:49:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77a7e4208e5fdc95369ae097d8401e247e0ade1d6f109b7800db74d7d08e5826","abstract_canon_sha256":"485d955aa79df258f920503476dc2a672a04df1036f228782128958914658dc3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:58.030562Z","signature_b64":"uJjY+3C3QNx+0/SSjXt4oSBVd7AEgJ4jW5p5TiOIdiPCTz6AJcG7tJ6AG531w2cDX9rULtWRO3IuO94VUEqBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a47fb4d0bdf0dd5a97e3d43cd2d73b62d385d8588e696e29a42a5339e0ee4c30","last_reissued_at":"2026-07-08T01:18:58.030125Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:58.030125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Property-Driven Synthetic Data Engineering for Data-Scarce Software Systems: Reflections from the Breast Cancer Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Alberto Zambelli, Andrea Bombarda, Aurora Francesca Zanenga, Claudio Menghi, Marsha Chechik, Rita De Sanctis, Saverio D'Amico","submitted_at":"2026-07-07T10:49:46Z","abstract_excerpt":"Modern software systems increasingly depend on data for analysis, prediction, testing, and decision-making. Yet many important domains, including medicine, safety-critical systems, and regulated industries, lack abundant, shareable, or representative data. Synthetic data generation is often proposed as a remedy, but our experience engineering software for intraoperative radiotherapy (IORT) in breast cancer treatment suggests that synthetic data shifts rather than solves the central engineering problem. The key challenge becomes deciding which properties synthetic data must preserve, how these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06133","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/2607.06133/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":"2607.06133","created_at":"2026-07-08T01:18:58.030189+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06133v1","created_at":"2026-07-08T01:18:58.030189+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06133","created_at":"2026-07-08T01:18:58.030189+00:00"},{"alias_kind":"pith_short_12","alias_value":"UR73JUF56DOV","created_at":"2026-07-08T01:18:58.030189+00:00"},{"alias_kind":"pith_short_16","alias_value":"UR73JUF56DOVVF7D","created_at":"2026-07-08T01:18:58.030189+00:00"},{"alias_kind":"pith_short_8","alias_value":"UR73JUF5","created_at":"2026-07-08T01:18:58.030189+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/UR73JUF56DOVVF7D2Q6NFVZ3ML","json":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML.json","graph_json":"https://pith.science/api/pith-number/UR73JUF56DOVVF7D2Q6NFVZ3ML/graph.json","events_json":"https://pith.science/api/pith-number/UR73JUF56DOVVF7D2Q6NFVZ3ML/events.json","paper":"https://pith.science/paper/UR73JUF5"},"agent_actions":{"view_html":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML","download_json":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML.json","view_paper":"https://pith.science/paper/UR73JUF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06133&json=true","fetch_graph":"https://pith.science/api/pith-number/UR73JUF56DOVVF7D2Q6NFVZ3ML/graph.json","fetch_events":"https://pith.science/api/pith-number/UR73JUF56DOVVF7D2Q6NFVZ3ML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML/action/storage_attestation","attest_author":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML/action/author_attestation","sign_citation":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML/action/citation_signature","submit_replication":"https://pith.science/pith/UR73JUF56DOVVF7D2Q6NFVZ3ML/action/replication_record"}},"created_at":"2026-07-08T01:18:58.030189+00:00","updated_at":"2026-07-08T01:18:58.030189+00:00"}