{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WLSGZL6RGW72IA5QUQKWCMV3OF","short_pith_number":"pith:WLSGZL6R","schema_version":"1.0","canonical_sha256":"b2e46cafd135bfa403b0a4156132bb71417e5770a284650f48eac5eddc03b894","source":{"kind":"arxiv","id":"2406.13130","version":1},"attestation_state":"computed","paper":{"title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi-Hua Wang, Guang Cheng, Joshua Mabry, Yu Xia","submitted_at":"2024-06-19T00:47:38Z","abstract_excerpt":"The evaluation of synthetic data generation is crucial, especially in the retail sector where data accuracy is paramount. This paper introduces a comprehensive framework for assessing synthetic retail data, focusing on fidelity, utility, and privacy. Our approach differentiates between continuous and discrete data attributes, providing precise evaluation criteria. Fidelity is measured through stability and generalizability. Stability ensures synthetic data accurately replicates known data distributions, while generalizability confirms its robustness in novel scenarios. Utility is demonstrated "},"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":"2406.13130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T00:47:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db767303f5fda7ffee85c57d20479e5046726d68422804ee5b208b4fd6ede056","abstract_canon_sha256":"fe510c4a8d2cc77728c654c1a96cbaddc31fca913fd2a24dfe6ac7c047cc0d71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:25.553329Z","signature_b64":"JahdBfc3IvDnS5wi1rUSujzGvUEsFP6CPTHPEynDsECixeOJhck7dn2HVGP0Wi9+IjI4cvQqXrN7DRZyTPBtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e46cafd135bfa403b0a4156132bb71417e5770a284650f48eac5eddc03b894","last_reissued_at":"2026-07-05T08:34:25.552738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:25.552738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi-Hua Wang, Guang Cheng, Joshua Mabry, Yu Xia","submitted_at":"2024-06-19T00:47:38Z","abstract_excerpt":"The evaluation of synthetic data generation is crucial, especially in the retail sector where data accuracy is paramount. This paper introduces a comprehensive framework for assessing synthetic retail data, focusing on fidelity, utility, and privacy. Our approach differentiates between continuous and discrete data attributes, providing precise evaluation criteria. Fidelity is measured through stability and generalizability. Stability ensures synthetic data accurately replicates known data distributions, while generalizability confirms its robustness in novel scenarios. Utility is demonstrated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13130","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/2406.13130/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":"2406.13130","created_at":"2026-07-05T08:34:25.552815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13130v1","created_at":"2026-07-05T08:34:25.552815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13130","created_at":"2026-07-05T08:34:25.552815+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLSGZL6RGW72","created_at":"2026-07-05T08:34:25.552815+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLSGZL6RGW72IA5Q","created_at":"2026-07-05T08:34:25.552815+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLSGZL6R","created_at":"2026-07-05T08:34:25.552815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26053","citing_title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF","json":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF.json","graph_json":"https://pith.science/api/pith-number/WLSGZL6RGW72IA5QUQKWCMV3OF/graph.json","events_json":"https://pith.science/api/pith-number/WLSGZL6RGW72IA5QUQKWCMV3OF/events.json","paper":"https://pith.science/paper/WLSGZL6R"},"agent_actions":{"view_html":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF","download_json":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF.json","view_paper":"https://pith.science/paper/WLSGZL6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13130&json=true","fetch_graph":"https://pith.science/api/pith-number/WLSGZL6RGW72IA5QUQKWCMV3OF/graph.json","fetch_events":"https://pith.science/api/pith-number/WLSGZL6RGW72IA5QUQKWCMV3OF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF/action/storage_attestation","attest_author":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF/action/author_attestation","sign_citation":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF/action/citation_signature","submit_replication":"https://pith.science/pith/WLSGZL6RGW72IA5QUQKWCMV3OF/action/replication_record"}},"created_at":"2026-07-05T08:34:25.552815+00:00","updated_at":"2026-07-05T08:34:25.552815+00:00"}