{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2WN53HCYUSIWWH47RDWBVNFCBG","short_pith_number":"pith:2WN53HCY","schema_version":"1.0","canonical_sha256":"d59bdd9c58a4916b1f9f88ec1ab4a209b567a98cca3cfa5efa3b7995f868bd45","source":{"kind":"arxiv","id":"2404.18209","version":1},"attestation_state":"computed","paper":{"title":"4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Christos Faloutsos, Chuan Lei, David Wipf, Guang Yang, Han Zhang, Jiahang Li, Jianheng Tang, Minjie Wang, Muhan Zhang, Ning Li, Quan Gan, Weinan Zhang, Xiao Qin, Yakun Song, Yanbo Wang, Yanlin Zhang, Zheng Zhang, Zhenkun Cai, Zizhao Zhang, Zunyao Mao","submitted_at":"2024-04-28T15:04:54Z","abstract_excerpt":"Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls well behind advances in other domains such as computer vision or natural language processing. This deficit stems, at least in part, from the lack of established/public RDB benchmarks as needed for training and evaluation purposes. As a result, related model development thus far often defaults to tabular approaches trained on ubiquitous single-table benchmarks, or on the relational side, graph-based alternative"},"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":"2404.18209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-28T15:04:54Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"9b3d2671afa646fbe6b50532b6f1585d7b1a05494285626c15b2d048d778518e","abstract_canon_sha256":"24d5b581f2f9e98eea8beae8b182805822334228492caf1945f2be423398e42b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:59.924401Z","signature_b64":"cWG2DQVFAoSk3kleaXXBYei1Vp0yrh47W4KlssyaCo6ZoyZLnxZYVcuAa1Ysebog3jiI1GQvWHMYvUAzz3G7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59bdd9c58a4916b1f9f88ec1ab4a209b567a98cca3cfa5efa3b7995f868bd45","last_reissued_at":"2026-07-05T08:12:59.923948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:59.923948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Christos Faloutsos, Chuan Lei, David Wipf, Guang Yang, Han Zhang, Jiahang Li, Jianheng Tang, Minjie Wang, Muhan Zhang, Ning Li, Quan Gan, Weinan Zhang, Xiao Qin, Yakun Song, Yanbo Wang, Yanlin Zhang, Zheng Zhang, Zhenkun Cai, Zizhao Zhang, Zunyao Mao","submitted_at":"2024-04-28T15:04:54Z","abstract_excerpt":"Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls well behind advances in other domains such as computer vision or natural language processing. This deficit stems, at least in part, from the lack of established/public RDB benchmarks as needed for training and evaluation purposes. As a result, related model development thus far often defaults to tabular approaches trained on ubiquitous single-table benchmarks, or on the relational side, graph-based alternative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18209","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/2404.18209/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":"2404.18209","created_at":"2026-07-05T08:12:59.924001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18209v1","created_at":"2026-07-05T08:12:59.924001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18209","created_at":"2026-07-05T08:12:59.924001+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WN53HCYUSIW","created_at":"2026-07-05T08:12:59.924001+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WN53HCYUSIWWH47","created_at":"2026-07-05T08:12:59.924001+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WN53HCY","created_at":"2026-07-05T08:12:59.924001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.16527","citing_title":"Joint Relational Database Generation via Graph-Conditional Diffusion Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14464","citing_title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG","json":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG.json","graph_json":"https://pith.science/api/pith-number/2WN53HCYUSIWWH47RDWBVNFCBG/graph.json","events_json":"https://pith.science/api/pith-number/2WN53HCYUSIWWH47RDWBVNFCBG/events.json","paper":"https://pith.science/paper/2WN53HCY"},"agent_actions":{"view_html":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG","download_json":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG.json","view_paper":"https://pith.science/paper/2WN53HCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18209&json=true","fetch_graph":"https://pith.science/api/pith-number/2WN53HCYUSIWWH47RDWBVNFCBG/graph.json","fetch_events":"https://pith.science/api/pith-number/2WN53HCYUSIWWH47RDWBVNFCBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG/action/storage_attestation","attest_author":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG/action/author_attestation","sign_citation":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG/action/citation_signature","submit_replication":"https://pith.science/pith/2WN53HCYUSIWWH47RDWBVNFCBG/action/replication_record"}},"created_at":"2026-07-05T08:12:59.924001+00:00","updated_at":"2026-07-05T08:12:59.924001+00:00"}