{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NOZ3LB5EQGUOZYMQX4W4SNQFI7","short_pith_number":"pith:NOZ3LB5E","schema_version":"1.0","canonical_sha256":"6bb3b587a481a8ece190bf2dc9360547de45a0a25cba02139360906fa7e2d249","source":{"kind":"arxiv","id":"2210.01944","version":4},"attestation_state":"computed","paper":{"title":"A Framework for Large Scale Synthetic Graph Dataset Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Alex Fit-Florea, Artur Kasymov, Dawid Majchrowski, Pawel Morkisz, Piotr Bigaj, Sajad Darabi","submitted_at":"2022-10-04T22:41:33Z","abstract_excerpt":"Recently there has been increasing interest in developing and deploying deep graph learning algorithms for many tasks, such as fraud detection and recommender systems. Albeit, there is a limited number of publicly available graph-structured datasets, most of which are tiny compared to production-sized applications or are limited in their application domain. This work tackles this shortcoming by proposing a scalable synthetic graph generation tool to scale the datasets to production-size graphs with trillions of edges and billions of nodes. The tool learns a series of parametric models from pro"},"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":"2210.01944","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-04T22:41:33Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"32cbf73365fd9a1d9e21c01f330fbf32edca8d5217380bbfa968965457034a16","abstract_canon_sha256":"4aa5b483d565c72c18049ddb257654d1e6de0e236cc020fff126338e0c2b4015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:19.916664Z","signature_b64":"0jkiuVjeOYxj0ERODFZpEfr6gE/hxy7ibsKdWNTqaWci952xzRPLIG999Crogh2BMQQjXJ935e3cqAQv4nSzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bb3b587a481a8ece190bf2dc9360547de45a0a25cba02139360906fa7e2d249","last_reissued_at":"2026-07-05T06:57:19.916269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:19.916269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Framework for Large Scale Synthetic Graph Dataset Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Alex Fit-Florea, Artur Kasymov, Dawid Majchrowski, Pawel Morkisz, Piotr Bigaj, Sajad Darabi","submitted_at":"2022-10-04T22:41:33Z","abstract_excerpt":"Recently there has been increasing interest in developing and deploying deep graph learning algorithms for many tasks, such as fraud detection and recommender systems. Albeit, there is a limited number of publicly available graph-structured datasets, most of which are tiny compared to production-sized applications or are limited in their application domain. This work tackles this shortcoming by proposing a scalable synthetic graph generation tool to scale the datasets to production-size graphs with trillions of edges and billions of nodes. The tool learns a series of parametric models from pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01944","kind":"arxiv","version":4},"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/2210.01944/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":"2210.01944","created_at":"2026-07-05T06:57:19.916324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01944v4","created_at":"2026-07-05T06:57:19.916324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01944","created_at":"2026-07-05T06:57:19.916324+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOZ3LB5EQGUO","created_at":"2026-07-05T06:57:19.916324+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOZ3LB5EQGUOZYMQ","created_at":"2026-07-05T06:57:19.916324+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOZ3LB5E","created_at":"2026-07-05T06:57:19.916324+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/NOZ3LB5EQGUOZYMQX4W4SNQFI7","json":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7.json","graph_json":"https://pith.science/api/pith-number/NOZ3LB5EQGUOZYMQX4W4SNQFI7/graph.json","events_json":"https://pith.science/api/pith-number/NOZ3LB5EQGUOZYMQX4W4SNQFI7/events.json","paper":"https://pith.science/paper/NOZ3LB5E"},"agent_actions":{"view_html":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7","download_json":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7.json","view_paper":"https://pith.science/paper/NOZ3LB5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01944&json=true","fetch_graph":"https://pith.science/api/pith-number/NOZ3LB5EQGUOZYMQX4W4SNQFI7/graph.json","fetch_events":"https://pith.science/api/pith-number/NOZ3LB5EQGUOZYMQX4W4SNQFI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7/action/storage_attestation","attest_author":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7/action/author_attestation","sign_citation":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7/action/citation_signature","submit_replication":"https://pith.science/pith/NOZ3LB5EQGUOZYMQX4W4SNQFI7/action/replication_record"}},"created_at":"2026-07-05T06:57:19.916324+00:00","updated_at":"2026-07-05T06:57:19.916324+00:00"}