{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XYUDRH5NWNVLY2XD7MXE6BAPPR","short_pith_number":"pith:XYUDRH5N","canonical_record":{"source":{"id":"2412.06809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T09:53:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"614d1b6fe8570a8fdbd0b5db945219cd15589765b884834cedff053af2e0b4c8","abstract_canon_sha256":"dd3ad2c208c6547f6f9b6db8de73a9868e75af0a380274b903e0f6f17ed2fbba"},"schema_version":"1.0"},"canonical_sha256":"be28389fadb36abc6ae3fb2e4f040f7c55841bad78988ebb2efb99bb35d3eaec","source":{"kind":"arxiv","id":"2412.06809","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06809","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06809v1","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06809","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_12","alias_value":"XYUDRH5NWNVL","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_16","alias_value":"XYUDRH5NWNVLY2XD","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_8","alias_value":"XYUDRH5N","created_at":"2026-07-05T09:46:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XYUDRH5NWNVLY2XD7MXE6BAPPR","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T09:53:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"614d1b6fe8570a8fdbd0b5db945219cd15589765b884834cedff053af2e0b4c8","abstract_canon_sha256":"dd3ad2c208c6547f6f9b6db8de73a9868e75af0a380274b903e0f6f17ed2fbba"},"schema_version":"1.0"},"canonical_sha256":"be28389fadb36abc6ae3fb2e4f040f7c55841bad78988ebb2efb99bb35d3eaec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:57.303897Z","signature_b64":"T2Xgt7P80cvURM4qt/QsoCRqZvRhICKUWr3XFmM2voi4yoneAm9xPpNKuVXsJxqKRcb+gEl1A65HZHsGBZJUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be28389fadb36abc6ae3fb2e4f040f7c55841bad78988ebb2efb99bb35d3eaec","last_reissued_at":"2026-07-05T09:46:57.303463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:57.303463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06809","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":"2026-07-05T09:46:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ipvmUHdkS62jtj4qKdXDADf70S41Xis4MazcVP0EAWpgipJ7+c+0MXBPpkxOEYvWdF2Ei+V2BSeQM56tmqnQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T04:02:13.916770Z"},"content_sha256":"9ca589d9c1392d2af5ada9e12a6435a7805b707755fa3beb51dc8fbcd0e0aa3d","schema_version":"1.0","event_id":"sha256:9ca589d9c1392d2af5ada9e12a6435a7805b707755fa3beb51dc8fbcd0e0aa3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XYUDRH5NWNVLY2XD7MXE6BAPPR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Diverse Synthetic Datasets for Evaluation of Real-life Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bla\\v{z} Mramor, Bla\\v{z} \\v{S}krlj, Jure Dem\\v{s}ar, Miha Malen\\v{s}ek","submitted_at":"2024-11-27T09:53:14Z","abstract_excerpt":"Synthetic datasets are important for evaluating and testing machine learning models. When evaluating real-life recommender systems, high-dimensional categorical (and sparse) datasets are often considered. Unfortunately, there are not many solutions that would allow generation of artificial datasets with such characteristics. For that purpose, we developed a novel framework for generating synthetic datasets that are diverse and statistically coherent. Our framework allows for creation of datasets with controlled attributes, enabling iterative modifications to fit specific experimental needs, su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06809","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/2412.06809/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":"2026-07-05T09:46:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmWM+LO3n65cXiLVm0+ZdlruzYQuw+MNW7YGFcMph1KyRBHgk8Z5AYFDirw1yj4HqrDjOX/FFtnXkWQ1Dk03Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T04:02:13.917158Z"},"content_sha256":"ec35064b2e7fa86d011e8bf743b21602789c031d36b9be62e466a5ecab92ab37","schema_version":"1.0","event_id":"sha256:ec35064b2e7fa86d011e8bf743b21602789c031d36b9be62e466a5ecab92ab37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/bundle.json","state_url":"https://pith.science/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/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":"2026-07-28T04:02:13Z","links":{"resolver":"https://pith.science/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR","bundle":"https://pith.science/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/bundle.json","state":"https://pith.science/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYUDRH5NWNVLY2XD7MXE6BAPPR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XYUDRH5NWNVLY2XD7MXE6BAPPR","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":"dd3ad2c208c6547f6f9b6db8de73a9868e75af0a380274b903e0f6f17ed2fbba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T09:53:14Z","title_canon_sha256":"614d1b6fe8570a8fdbd0b5db945219cd15589765b884834cedff053af2e0b4c8"},"schema_version":"1.0","source":{"id":"2412.06809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06809","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06809v1","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06809","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_12","alias_value":"XYUDRH5NWNVL","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_16","alias_value":"XYUDRH5NWNVLY2XD","created_at":"2026-07-05T09:46:57Z"},{"alias_kind":"pith_short_8","alias_value":"XYUDRH5N","created_at":"2026-07-05T09:46:57Z"}],"graph_snapshots":[{"event_id":"sha256:ec35064b2e7fa86d011e8bf743b21602789c031d36b9be62e466a5ecab92ab37","target":"graph","created_at":"2026-07-05T09:46:57Z","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/2412.06809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic datasets are important for evaluating and testing machine learning models. When evaluating real-life recommender systems, high-dimensional categorical (and sparse) datasets are often considered. Unfortunately, there are not many solutions that would allow generation of artificial datasets with such characteristics. For that purpose, we developed a novel framework for generating synthetic datasets that are diverse and statistically coherent. Our framework allows for creation of datasets with controlled attributes, enabling iterative modifications to fit specific experimental needs, su","authors_text":"Bla\\v{z} Mramor, Bla\\v{z} \\v{S}krlj, Jure Dem\\v{s}ar, Miha Malen\\v{s}ek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T09:53:14Z","title":"Generating Diverse Synthetic Datasets for Evaluation of Real-life Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06809","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":"sha256:9ca589d9c1392d2af5ada9e12a6435a7805b707755fa3beb51dc8fbcd0e0aa3d","target":"record","created_at":"2026-07-05T09:46:57Z","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":"dd3ad2c208c6547f6f9b6db8de73a9868e75af0a380274b903e0f6f17ed2fbba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-27T09:53:14Z","title_canon_sha256":"614d1b6fe8570a8fdbd0b5db945219cd15589765b884834cedff053af2e0b4c8"},"schema_version":"1.0","source":{"id":"2412.06809","kind":"arxiv","version":1}},"canonical_sha256":"be28389fadb36abc6ae3fb2e4f040f7c55841bad78988ebb2efb99bb35d3eaec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be28389fadb36abc6ae3fb2e4f040f7c55841bad78988ebb2efb99bb35d3eaec","first_computed_at":"2026-07-05T09:46:57.303463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:57.303463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T2Xgt7P80cvURM4qt/QsoCRqZvRhICKUWr3XFmM2voi4yoneAm9xPpNKuVXsJxqKRcb+gEl1A65HZHsGBZJUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:57.303897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ca589d9c1392d2af5ada9e12a6435a7805b707755fa3beb51dc8fbcd0e0aa3d","sha256:ec35064b2e7fa86d011e8bf743b21602789c031d36b9be62e466a5ecab92ab37"],"state_sha256":"b96181c9dcc4514bdc3f5556c4bda34d5e8c6e63bc2fdf241db9d864f2f7312b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"68nqtAUYgF8O7HSssIZnpBPeOWwIaEqopFtKxtg9F/Ld962PDgGPSaiGoPg+noSGc4mnV5sK9X0nst9nmBrSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T04:02:13.919350Z","bundle_sha256":"fa827cd06df0aee60372b119598394607a2ae61fc5c7685721dd7e40cfe623ed"}}