{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SNEP7LUVPVJDN7BP75O4HZRDE6","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":"c73961b14e37c0ae1c41d2453cedc732ffa91521cfe730bc31993d856a8bc10b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T12:01:42Z","title_canon_sha256":"b6db634ec34d80f68471f37daf17202b95840422f3252cfe1f773f1c0ecfbc1d"},"schema_version":"1.0","source":{"id":"2404.09703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09703","created_at":"2026-07-05T08:08:10Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09703v1","created_at":"2026-07-05T08:08:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09703","created_at":"2026-07-05T08:08:10Z"},{"alias_kind":"pith_short_12","alias_value":"SNEP7LUVPVJD","created_at":"2026-07-05T08:08:10Z"},{"alias_kind":"pith_short_16","alias_value":"SNEP7LUVPVJDN7BP","created_at":"2026-07-05T08:08:10Z"},{"alias_kind":"pith_short_8","alias_value":"SNEP7LUV","created_at":"2026-07-05T08:08:10Z"}],"graph_snapshots":[{"event_id":"sha256:d76ba23dc39be33675e6c1e5a6609ef8aa0ac0644c8edcf339ea3fbd9c64d1e9","target":"graph","created_at":"2026-07-05T08:08:10Z","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/2404.09703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning is now used in many applications thanks to its ability to predict, generate, or discover patterns from large quantities of data. However, the process of collecting and transforming data for practical use is intricate. Even in today's digital era, where substantial data is generated daily, it is uncommon for it to be readily usable; most often, it necessitates meticulous manual data preparation. The haste in developing new models can frequently result in various shortcomings, potentially posing risks when deployed in real-world scenarios (eg social discrimination, critical fail","authors_text":"Albert Clap\\'es, Isabelle Guyon, Jan N. van Rijn, Julio C. S. Jacques Junior, Jun Wan, Prasanna Balaprakash, Romain Egele, Sergio Escalera, Thomas Moeslund, Xavier Bar\\'o","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T12:01:42Z","title":"AI Competitions and Benchmarks: Dataset Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09703","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:e37412b07ad2c64978393bf908a7bdf8b4ffaca0af010ab2024e2832be982784","target":"record","created_at":"2026-07-05T08:08:10Z","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":"c73961b14e37c0ae1c41d2453cedc732ffa91521cfe730bc31993d856a8bc10b","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T12:01:42Z","title_canon_sha256":"b6db634ec34d80f68471f37daf17202b95840422f3252cfe1f773f1c0ecfbc1d"},"schema_version":"1.0","source":{"id":"2404.09703","kind":"arxiv","version":1}},"canonical_sha256":"9348ffae957d5236fc2fff5dc3e623278b120b24234b1e8e33ab86a907f52b2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9348ffae957d5236fc2fff5dc3e623278b120b24234b1e8e33ab86a907f52b2c","first_computed_at":"2026-07-05T08:08:10.671827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:10.671827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bq64qd7VG51T4rtzL5wdVCtC9hg9nDSQgJ+rieSlSIWZIAPcl1O5m8y3WhF9rFjFC5nyxEaut7Zua9l+vzpXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:10.672330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e37412b07ad2c64978393bf908a7bdf8b4ffaca0af010ab2024e2832be982784","sha256:d76ba23dc39be33675e6c1e5a6609ef8aa0ac0644c8edcf339ea3fbd9c64d1e9"],"state_sha256":"1e43f622a2522648da59b7f7a71e5a4a2bf99bbbc4439327dd3f0db64e45011b"}