{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KZ2TQHOQC23JOZZCU7SA66SBUQ","short_pith_number":"pith:KZ2TQHOQ","schema_version":"1.0","canonical_sha256":"5675381dd016b6976722a7e40f7a41a40d41233f1428a746d991c758fc65ec35","source":{"kind":"arxiv","id":"2311.13028","version":2},"attestation_state":"computed","paper":{"title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","eess.SP"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Ahmed Alaa, Alicia Parrish, Bernard Koch, Bojan Karla\\v{s}, Braden Hancock, Ce Zhang, Cody Coleman, Curtis G Northcutt, Danilo Brajovic, Debojyoti Dutta, Girmaw Abebe Tadesse, Isabelle Guyon, James Zou, Joaquin Vanschoren, Kurt Bollacker, Lilith Bat-Leah, Lora Aroyo, Luis Oala, Manil Maskey, Matthew Lease, Max Bartolo, Meg Risdal, Michael W. Mahoney, Mihaela van der Schaar, Natasha Noy, Nezihe Merve G\\\"urel, Peter Mattson, Praveen Paritosh, Rainier Aliment, Rotem Dror, Ryan Hileman, Tzu-Sheng Kuo, Vijay Janapa Reddi, William A Gaviria Rojas, Wojciech Samek, Xiaozhe Yao, Yang Liu","submitted_at":"2023-11-21T22:29:25Z","abstract_excerpt":"Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods towards positive scientific, societal and business impact."},"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":"2311.13028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T22:29:25Z","cross_cats_sorted":["cs.AI","cs.DC","eess.SP"],"title_canon_sha256":"2243f1b218b3be780a3117ed8b81ef0aa3dbd576bf4769514f53ebeb89b4bb6a","abstract_canon_sha256":"909b754dcb8a1ce87f4c388884b207965d85c4ff25b072135d80685c139e9a5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:51.040212Z","signature_b64":"jI5+uJnw4j8VyEGz9eHXJCwwT8lb/mmDYzwrAvARDCYyGttqf3Qeu+K5l9dD5yFAbt59c9YkMGtVf63XdYOVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5675381dd016b6976722a7e40f7a41a40d41233f1428a746d991c758fc65ec35","last_reissued_at":"2026-07-05T08:25:51.039614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:51.039614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC","eess.SP"],"primary_cat":"cs.LG","authors_text":"Adji Bousso Dieng, Ahmed Alaa, Alicia Parrish, Bernard Koch, Bojan Karla\\v{s}, Braden Hancock, Ce Zhang, Cody Coleman, Curtis G Northcutt, Danilo Brajovic, Debojyoti Dutta, Girmaw Abebe Tadesse, Isabelle Guyon, James Zou, Joaquin Vanschoren, Kurt Bollacker, Lilith Bat-Leah, Lora Aroyo, Luis Oala, Manil Maskey, Matthew Lease, Max Bartolo, Meg Risdal, Michael W. Mahoney, Mihaela van der Schaar, Natasha Noy, Nezihe Merve G\\\"urel, Peter Mattson, Praveen Paritosh, Rainier Aliment, Rotem Dror, Ryan Hileman, Tzu-Sheng Kuo, Vijay Janapa Reddi, William A Gaviria Rojas, Wojciech Samek, Xiaozhe Yao, Yang Liu","submitted_at":"2023-11-21T22:29:25Z","abstract_excerpt":"Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure development for the creation of next-generation public datasets that will advance machine learning science. We chart a path forward as a collective effort to sustain the creation and maintenance of these datasets and methods towards positive scientific, societal and business impact."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13028","kind":"arxiv","version":2},"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/2311.13028/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":"2311.13028","created_at":"2026-07-05T08:25:51.039675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.13028v2","created_at":"2026-07-05T08:25:51.039675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13028","created_at":"2026-07-05T08:25:51.039675+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ2TQHOQC23J","created_at":"2026-07-05T08:25:51.039675+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ2TQHOQC23JOZZC","created_at":"2026-07-05T08:25:51.039675+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ2TQHOQ","created_at":"2026-07-05T08:25:51.039675+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/KZ2TQHOQC23JOZZCU7SA66SBUQ","json":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ.json","graph_json":"https://pith.science/api/pith-number/KZ2TQHOQC23JOZZCU7SA66SBUQ/graph.json","events_json":"https://pith.science/api/pith-number/KZ2TQHOQC23JOZZCU7SA66SBUQ/events.json","paper":"https://pith.science/paper/KZ2TQHOQ"},"agent_actions":{"view_html":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ","download_json":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ.json","view_paper":"https://pith.science/paper/KZ2TQHOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.13028&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ2TQHOQC23JOZZCU7SA66SBUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ2TQHOQC23JOZZCU7SA66SBUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ/action/storage_attestation","attest_author":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ/action/author_attestation","sign_citation":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ/action/citation_signature","submit_replication":"https://pith.science/pith/KZ2TQHOQC23JOZZCU7SA66SBUQ/action/replication_record"}},"created_at":"2026-07-05T08:25:51.039675+00:00","updated_at":"2026-07-05T08:25:51.039675+00:00"}