{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QIT3JDI2HZVJQLJRANXAHBK3UA","short_pith_number":"pith:QIT3JDI2","schema_version":"1.0","canonical_sha256":"8227b48d1a3e6a982d31036e03855ba0386801cf149ca1e8cd54d468fd92893a","source":{"kind":"arxiv","id":"2605.29786","version":1},"attestation_state":"computed","paper":{"title":"Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benedictus Kent Rachmat, Ihsan Ullah, Isabelle Guyon, Joaquin Vanschoren, Jonathan Lebensold, Leonardo Martins Bianco, Luis Oala, Omar Benjelloun, Peyman Vahidi, Sebastian Lobentanzer, Thanh Gia Hieu Khuong","submitted_at":"2026-05-28T11:34:09Z","abstract_excerpt":"Reproducibility is fundamental to the scientific method, yet remains a critical challenge in machine learning. Contributing factors include underspecified execution details and brittle software environments. Human-centric remedies, such as checklists and manual verification, help but require intensive effort and fail to scale. To address this, we introduce Croissant Tasks: a declarative, machine-actionable metadata format that abstracts low-level implementation details into high-level specifications. This format enables conceptual reproducibility: verifying claims via independent, agent-genera"},"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":"2605.29786","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T11:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"ab9a60ae2b21b8ceab61f4758c3628a4f04d6055681c41750d9612f2c4cb5185","abstract_canon_sha256":"c26272826ce78342c2f3a16789195287ab23b6ad84fef532aa13750b5ff1f272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:52.292190Z","signature_b64":"5lWTwo/5xZq4jjG3hj36+z8invtJ+uzLHDZ8nvdZGnf52ikg4tvIb8258RN5yvejPmSL7qb9m4G8UGKY3VwxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8227b48d1a3e6a982d31036e03855ba0386801cf149ca1e8cd54d468fd92893a","last_reissued_at":"2026-05-29T02:05:52.291364Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:52.291364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benedictus Kent Rachmat, Ihsan Ullah, Isabelle Guyon, Joaquin Vanschoren, Jonathan Lebensold, Leonardo Martins Bianco, Luis Oala, Omar Benjelloun, Peyman Vahidi, Sebastian Lobentanzer, Thanh Gia Hieu Khuong","submitted_at":"2026-05-28T11:34:09Z","abstract_excerpt":"Reproducibility is fundamental to the scientific method, yet remains a critical challenge in machine learning. Contributing factors include underspecified execution details and brittle software environments. Human-centric remedies, such as checklists and manual verification, help but require intensive effort and fail to scale. To address this, we introduce Croissant Tasks: a declarative, machine-actionable metadata format that abstracts low-level implementation details into high-level specifications. This format enables conceptual reproducibility: verifying claims via independent, agent-genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29786","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/2605.29786/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":"2605.29786","created_at":"2026-05-29T02:05:52.291502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29786v1","created_at":"2026-05-29T02:05:52.291502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29786","created_at":"2026-05-29T02:05:52.291502+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIT3JDI2HZVJ","created_at":"2026-05-29T02:05:52.291502+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIT3JDI2HZVJQLJR","created_at":"2026-05-29T02:05:52.291502+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIT3JDI2","created_at":"2026-05-29T02:05:52.291502+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/QIT3JDI2HZVJQLJRANXAHBK3UA","json":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA.json","graph_json":"https://pith.science/api/pith-number/QIT3JDI2HZVJQLJRANXAHBK3UA/graph.json","events_json":"https://pith.science/api/pith-number/QIT3JDI2HZVJQLJRANXAHBK3UA/events.json","paper":"https://pith.science/paper/QIT3JDI2"},"agent_actions":{"view_html":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA","download_json":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA.json","view_paper":"https://pith.science/paper/QIT3JDI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29786&json=true","fetch_graph":"https://pith.science/api/pith-number/QIT3JDI2HZVJQLJRANXAHBK3UA/graph.json","fetch_events":"https://pith.science/api/pith-number/QIT3JDI2HZVJQLJRANXAHBK3UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA/action/storage_attestation","attest_author":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA/action/author_attestation","sign_citation":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA/action/citation_signature","submit_replication":"https://pith.science/pith/QIT3JDI2HZVJQLJRANXAHBK3UA/action/replication_record"}},"created_at":"2026-05-29T02:05:52.291502+00:00","updated_at":"2026-05-29T02:05:52.291502+00:00"}