{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B3V37UQPHEHHK7LZJ76Q5S5A6Y","short_pith_number":"pith:B3V37UQP","schema_version":"1.0","canonical_sha256":"0eebbfd20f390e757d794ffd0ecba0f6157b76efccb9e60bd7e7becd732a0bca","source":{"kind":"arxiv","id":"1904.12437","version":2},"attestation_state":"computed","paper":{"title":"Challenges and Pitfalls of Machine Learning Evaluation and Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-Mei Hwu","submitted_at":"2019-04-29T03:35:15Z","abstract_excerpt":"An increasingly complex and diverse collection of Machine Learning (ML) models as well as hardware/software stacks, collectively referred to as \"ML artifacts\", are being proposed - leading to a diverse landscape of ML. These ML innovations proposed have outpaced researchers' ability to analyze, study and adapt them. This is exacerbated by the complicated and sometimes non-reproducible procedures for ML evaluation. A common practice of sharing ML artifacts is through repositories where artifact authors post ad-hoc code and some documentation, but often fail to reveal critical information for ot"},"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":"1904.12437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-29T03:35:15Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"20e0b37b166d88878df389557d405780f9ad14a84285ab61721e29ace095fe0b","abstract_canon_sha256":"24ba5ca4f84846881bf48adb238816fb79b4bdaf554961c482d7c4bd81dd9d38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:19.531925Z","signature_b64":"tTkhVgepb1b3lU2xzL9xoHyR1ewqIEacdEPMXgkYovLcXz3fBgj8KRWBzTrPBtE19vKQsIinDLXDJ360sBvhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eebbfd20f390e757d794ffd0ecba0f6157b76efccb9e60bd7e7becd732a0bca","last_reissued_at":"2026-05-17T23:42:19.531495Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:19.531495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges and Pitfalls of Machine Learning Evaluation and Benchmarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-Mei Hwu","submitted_at":"2019-04-29T03:35:15Z","abstract_excerpt":"An increasingly complex and diverse collection of Machine Learning (ML) models as well as hardware/software stacks, collectively referred to as \"ML artifacts\", are being proposed - leading to a diverse landscape of ML. These ML innovations proposed have outpaced researchers' ability to analyze, study and adapt them. This is exacerbated by the complicated and sometimes non-reproducible procedures for ML evaluation. A common practice of sharing ML artifacts is through repositories where artifact authors post ad-hoc code and some documentation, but often fail to reveal critical information for ot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12437","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":""},"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":"1904.12437","created_at":"2026-05-17T23:42:19.531561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12437v2","created_at":"2026-05-17T23:42:19.531561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12437","created_at":"2026-05-17T23:42:19.531561+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3V37UQPHEHH","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3V37UQPHEHHK7LZ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3V37UQP","created_at":"2026-05-18T12:33:12.712433+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/B3V37UQPHEHHK7LZJ76Q5S5A6Y","json":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y.json","graph_json":"https://pith.science/api/pith-number/B3V37UQPHEHHK7LZJ76Q5S5A6Y/graph.json","events_json":"https://pith.science/api/pith-number/B3V37UQPHEHHK7LZJ76Q5S5A6Y/events.json","paper":"https://pith.science/paper/B3V37UQP"},"agent_actions":{"view_html":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y","download_json":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y.json","view_paper":"https://pith.science/paper/B3V37UQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12437&json=true","fetch_graph":"https://pith.science/api/pith-number/B3V37UQPHEHHK7LZJ76Q5S5A6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/B3V37UQPHEHHK7LZJ76Q5S5A6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y/action/storage_attestation","attest_author":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y/action/author_attestation","sign_citation":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y/action/citation_signature","submit_replication":"https://pith.science/pith/B3V37UQPHEHHK7LZJ76Q5S5A6Y/action/replication_record"}},"created_at":"2026-05-17T23:42:19.531561+00:00","updated_at":"2026-05-17T23:42:19.531561+00:00"}