{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4WBVULTF5WDS333Y6TZOJ2HBFI","short_pith_number":"pith:4WBVULTF","canonical_record":{"source":{"id":"2011.02832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-04T17:58:18Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"f4aa080224479f00c199ed0afb247dab072ff87d28438efb3197dd25bae39c79","abstract_canon_sha256":"4e986443b22482c79fe9ce327e012ec2f429695eaf621fd4ad5baafb524f5ac5"},"schema_version":"1.0"},"canonical_sha256":"e5835a2e65ed872def78f4f2e4e8e12a373fa1746456c2132392ceb0f5f5bc46","source":{"kind":"arxiv","id":"2011.02832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02832","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02832v2","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02832","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_12","alias_value":"4WBVULTF5WDS","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_16","alias_value":"4WBVULTF5WDS333Y","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_8","alias_value":"4WBVULTF","created_at":"2026-07-05T03:06:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4WBVULTF5WDS333Y6TZOJ2HBFI","target":"record","payload":{"canonical_record":{"source":{"id":"2011.02832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-04T17:58:18Z","cross_cats_sorted":["stat.ME","stat.ML"],"title_canon_sha256":"f4aa080224479f00c199ed0afb247dab072ff87d28438efb3197dd25bae39c79","abstract_canon_sha256":"4e986443b22482c79fe9ce327e012ec2f429695eaf621fd4ad5baafb524f5ac5"},"schema_version":"1.0"},"canonical_sha256":"e5835a2e65ed872def78f4f2e4e8e12a373fa1746456c2132392ceb0f5f5bc46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:57.620540Z","signature_b64":"ZO9noT0h4mmtP98lHfgaCu+/sHBrzTd8MizHx84hdtT0EM5SIqOLug+ghwfclOMVHvoJHAtlyViY6WnQ/d66DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5835a2e65ed872def78f4f2e4e8e12a373fa1746456c2132392ceb0f5f5bc46","last_reissued_at":"2026-07-05T03:06:57.620108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:57.620108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.02832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:06:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"py+rWEdX/jQOEgT8PcnUJMnmgzJPGP1yfcTnYhix5H6TVeu7kAGB6drKZOoC3hO1NyWsyABAbwI1nZtgbl0XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:43:42.184569Z"},"content_sha256":"aa8de836632e468234a7c3f3b9c7447e22e7562f3a6df650532e82ac08b14b8c","schema_version":"1.0","event_id":"sha256:aa8de836632e468234a7c3f3b9c7447e22e7562f3a6df650532e82ac08b14b8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4WBVULTF5WDS333Y6TZOJ2HBFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pitfalls in Machine Learning Research: Reexamining the Development Cycle","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Stella Biderman, Walter J. Scheirer","submitted_at":"2020-11-04T17:58:18Z","abstract_excerpt":"Machine learning has the potential to fuel further advances in data science, but it is greatly hindered by an ad hoc design process, poor data hygiene, and a lack of statistical rigor in model evaluation. Recently, these issues have begun to attract more attention as they have caused public and embarrassing issues in research and development. Drawing from our experience as machine learning researchers, we follow the machine learning process from algorithm design to data collection to model evaluation, drawing attention to common pitfalls and providing practical recommendations for improvements"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02832","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/2011.02832/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":"2026-07-05T03:06:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xs+IMZJaKQ5Cl2aOBu5+Om7X7a/m7Fw2HjedWPJ1wJHtbcuJYLSEHNPf+YjXO9OhXZ/RZIP/N8U/uVEavJW/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:43:42.185286Z"},"content_sha256":"db253daeb7c5ffe8f76f6a1bf75baae0017e845e0e8b4d9a8ed7cac48f89839b","schema_version":"1.0","event_id":"sha256:db253daeb7c5ffe8f76f6a1bf75baae0017e845e0e8b4d9a8ed7cac48f89839b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/bundle.json","state_url":"https://pith.science/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/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":"2026-08-12T07:43:42Z","links":{"resolver":"https://pith.science/pith/4WBVULTF5WDS333Y6TZOJ2HBFI","bundle":"https://pith.science/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/bundle.json","state":"https://pith.science/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WBVULTF5WDS333Y6TZOJ2HBFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4WBVULTF5WDS333Y6TZOJ2HBFI","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":"4e986443b22482c79fe9ce327e012ec2f429695eaf621fd4ad5baafb524f5ac5","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-04T17:58:18Z","title_canon_sha256":"f4aa080224479f00c199ed0afb247dab072ff87d28438efb3197dd25bae39c79"},"schema_version":"1.0","source":{"id":"2011.02832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02832","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02832v2","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02832","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_12","alias_value":"4WBVULTF5WDS","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_16","alias_value":"4WBVULTF5WDS333Y","created_at":"2026-07-05T03:06:57Z"},{"alias_kind":"pith_short_8","alias_value":"4WBVULTF","created_at":"2026-07-05T03:06:57Z"}],"graph_snapshots":[{"event_id":"sha256:db253daeb7c5ffe8f76f6a1bf75baae0017e845e0e8b4d9a8ed7cac48f89839b","target":"graph","created_at":"2026-07-05T03:06:57Z","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/2011.02832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning has the potential to fuel further advances in data science, but it is greatly hindered by an ad hoc design process, poor data hygiene, and a lack of statistical rigor in model evaluation. Recently, these issues have begun to attract more attention as they have caused public and embarrassing issues in research and development. Drawing from our experience as machine learning researchers, we follow the machine learning process from algorithm design to data collection to model evaluation, drawing attention to common pitfalls and providing practical recommendations for improvements","authors_text":"Stella Biderman, Walter J. Scheirer","cross_cats":["stat.ME","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-04T17:58:18Z","title":"Pitfalls in Machine Learning Research: Reexamining the Development Cycle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02832","kind":"arxiv","version":2},"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:aa8de836632e468234a7c3f3b9c7447e22e7562f3a6df650532e82ac08b14b8c","target":"record","created_at":"2026-07-05T03:06:57Z","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":"4e986443b22482c79fe9ce327e012ec2f429695eaf621fd4ad5baafb524f5ac5","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-04T17:58:18Z","title_canon_sha256":"f4aa080224479f00c199ed0afb247dab072ff87d28438efb3197dd25bae39c79"},"schema_version":"1.0","source":{"id":"2011.02832","kind":"arxiv","version":2}},"canonical_sha256":"e5835a2e65ed872def78f4f2e4e8e12a373fa1746456c2132392ceb0f5f5bc46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5835a2e65ed872def78f4f2e4e8e12a373fa1746456c2132392ceb0f5f5bc46","first_computed_at":"2026-07-05T03:06:57.620108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:57.620108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZO9noT0h4mmtP98lHfgaCu+/sHBrzTd8MizHx84hdtT0EM5SIqOLug+ghwfclOMVHvoJHAtlyViY6WnQ/d66DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:57.620540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa8de836632e468234a7c3f3b9c7447e22e7562f3a6df650532e82ac08b14b8c","sha256:db253daeb7c5ffe8f76f6a1bf75baae0017e845e0e8b4d9a8ed7cac48f89839b"],"state_sha256":"e11ceb93dfb949dc9364a85ee334220bbbbd47e31c21fcc89fd3b22b0b9995d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HRtPV+kCYnkHlt9IEbZPwNRcBEw9jlqcK/1pZSIB9aZTs1touuhyGmda16K7ap0o0/1XS/R2Kf9AyiCPxQJ0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:43:42.194000Z","bundle_sha256":"2ff13da228c7f1cad54d3e27ff68db75da13be86d738b16426da7c4f25888c5c"}}