{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:A4LR57DYV7TBRHB47PZYWOOJH3","short_pith_number":"pith:A4LR57DY","canonical_record":{"source":{"id":"2005.01520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T14:33:39Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"f2d23e668934a4f8725fcc74c526e5a8e1aed0b987c5989c98d6647860102e87","abstract_canon_sha256":"da7144b4a4cd76241a755cffb0b72008b4004649c064215bc3562d590e31c586"},"schema_version":"1.0"},"canonical_sha256":"07171efc78afe6189c3cfbf38b39c93efea264970b58f4993eb0cfad7b533e77","source":{"kind":"arxiv","id":"2005.01520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01520","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01520v1","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01520","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"A4LR57DYV7TB","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"A4LR57DYV7TBRHB4","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"A4LR57DY","created_at":"2026-07-05T01:00:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:A4LR57DYV7TBRHB47PZYWOOJH3","target":"record","payload":{"canonical_record":{"source":{"id":"2005.01520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T14:33:39Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"f2d23e668934a4f8725fcc74c526e5a8e1aed0b987c5989c98d6647860102e87","abstract_canon_sha256":"da7144b4a4cd76241a755cffb0b72008b4004649c064215bc3562d590e31c586"},"schema_version":"1.0"},"canonical_sha256":"07171efc78afe6189c3cfbf38b39c93efea264970b58f4993eb0cfad7b533e77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:08.571729Z","signature_b64":"Pj1NM/Suupt+9moLLeO8jrBFzNIXAvwbgjljQSUwZUPU8MP/KT3KcVR4bm06ycpLr5Ox1M5WAW6IG+V7McuUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07171efc78afe6189c3cfbf38b39c93efea264970b58f4993eb0cfad7b533e77","last_reissued_at":"2026-07-05T01:00:08.571338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:08.571338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.01520","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zIb1u5J9ZdC8Cz/BdOXOxfcnxTRrYHm+xO3e3a1M+P+TQOcPHv1pieRgJ/g27JCVZ2cMdmoFO59KakfeCzzSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:29:59.116667Z"},"content_sha256":"a262d12fb87c42fdc42fb05f17a11f6f364a722ed44b75cbee076756284792ee","schema_version":"1.0","event_id":"sha256:a262d12fb87c42fdc42fb05f17a11f6f364a722ed44b75cbee076756284792ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:A4LR57DYV7TBRHB47PZYWOOJH3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demystifying a Dark Art: Understanding Real-World Machine Learning Model Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Aditya Parameswaran, Angela Lee, Doris Lee, Doris Xin","submitted_at":"2020-05-04T14:33:39Z","abstract_excerpt":"It is well-known that the process of developing machine learning (ML) workflows is a dark-art; even experts struggle to find an optimal workflow leading to a high accuracy model. Users currently rely on empirical trial-and-error to obtain their own set of battle-tested guidelines to inform their modeling decisions. In this study, we aim to demystify this dark art by understanding how people iterate on ML workflows in practice. We analyze over 475k user-generated workflows on OpenML, an open-source platform for tracking and sharing ML workflows. We find that users often adopt a manual, automate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01520","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/2005.01520/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":"2026-07-05T01:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j50h8CIivlDnGJ0UekG5zjxtqxufKL0bxKIn+jFOxQ6QP5BFOLRX5He+VNwHFoBMj8aH3k5XUMmQKxDzbzN/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:29:59.117559Z"},"content_sha256":"8115878ec7ad0fe107f0238ec930b6b595b36447f7dc32486cb8a0391963c97e","schema_version":"1.0","event_id":"sha256:8115878ec7ad0fe107f0238ec930b6b595b36447f7dc32486cb8a0391963c97e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4LR57DYV7TBRHB47PZYWOOJH3/bundle.json","state_url":"https://pith.science/pith/A4LR57DYV7TBRHB47PZYWOOJH3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4LR57DYV7TBRHB47PZYWOOJH3/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":"2026-08-07T21:29:59Z","links":{"resolver":"https://pith.science/pith/A4LR57DYV7TBRHB47PZYWOOJH3","bundle":"https://pith.science/pith/A4LR57DYV7TBRHB47PZYWOOJH3/bundle.json","state":"https://pith.science/pith/A4LR57DYV7TBRHB47PZYWOOJH3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4LR57DYV7TBRHB47PZYWOOJH3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A4LR57DYV7TBRHB47PZYWOOJH3","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":"da7144b4a4cd76241a755cffb0b72008b4004649c064215bc3562d590e31c586","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T14:33:39Z","title_canon_sha256":"f2d23e668934a4f8725fcc74c526e5a8e1aed0b987c5989c98d6647860102e87"},"schema_version":"1.0","source":{"id":"2005.01520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01520","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01520v1","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01520","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"A4LR57DYV7TB","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"A4LR57DYV7TBRHB4","created_at":"2026-07-05T01:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"A4LR57DY","created_at":"2026-07-05T01:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:8115878ec7ad0fe107f0238ec930b6b595b36447f7dc32486cb8a0391963c97e","target":"graph","created_at":"2026-07-05T01:00:08Z","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/2005.01520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is well-known that the process of developing machine learning (ML) workflows is a dark-art; even experts struggle to find an optimal workflow leading to a high accuracy model. Users currently rely on empirical trial-and-error to obtain their own set of battle-tested guidelines to inform their modeling decisions. In this study, we aim to demystify this dark art by understanding how people iterate on ML workflows in practice. We analyze over 475k user-generated workflows on OpenML, an open-source platform for tracking and sharing ML workflows. We find that users often adopt a manual, automate","authors_text":"Aditya Parameswaran, Angela Lee, Doris Lee, Doris Xin","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T14:33:39Z","title":"Demystifying a Dark Art: Understanding Real-World Machine Learning Model Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01520","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:a262d12fb87c42fdc42fb05f17a11f6f364a722ed44b75cbee076756284792ee","target":"record","created_at":"2026-07-05T01:00:08Z","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":"da7144b4a4cd76241a755cffb0b72008b4004649c064215bc3562d590e31c586","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-04T14:33:39Z","title_canon_sha256":"f2d23e668934a4f8725fcc74c526e5a8e1aed0b987c5989c98d6647860102e87"},"schema_version":"1.0","source":{"id":"2005.01520","kind":"arxiv","version":1}},"canonical_sha256":"07171efc78afe6189c3cfbf38b39c93efea264970b58f4993eb0cfad7b533e77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07171efc78afe6189c3cfbf38b39c93efea264970b58f4993eb0cfad7b533e77","first_computed_at":"2026-07-05T01:00:08.571338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:08.571338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pj1NM/Suupt+9moLLeO8jrBFzNIXAvwbgjljQSUwZUPU8MP/KT3KcVR4bm06ycpLr5Ox1M5WAW6IG+V7McuUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:08.571729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a262d12fb87c42fdc42fb05f17a11f6f364a722ed44b75cbee076756284792ee","sha256:8115878ec7ad0fe107f0238ec930b6b595b36447f7dc32486cb8a0391963c97e"],"state_sha256":"7be09aa5daf777246fa4090e2ab7e1e574835b8b3f3ca0e3560699e54c10deca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5RrXNCUMkior4v44cAKTZZMpnKsPOVGEut/NJORb71ij0j1SkIBCNiAZqpi/5//4WODWsh5OETWPCg/XaVNeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:29:59.123140Z","bundle_sha256":"f24ab7af7c533bd87cd215de07508fe2fddc1172cb3d16cbfca99db09e114959"}}