{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SKOCZ6EBSXZTEMIJM7LMPWTBC6","short_pith_number":"pith:SKOCZ6EB","canonical_record":{"source":{"id":"2301.10319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-24T21:40:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aeccf3b2ee938497c226203feb723d6221c1838e96ce1dd80375ebe3722a950b","abstract_canon_sha256":"a1bcd2681921c54f87f201e3879c76ddc01498bc79e4f0032f74f16ab5a4b973"},"schema_version":"1.0"},"canonical_sha256":"929c2cf88195f332310967d6c7da6117a918895571a6041b5ff4ae655da160b1","source":{"kind":"arxiv","id":"2301.10319","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10319","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10319v2","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10319","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"SKOCZ6EBSXZT","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"SKOCZ6EBSXZTEMIJ","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"SKOCZ6EB","created_at":"2026-07-05T06:35:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SKOCZ6EBSXZTEMIJM7LMPWTBC6","target":"record","payload":{"canonical_record":{"source":{"id":"2301.10319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-24T21:40:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"aeccf3b2ee938497c226203feb723d6221c1838e96ce1dd80375ebe3722a950b","abstract_canon_sha256":"a1bcd2681921c54f87f201e3879c76ddc01498bc79e4f0032f74f16ab5a4b973"},"schema_version":"1.0"},"canonical_sha256":"929c2cf88195f332310967d6c7da6117a918895571a6041b5ff4ae655da160b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:47.948106Z","signature_b64":"6hqrQNtV0sMXZCQIcuRcbn0NBO1IGstc25vfqyJp4K5ZxPnceIE6SQYMSeOC4mWaATsHNTggSYuQyIpT/BJQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"929c2cf88195f332310967d6c7da6117a918895571a6041b5ff4ae655da160b1","last_reissued_at":"2026-07-05T06:35:47.947574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:47.947574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.10319","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":"2026-07-05T06:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbhbi3aq5xm4GmDoFXt22Dx2Jg5ok3Kzd3DhtE2QJ9rBGO8rO5rRKK5izL3Ogz73MNp3VSWKt+qAoAwfzVKfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:18:44.316796Z"},"content_sha256":"41eacce06d4c050def3db1f0eced3cf8407dca9a30ba3a53634f657984797283","schema_version":"1.0","event_id":"sha256:41eacce06d4c050def3db1f0eced3cf8407dca9a30ba3a53634f657984797283"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SKOCZ6EBSXZTEMIJM7LMPWTBC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Designing Data: Proactive Data Collection and Iteration for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Aspen Hopkins, Dominik Moritz, Fred Hohman, Luca Zappella, Xavier Suau Cuadros","submitted_at":"2023-01-24T21:40:29Z","abstract_excerpt":"Lack of diversity in data collection has caused significant failures in machine learning (ML) applications. While ML developers perform post-collection interventions, these are time intensive and rarely comprehensive. Thus, new methods to track & manage data collection, iteration, and model training are necessary for evaluating whether datasets reflect real world variability. We present designing data, an iterative approach to data collection connecting HCI concepts with ML techniques. Our process includes (1) Pre-Collection Planning, to reflexively prompt and document expected data distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10319","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/2301.10319/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":"2026-07-05T06:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TilLHXAhbFYP7jUzX8aKgNze5Erwfa9ad1/R1ALqqZk+psXJkvxpZ1HqAMCcNhdRs/PcoS2RkVs9g2CJEqYbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:18:44.317442Z"},"content_sha256":"5709c4c0d99973e1ee15a9b3e7e5a9a78e3cd99454abe65c3f558670a0cb96bf","schema_version":"1.0","event_id":"sha256:5709c4c0d99973e1ee15a9b3e7e5a9a78e3cd99454abe65c3f558670a0cb96bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/bundle.json","state_url":"https://pith.science/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/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":"2026-08-15T03:18:44Z","links":{"resolver":"https://pith.science/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6","bundle":"https://pith.science/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/bundle.json","state":"https://pith.science/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKOCZ6EBSXZTEMIJM7LMPWTBC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SKOCZ6EBSXZTEMIJM7LMPWTBC6","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":"a1bcd2681921c54f87f201e3879c76ddc01498bc79e4f0032f74f16ab5a4b973","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-24T21:40:29Z","title_canon_sha256":"aeccf3b2ee938497c226203feb723d6221c1838e96ce1dd80375ebe3722a950b"},"schema_version":"1.0","source":{"id":"2301.10319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10319","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10319v2","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10319","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"SKOCZ6EBSXZT","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"SKOCZ6EBSXZTEMIJ","created_at":"2026-07-05T06:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"SKOCZ6EB","created_at":"2026-07-05T06:35:47Z"}],"graph_snapshots":[{"event_id":"sha256:5709c4c0d99973e1ee15a9b3e7e5a9a78e3cd99454abe65c3f558670a0cb96bf","target":"graph","created_at":"2026-07-05T06:35:47Z","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/2301.10319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lack of diversity in data collection has caused significant failures in machine learning (ML) applications. While ML developers perform post-collection interventions, these are time intensive and rarely comprehensive. Thus, new methods to track & manage data collection, iteration, and model training are necessary for evaluating whether datasets reflect real world variability. We present designing data, an iterative approach to data collection connecting HCI concepts with ML techniques. Our process includes (1) Pre-Collection Planning, to reflexively prompt and document expected data distributi","authors_text":"Aspen Hopkins, Dominik Moritz, Fred Hohman, Luca Zappella, Xavier Suau Cuadros","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-24T21:40:29Z","title":"Designing Data: Proactive Data Collection and Iteration for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10319","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":"sha256:41eacce06d4c050def3db1f0eced3cf8407dca9a30ba3a53634f657984797283","target":"record","created_at":"2026-07-05T06:35:47Z","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":"a1bcd2681921c54f87f201e3879c76ddc01498bc79e4f0032f74f16ab5a4b973","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-01-24T21:40:29Z","title_canon_sha256":"aeccf3b2ee938497c226203feb723d6221c1838e96ce1dd80375ebe3722a950b"},"schema_version":"1.0","source":{"id":"2301.10319","kind":"arxiv","version":2}},"canonical_sha256":"929c2cf88195f332310967d6c7da6117a918895571a6041b5ff4ae655da160b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"929c2cf88195f332310967d6c7da6117a918895571a6041b5ff4ae655da160b1","first_computed_at":"2026-07-05T06:35:47.947574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:47.947574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6hqrQNtV0sMXZCQIcuRcbn0NBO1IGstc25vfqyJp4K5ZxPnceIE6SQYMSeOC4mWaATsHNTggSYuQyIpT/BJQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:47.948106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41eacce06d4c050def3db1f0eced3cf8407dca9a30ba3a53634f657984797283","sha256:5709c4c0d99973e1ee15a9b3e7e5a9a78e3cd99454abe65c3f558670a0cb96bf"],"state_sha256":"076903302075e283da8ba55442f59139eb0b15c892ed7da64369b626e04a3698"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vsiw5kUUvYnK/vpFRvC7xvyJxbEs7s4Rcg8Cgap39jD6hijRrzbGwH81yVFlZDT9tps3egBIk9WbNCWFMmJ0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:18:44.322992Z","bundle_sha256":"6f124d52b9da61e0a99d9ee2c2c5e7c38e9c9a279a9c2e9d4af46a6a5c5c5ddc"}}