{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XXLJFBKAM7XKLXLIXKWSLYSV2Y","short_pith_number":"pith:XXLJFBKA","canonical_record":{"source":{"id":"2207.04958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2022-07-11T15:39:02Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"902816ef80b90b2c33302364234afd540d4a6a1784ad387d4752f12069ed9a67","abstract_canon_sha256":"552d80a3dc15cb8e6abdda245fc5750ed5272611abef8164bb1328df80b88f9f"},"schema_version":"1.0"},"canonical_sha256":"bdd692854067eea5dd68baad25e255d63d50d05804473a80ffc1f8e2bfb6fe88","source":{"kind":"arxiv","id":"2207.04958","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04958","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04958v2","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04958","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_12","alias_value":"XXLJFBKAM7XK","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_16","alias_value":"XXLJFBKAM7XKLXLI","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_8","alias_value":"XXLJFBKA","created_at":"2026-07-05T04:47:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XXLJFBKAM7XKLXLIXKWSLYSV2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2207.04958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2022-07-11T15:39:02Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"902816ef80b90b2c33302364234afd540d4a6a1784ad387d4752f12069ed9a67","abstract_canon_sha256":"552d80a3dc15cb8e6abdda245fc5750ed5272611abef8164bb1328df80b88f9f"},"schema_version":"1.0"},"canonical_sha256":"bdd692854067eea5dd68baad25e255d63d50d05804473a80ffc1f8e2bfb6fe88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:28.993364Z","signature_b64":"teOMKVLhWvzKx2eZpIXHA4e/QZZiAY/KGm6J8aufdIddNp0YpLiKl317lEzZP/f67Qj9//HOjkl4lQ+xC97kBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd692854067eea5dd68baad25e255d63d50d05804473a80ffc1f8e2bfb6fe88","last_reissued_at":"2026-07-05T04:47:28.992933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:28.992933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.04958","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":"2026-07-05T04:47:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MknDg546v3ltVxblSikr3ECUhLfGLfyaiyMkrWdzPDPtP9mhz369UI289BTfjk6NlspNO8tJNzzadLo1A9+/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:44:52.268590Z"},"content_sha256":"e34fcd5bf67a425cd8d331b8de25edf57b11b852ed8983869c03e793d92dd682","schema_version":"1.0","event_id":"sha256:e34fcd5bf67a425cd8d331b8de25edf57b11b852ed8983869c03e793d92dd682"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XXLJFBKAM7XKLXLIXKWSLYSV2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Documenting Data Production Processes: A Participatory Approach for Data Work","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.HC","authors_text":"Adriana Alvarado Garcia, Alex Hanna, Julian Posada, Marc Pohl, Milagros Miceli, Sonja Mei Wang, Tianling Yang","submitted_at":"2022-07-11T15:39:02Z","abstract_excerpt":"The opacity of machine learning data is a significant threat to ethical data work and intelligible systems. Previous research has addressed this issue by proposing standardized checklists to document datasets. This paper expands that field of inquiry by proposing a shift of perspective: from documenting datasets toward documenting data production. We draw on participatory design and collaborate with data workers at two companies located in Bulgaria and Argentina, where the collection and annotation of data for machine learning are outsourced. Our investigation comprises 2.5 years of research, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04958","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/2207.04958/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":"2026-07-05T04:47:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsUO0SCHUAe2aAbmz1yOVOBD81eHfvaha4SpCHeZLbgpYZWuBGwGipXqnmbD8LwyNDV+qyyWzsEL7PFvx09NCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:44:52.268957Z"},"content_sha256":"ecdc39e97ef0a386cf1052ab66d6822d01cf479fa6f014a074bb23c11e35a9a9","schema_version":"1.0","event_id":"sha256:ecdc39e97ef0a386cf1052ab66d6822d01cf479fa6f014a074bb23c11e35a9a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/bundle.json","state_url":"https://pith.science/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/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":"2026-07-07T02:44:52Z","links":{"resolver":"https://pith.science/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y","bundle":"https://pith.science/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/bundle.json","state":"https://pith.science/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXLJFBKAM7XKLXLIXKWSLYSV2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XXLJFBKAM7XKLXLIXKWSLYSV2Y","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":"552d80a3dc15cb8e6abdda245fc5750ed5272611abef8164bb1328df80b88f9f","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2022-07-11T15:39:02Z","title_canon_sha256":"902816ef80b90b2c33302364234afd540d4a6a1784ad387d4752f12069ed9a67"},"schema_version":"1.0","source":{"id":"2207.04958","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04958","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04958v2","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04958","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_12","alias_value":"XXLJFBKAM7XK","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_16","alias_value":"XXLJFBKAM7XKLXLI","created_at":"2026-07-05T04:47:28Z"},{"alias_kind":"pith_short_8","alias_value":"XXLJFBKA","created_at":"2026-07-05T04:47:28Z"}],"graph_snapshots":[{"event_id":"sha256:ecdc39e97ef0a386cf1052ab66d6822d01cf479fa6f014a074bb23c11e35a9a9","target":"graph","created_at":"2026-07-05T04:47:28Z","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/2207.04958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The opacity of machine learning data is a significant threat to ethical data work and intelligible systems. Previous research has addressed this issue by proposing standardized checklists to document datasets. This paper expands that field of inquiry by proposing a shift of perspective: from documenting datasets toward documenting data production. We draw on participatory design and collaborate with data workers at two companies located in Bulgaria and Argentina, where the collection and annotation of data for machine learning are outsourced. Our investigation comprises 2.5 years of research, ","authors_text":"Adriana Alvarado Garcia, Alex Hanna, Julian Posada, Marc Pohl, Milagros Miceli, Sonja Mei Wang, Tianling Yang","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2022-07-11T15:39:02Z","title":"Documenting Data Production Processes: A Participatory Approach for Data Work"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04958","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:e34fcd5bf67a425cd8d331b8de25edf57b11b852ed8983869c03e793d92dd682","target":"record","created_at":"2026-07-05T04:47:28Z","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":"552d80a3dc15cb8e6abdda245fc5750ed5272611abef8164bb1328df80b88f9f","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2022-07-11T15:39:02Z","title_canon_sha256":"902816ef80b90b2c33302364234afd540d4a6a1784ad387d4752f12069ed9a67"},"schema_version":"1.0","source":{"id":"2207.04958","kind":"arxiv","version":2}},"canonical_sha256":"bdd692854067eea5dd68baad25e255d63d50d05804473a80ffc1f8e2bfb6fe88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdd692854067eea5dd68baad25e255d63d50d05804473a80ffc1f8e2bfb6fe88","first_computed_at":"2026-07-05T04:47:28.992933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:47:28.992933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"teOMKVLhWvzKx2eZpIXHA4e/QZZiAY/KGm6J8aufdIddNp0YpLiKl317lEzZP/f67Qj9//HOjkl4lQ+xC97kBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:47:28.993364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04958","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e34fcd5bf67a425cd8d331b8de25edf57b11b852ed8983869c03e793d92dd682","sha256:ecdc39e97ef0a386cf1052ab66d6822d01cf479fa6f014a074bb23c11e35a9a9"],"state_sha256":"5af37b0fbf228dd7cc8ded10ff157b21106b2d5716fde17979e72ba9a2282d12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E5AvdsCN9EyPe1ukLy03vMj855tI1MY0uzkej+QWY1UaKJbPwmLxASPMZ8+IDrofDllw03fTbwNeNI5EQg4eDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:44:52.270850Z","bundle_sha256":"40b7b431d0ee7130b7999adaf62c7cc7bf97121e84576f81646a0ffe706d9b4f"}}