{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:75MREC5LIHAZXCED36BA4PYBHJ","short_pith_number":"pith:75MREC5L","canonical_record":{"source":{"id":"2012.07816","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","cross_cats_sorted":["cs.HC","cs.SE"],"title_canon_sha256":"50ea6711f0500fc59c28a93403b916108553fa9962e4382728f38baedde36af9","abstract_canon_sha256":"4fbf72af9b496c0c47f75572f7d6f469da975dbda133bc7b0ef632371aa98888"},"schema_version":"1.0"},"canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","source":{"kind":"arxiv","id":"2012.07816","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07816","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07816v5","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07816","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"75MREC5LIHAZ","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"75MREC5LIHAZXCED","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"75MREC5L","created_at":"2026-07-05T03:24:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:75MREC5LIHAZXCED36BA4PYBHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.07816","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","cross_cats_sorted":["cs.HC","cs.SE"],"title_canon_sha256":"50ea6711f0500fc59c28a93403b916108553fa9962e4382728f38baedde36af9","abstract_canon_sha256":"4fbf72af9b496c0c47f75572f7d6f469da975dbda133bc7b0ef632371aa98888"},"schema_version":"1.0"},"canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:55.662684Z","signature_b64":"zUFL4NE8hsswmYoywz2J6vF18MjNxZvhPxl6j+kCi8whx55+nmP58QeI9SK5XXDTNTkjctFjvhfmXQndbVYpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","last_reissued_at":"2026-07-05T03:24:55.662266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:55.662266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.07816","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PTTXUVvpMCR1CKnlyw1ii03eUIrQwtOEa3T5J3m2IeQ0UTBZ2Xz2vdjBy2B5CnNKlKGeWYe6cGx/YMwX7lBBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:37:51.342255Z"},"content_sha256":"6ab73c0092497aa5e652a31e3ebb62007c3b2a6fde3ddc163d4a5d0719d5bf8a","schema_version":"1.0","event_id":"sha256:6ab73c0092497aa5e652a31e3ebb62007c3b2a6fde3ddc163d4a5d0719d5bf8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:75MREC5LIHAZXCED36BA4PYBHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enabling Collaborative Data Science Development with the Ballet Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SE"],"primary_cat":"cs.LG","authors_text":"J\\\"urgen Cito, Kalyan Veeramachaneni, Kelvin Lu, Micah J. Smith","submitted_at":"2020-12-14T18:51:23Z","abstract_excerpt":"While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams. We describe challenges to scaling data science collaborations and present a conceptual framework and ML programming model to address them. We instantiate these ideas in Ballet, a lightweight framework for collaborative, open-source data science through a focus on feature engineering, and an accompanying cloud-based development environment. Using our framework, collaborators incrementally pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07816","kind":"arxiv","version":5},"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/2012.07816/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":"2026-07-05T03:24:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0YGmHRuJdNsyacf687g4Hre1GJjCFMEyYhshprIrSfxKg6xDZ207tums5lhRKmoqU1Ov8gmkrs5R+95A3zJlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:37:51.343043Z"},"content_sha256":"faf47f3d2e1a153bc05995003f74ed2dba276d9cda9827f30aef86fae7b24906","schema_version":"1.0","event_id":"sha256:faf47f3d2e1a153bc05995003f74ed2dba276d9cda9827f30aef86fae7b24906"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/bundle.json","state_url":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/75MREC5LIHAZXCED36BA4PYBHJ/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":"2026-08-13T23:37:51Z","links":{"resolver":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ","bundle":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/bundle.json","state":"https://pith.science/pith/75MREC5LIHAZXCED36BA4PYBHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/75MREC5LIHAZXCED36BA4PYBHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:75MREC5LIHAZXCED36BA4PYBHJ","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":"4fbf72af9b496c0c47f75572f7d6f469da975dbda133bc7b0ef632371aa98888","cross_cats_sorted":["cs.HC","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","title_canon_sha256":"50ea6711f0500fc59c28a93403b916108553fa9962e4382728f38baedde36af9"},"schema_version":"1.0","source":{"id":"2012.07816","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07816","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07816v5","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07816","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"75MREC5LIHAZ","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"75MREC5LIHAZXCED","created_at":"2026-07-05T03:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"75MREC5L","created_at":"2026-07-05T03:24:55Z"}],"graph_snapshots":[{"event_id":"sha256:faf47f3d2e1a153bc05995003f74ed2dba276d9cda9827f30aef86fae7b24906","target":"graph","created_at":"2026-07-05T03:24:55Z","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/2012.07816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams. We describe challenges to scaling data science collaborations and present a conceptual framework and ML programming model to address them. We instantiate these ideas in Ballet, a lightweight framework for collaborative, open-source data science through a focus on feature engineering, and an accompanying cloud-based development environment. Using our framework, collaborators incrementally pro","authors_text":"J\\\"urgen Cito, Kalyan Veeramachaneni, Kelvin Lu, Micah J. Smith","cross_cats":["cs.HC","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","title":"Enabling Collaborative Data Science Development with the Ballet Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07816","kind":"arxiv","version":5},"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":"sha256:6ab73c0092497aa5e652a31e3ebb62007c3b2a6fde3ddc163d4a5d0719d5bf8a","target":"record","created_at":"2026-07-05T03:24:55Z","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":"4fbf72af9b496c0c47f75572f7d6f469da975dbda133bc7b0ef632371aa98888","cross_cats_sorted":["cs.HC","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-14T18:51:23Z","title_canon_sha256":"50ea6711f0500fc59c28a93403b916108553fa9962e4382728f38baedde36af9"},"schema_version":"1.0","source":{"id":"2012.07816","kind":"arxiv","version":5}},"canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff59120bab41c19b8883df820e3f013a523c2c0d1e8e8e479624244dc7fc8557","first_computed_at":"2026-07-05T03:24:55.662266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:55.662266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zUFL4NE8hsswmYoywz2J6vF18MjNxZvhPxl6j+kCi8whx55+nmP58QeI9SK5XXDTNTkjctFjvhfmXQndbVYpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:55.662684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07816","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ab73c0092497aa5e652a31e3ebb62007c3b2a6fde3ddc163d4a5d0719d5bf8a","sha256:faf47f3d2e1a153bc05995003f74ed2dba276d9cda9827f30aef86fae7b24906"],"state_sha256":"ff135fe17535a03046acd34f2aadedaa5f2ee847fe477b082088ccb27960dfbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rX14HihVMBp6aNmNT+yC0ViQ2tX5kKkLzn2WF0me8mq1uaFajubxOkHxH6t639nl0wN6op/tKD1eEc2elwbdBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:37:51.355362Z","bundle_sha256":"91661a5f6a413cb25a7ae432bf9a8ac686af0b2e3df99cb5cbecdee30e04e1ad"}}