{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:V7XWZ3QGHPG3C2FX6OSHYOPLKJ","short_pith_number":"pith:V7XWZ3QG","canonical_record":{"source":{"id":"1812.10176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-25T23:44:07Z","cross_cats_sorted":[],"title_canon_sha256":"a1252d39e227ecf8eb6bee040a89d51cc6d57a5e2ecf24c501f204b7bac6e132","abstract_canon_sha256":"839419e83242a2bf64253e5d1741c56582a34c51ae579bc7e52b7f2c7428372f"},"schema_version":"1.0"},"canonical_sha256":"afef6cee063bcdb168b7f3a47c39eb524d87a29f727254a617afe4079e337a2b","source":{"kind":"arxiv","id":"1812.10176","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10176","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10176v1","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10176","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"V7XWZ3QGHPG3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7XWZ3QGHPG3C2FX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7XWZ3QG","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:V7XWZ3QGHPG3C2FX6OSHYOPLKJ","target":"record","payload":{"canonical_record":{"source":{"id":"1812.10176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-25T23:44:07Z","cross_cats_sorted":[],"title_canon_sha256":"a1252d39e227ecf8eb6bee040a89d51cc6d57a5e2ecf24c501f204b7bac6e132","abstract_canon_sha256":"839419e83242a2bf64253e5d1741c56582a34c51ae579bc7e52b7f2c7428372f"},"schema_version":"1.0"},"canonical_sha256":"afef6cee063bcdb168b7f3a47c39eb524d87a29f727254a617afe4079e337a2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:24.877560Z","signature_b64":"ccIu6uR4ZlEJ7R1JiH+jK+B48CPAdpBddqzUI1+OOJ78UT4s9DqB0LCU9CKv4M4oWrbPS8x8X9KHDNiqxe7EBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afef6cee063bcdb168b7f3a47c39eb524d87a29f727254a617afe4079e337a2b","last_reissued_at":"2026-05-17T23:57:24.876945Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:24.876945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.10176","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":"2026-05-17T23:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WDaGarSwzKNDG7AibRbpHYN3kjReZBDjlr8f8jRENUEqfxnkVUbXFIplq+S5CHqyQdLliqwkhuIhiwMrGKeCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:50:04.545019Z"},"content_sha256":"7d38212430659d1db4d450a08ecc72da058566f269353e869b5d96ebf61ee556","schema_version":"1.0","event_id":"sha256:7d38212430659d1db4d450a08ecc72da058566f269353e869b5d96ebf61ee556"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:V7XWZ3QGHPG3C2FX6OSHYOPLKJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Variability-Aware Design Approach to the Data Analysis Modeling Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Donald Cowan, Maria Cristina Vale Tavares, Paulo Alencar","submitted_at":"2018-12-25T23:44:07Z","abstract_excerpt":"The massive amount of current data has led to many different forms of data analysis processes that aim to explore this data to uncover valuable insights. Methodologies to guide the development of big data science projects, including CRISP-DM and SEMMA, have been widely used in industry and academia. The data analysis modeling phase, which involves decisions on the most appropriate models to adopt, is at the core of these projects. However, from a software engineering perspective, the design and automation of activities performed in this phase are challenging. In this paper, we propose an appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10176","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":""},"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":"2026-05-17T23:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdiboDzcrBO/mOZT5O7lUXcAKsMF0wj19PYwIj8iv6zfdtEEkALM7IR1RgQxDlk3nK4Q4KbGc7enUpxNePZiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:50:04.545725Z"},"content_sha256":"68d1bcc36c267429fa69fea1f2db88437397e43a5fe49a7631f8fa2117f4a3ae","schema_version":"1.0","event_id":"sha256:68d1bcc36c267429fa69fea1f2db88437397e43a5fe49a7631f8fa2117f4a3ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/bundle.json","state_url":"https://pith.science/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/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":"2026-05-26T23:50:04Z","links":{"resolver":"https://pith.science/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ","bundle":"https://pith.science/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/bundle.json","state":"https://pith.science/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7XWZ3QGHPG3C2FX6OSHYOPLKJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V7XWZ3QGHPG3C2FX6OSHYOPLKJ","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":"839419e83242a2bf64253e5d1741c56582a34c51ae579bc7e52b7f2c7428372f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-25T23:44:07Z","title_canon_sha256":"a1252d39e227ecf8eb6bee040a89d51cc6d57a5e2ecf24c501f204b7bac6e132"},"schema_version":"1.0","source":{"id":"1812.10176","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10176","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10176v1","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10176","created_at":"2026-05-17T23:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"V7XWZ3QGHPG3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"V7XWZ3QGHPG3C2FX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"V7XWZ3QG","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:68d1bcc36c267429fa69fea1f2db88437397e43a5fe49a7631f8fa2117f4a3ae","target":"graph","created_at":"2026-05-17T23:57:24Z","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"},"paper":{"abstract_excerpt":"The massive amount of current data has led to many different forms of data analysis processes that aim to explore this data to uncover valuable insights. Methodologies to guide the development of big data science projects, including CRISP-DM and SEMMA, have been widely used in industry and academia. The data analysis modeling phase, which involves decisions on the most appropriate models to adopt, is at the core of these projects. However, from a software engineering perspective, the design and automation of activities performed in this phase are challenging. In this paper, we propose an appro","authors_text":"Donald Cowan, Maria Cristina Vale Tavares, Paulo Alencar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-25T23:44:07Z","title":"A Variability-Aware Design Approach to the Data Analysis Modeling Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10176","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":"sha256:7d38212430659d1db4d450a08ecc72da058566f269353e869b5d96ebf61ee556","target":"record","created_at":"2026-05-17T23:57:24Z","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":"839419e83242a2bf64253e5d1741c56582a34c51ae579bc7e52b7f2c7428372f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-25T23:44:07Z","title_canon_sha256":"a1252d39e227ecf8eb6bee040a89d51cc6d57a5e2ecf24c501f204b7bac6e132"},"schema_version":"1.0","source":{"id":"1812.10176","kind":"arxiv","version":1}},"canonical_sha256":"afef6cee063bcdb168b7f3a47c39eb524d87a29f727254a617afe4079e337a2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afef6cee063bcdb168b7f3a47c39eb524d87a29f727254a617afe4079e337a2b","first_computed_at":"2026-05-17T23:57:24.876945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:24.876945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ccIu6uR4ZlEJ7R1JiH+jK+B48CPAdpBddqzUI1+OOJ78UT4s9DqB0LCU9CKv4M4oWrbPS8x8X9KHDNiqxe7EBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:24.877560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.10176","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d38212430659d1db4d450a08ecc72da058566f269353e869b5d96ebf61ee556","sha256:68d1bcc36c267429fa69fea1f2db88437397e43a5fe49a7631f8fa2117f4a3ae"],"state_sha256":"cca2db2f10866588d4894c44397a9761ea0647524ddf47e620f75b85bc4f1ad4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hosSX46vlB3nfCJcuvKBumKpEGvV0EBk7p4issnw1Q2sDKApf81OPyN54UydcCJZ4OsAacQnnInZfQ9wUcU8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:50:04.549427Z","bundle_sha256":"eb57d136bee8500c0bab2229d0f3cc75ef2bab54b570ec67a988b5939bb79aa6"}}