{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NIVMVTDIBRYMAQNP3VM4PMGQQT","short_pith_number":"pith:NIVMVTDI","schema_version":"1.0","canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","source":{"kind":"arxiv","id":"2103.00136","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takeshi Teshima","submitted_at":"2021-02-27T06:13:59Z","abstract_excerpt":"Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowledge, we can infer the conditional independence (CI) relations that should hold in the data distribution. However, it is not straightforward how to incorporate this knowledge into predictive modeling. In this work, we propose a model-agnostic data augmentation method that allows us to exploit the prior knowledge of the CI encoded in a CG for supervised machine learning. We theoretically justify the proposed method by"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.00136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T06:13:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a7deaa9ce30566a650c83f7bf46f05c17dfb2d935a0a48f11d9387ffd4d71556","abstract_canon_sha256":"d5c0caf4e7772b209785e6d2d5893fbd5333aed35961f9d6252a38e6569e4f50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:20.737788Z","signature_b64":"OlGupkd7t89mT9qHy1MWqHTMCHh4SD/E1pmi906t+CY5vBjn/mkCUka7nMldQzluf1/+s2/KVJznRskb1fTvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","last_reissued_at":"2026-07-05T03:06:20.737308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:20.737308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takeshi Teshima","submitted_at":"2021-02-27T06:13:59Z","abstract_excerpt":"Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. When a CG is available, e.g., from the domain knowledge, we can infer the conditional independence (CI) relations that should hold in the data distribution. However, it is not straightforward how to incorporate this knowledge into predictive modeling. In this work, we propose a model-agnostic data augmentation method that allows us to exploit the prior knowledge of the CI encoded in a CG for supervised machine learning. We theoretically justify the proposed method by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00136","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/2103.00136/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.00136","created_at":"2026-07-05T03:06:20.737383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00136v2","created_at":"2026-07-05T03:06:20.737383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00136","created_at":"2026-07-05T03:06:20.737383+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIVMVTDIBRYM","created_at":"2026-07-05T03:06:20.737383+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIVMVTDIBRYMAQNP","created_at":"2026-07-05T03:06:20.737383+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIVMVTDI","created_at":"2026-07-05T03:06:20.737383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT","json":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT.json","graph_json":"https://pith.science/api/pith-number/NIVMVTDIBRYMAQNP3VM4PMGQQT/graph.json","events_json":"https://pith.science/api/pith-number/NIVMVTDIBRYMAQNP3VM4PMGQQT/events.json","paper":"https://pith.science/paper/NIVMVTDI"},"agent_actions":{"view_html":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT","download_json":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT.json","view_paper":"https://pith.science/paper/NIVMVTDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00136&json=true","fetch_graph":"https://pith.science/api/pith-number/NIVMVTDIBRYMAQNP3VM4PMGQQT/graph.json","fetch_events":"https://pith.science/api/pith-number/NIVMVTDIBRYMAQNP3VM4PMGQQT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/action/storage_attestation","attest_author":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/action/author_attestation","sign_citation":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/action/citation_signature","submit_replication":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/action/replication_record"}},"created_at":"2026-07-05T03:06:20.737383+00:00","updated_at":"2026-07-05T03:06:20.737383+00:00"}