{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NIVMVTDIBRYMAQNP3VM4PMGQQT","short_pith_number":"pith:NIVMVTDI","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"},"canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","source":{"kind":"arxiv","id":"2103.00136","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00136","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00136v2","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00136","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"NIVMVTDIBRYM","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"NIVMVTDIBRYMAQNP","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"NIVMVTDI","created_at":"2026-07-05T03:06:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NIVMVTDIBRYMAQNP3VM4PMGQQT","target":"record","payload":{"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"},"canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","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"},"source_kind":"arxiv","source_id":"2103.00136","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":"2026-07-05T03:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8jiE9ZqGtoo1Gu8szHmpKz1sADEmQbMgYoD7LhflJw0vAvztsZ8oi3RjWCGiYHvLSgqZ/xuVpsE4u2G+iyNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:09.785347Z"},"content_sha256":"4318e8d876a2c4343b67ba233aedf7800073e073ca37d1419046f49a03c95bea","schema_version":"1.0","event_id":"sha256:4318e8d876a2c4343b67ba233aedf7800073e073ca37d1419046f49a03c95bea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NIVMVTDIBRYMAQNP3VM4PMGQQT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AJbcVpXPKVpM+jzbrIcAGno09P3wiQUOCt21BlslFWFliTmSdQAYZYU9Vk939CNyd2h74HoayNbf2gGsz9feDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:09.785728Z"},"content_sha256":"4603926c18f122036b1d79d780ebf96029b604d9100874e862a98d1877a33ef3","schema_version":"1.0","event_id":"sha256:4603926c18f122036b1d79d780ebf96029b604d9100874e862a98d1877a33ef3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/bundle.json","state_url":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/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":"2026-07-06T19:05:09Z","links":{"resolver":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT","bundle":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/bundle.json","state":"https://pith.science/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIVMVTDIBRYMAQNP3VM4PMGQQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NIVMVTDIBRYMAQNP3VM4PMGQQT","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":"d5c0caf4e7772b209785e6d2d5893fbd5333aed35961f9d6252a38e6569e4f50","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T06:13:59Z","title_canon_sha256":"a7deaa9ce30566a650c83f7bf46f05c17dfb2d935a0a48f11d9387ffd4d71556"},"schema_version":"1.0","source":{"id":"2103.00136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00136","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00136v2","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00136","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"NIVMVTDIBRYM","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"NIVMVTDIBRYMAQNP","created_at":"2026-07-05T03:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"NIVMVTDI","created_at":"2026-07-05T03:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:4603926c18f122036b1d79d780ebf96029b604d9100874e862a98d1877a33ef3","target":"graph","created_at":"2026-07-05T03:06:20Z","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/2103.00136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Masashi Sugiyama, Takeshi Teshima","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T06:13:59Z","title":"Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00136","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":"sha256:4318e8d876a2c4343b67ba233aedf7800073e073ca37d1419046f49a03c95bea","target":"record","created_at":"2026-07-05T03:06:20Z","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":"d5c0caf4e7772b209785e6d2d5893fbd5333aed35961f9d6252a38e6569e4f50","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T06:13:59Z","title_canon_sha256":"a7deaa9ce30566a650c83f7bf46f05c17dfb2d935a0a48f11d9387ffd4d71556"},"schema_version":"1.0","source":{"id":"2103.00136","kind":"arxiv","version":2}},"canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a2acacc680c70c041afdd59c7b0d084ced6a3e8eabe0423c179bb3614cac647","first_computed_at":"2026-07-05T03:06:20.737308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:20.737308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OlGupkd7t89mT9qHy1MWqHTMCHh4SD/E1pmi906t+CY5vBjn/mkCUka7nMldQzluf1/+s2/KVJznRskb1fTvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:20.737788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4318e8d876a2c4343b67ba233aedf7800073e073ca37d1419046f49a03c95bea","sha256:4603926c18f122036b1d79d780ebf96029b604d9100874e862a98d1877a33ef3"],"state_sha256":"f9d67fcb43b1b58564af42a7d68cefc12e6fd3768091bde7b94ef2edef9683b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bmrarXsYDiiYzRR8CDN1SRmg5OJ57IaqZIN1ZCkc7Vi92PSSbMAkVpeSOux5VWo9nTwTuVTZDyMgRU+4HF7wBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:05:09.787703Z","bundle_sha256":"472ca1a65989eeea0a671a72488e8d8f455c8ff3f1c90d4144b5d676f4c4f5a1"}}