{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QUHBZ2K3K72GSIFW6KAAK54HDQ","short_pith_number":"pith:QUHBZ2K3","canonical_record":{"source":{"id":"1807.06713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-18T00:13:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04bc36d709d65049e7809b8fd5fc0604c9a019a770b7c4ed04eafa50742ee8d0","abstract_canon_sha256":"7c578ff7b7c81c7f2198b8a2689b0cb9b4fab4bf39a4eda3f7ebc392a81e62c3"},"schema_version":"1.0"},"canonical_sha256":"850e1ce95b57f46920b6f2800577871c09e79b9f4dde3f11825a1d6ec4641cee","source":{"kind":"arxiv","id":"1807.06713","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06713","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06713v2","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06713","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"QUHBZ2K3K72G","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QUHBZ2K3K72GSIFW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QUHBZ2K3","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QUHBZ2K3K72GSIFW6KAAK54HDQ","target":"record","payload":{"canonical_record":{"source":{"id":"1807.06713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-18T00:13:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04bc36d709d65049e7809b8fd5fc0604c9a019a770b7c4ed04eafa50742ee8d0","abstract_canon_sha256":"7c578ff7b7c81c7f2198b8a2689b0cb9b4fab4bf39a4eda3f7ebc392a81e62c3"},"schema_version":"1.0"},"canonical_sha256":"850e1ce95b57f46920b6f2800577871c09e79b9f4dde3f11825a1d6ec4641cee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:15.050292Z","signature_b64":"jx6MNqM7k96ZdG7zdhG8MZ0iyMxJgr6v0RNSGhG9vMA+SEgSBiH6MvR0Hu+MAP94vLWCqrriXBCeuSR2/iQ7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850e1ce95b57f46920b6f2800577871c09e79b9f4dde3f11825a1d6ec4641cee","last_reissued_at":"2026-05-17T23:57:15.049802Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:15.049802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.06713","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":"2026-05-17T23:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GV+XhZ7xCrkcIGKw4OWjYHPs0HdcJkw+T6AFh/rMtuQk3lUOiIdKJpKetBrVj81X8nPniFZFbfWFWemMJGsBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:27.873755Z"},"content_sha256":"3aeeef14b8afa6d294b5ca81e0dee57e36851e24e62a55a8240249569dbffe80","schema_version":"1.0","event_id":"sha256:3aeeef14b8afa6d294b5ca81e0dee57e36851e24e62a55a8240249569dbffe80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QUHBZ2K3K72GSIFW6KAAK54HDQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Interaction Effects Between Prediction and Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artur Dubrawski, Matt Barnes","submitted_at":"2018-07-18T00:13:31Z","abstract_excerpt":"Machine learning systems increasingly depend on pipelines of multiple algorithms to provide high quality and well structured predictions. This paper argues interaction effects between clustering and prediction (e.g. classification, regression) algorithms can cause subtle adverse behaviors during cross-validation that may not be initially apparent. In particular, we focus on the problem of estimating the out-of-cluster (OOC) prediction loss given an approximate clustering with probabilistic error rate $p_0$. Traditional cross-validation techniques exhibit significant empirical bias in this sett"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06713","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":""},"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":"2026-05-17T23:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRpp8Pi8l3DoIWybyOrqtilAlfLPyyLZRsmw0NOod5FnlZVmFW0UbO6muBJnqNIaOOsEWL8yy71eTW6+eHwUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:27.874109Z"},"content_sha256":"4635dadfa8b4bb8ec7460ccd8aae413566b6ffb352d67f06ee2403608e2e5a44","schema_version":"1.0","event_id":"sha256:4635dadfa8b4bb8ec7460ccd8aae413566b6ffb352d67f06ee2403608e2e5a44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/bundle.json","state_url":"https://pith.science/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/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":"2026-06-04T18:01:27Z","links":{"resolver":"https://pith.science/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ","bundle":"https://pith.science/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/bundle.json","state":"https://pith.science/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUHBZ2K3K72GSIFW6KAAK54HDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QUHBZ2K3K72GSIFW6KAAK54HDQ","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":"7c578ff7b7c81c7f2198b8a2689b0cb9b4fab4bf39a4eda3f7ebc392a81e62c3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-18T00:13:31Z","title_canon_sha256":"04bc36d709d65049e7809b8fd5fc0604c9a019a770b7c4ed04eafa50742ee8d0"},"schema_version":"1.0","source":{"id":"1807.06713","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.06713","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"1807.06713v2","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06713","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"QUHBZ2K3K72G","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QUHBZ2K3K72GSIFW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QUHBZ2K3","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:4635dadfa8b4bb8ec7460ccd8aae413566b6ffb352d67f06ee2403608e2e5a44","target":"graph","created_at":"2026-05-17T23:57:15Z","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":"Machine learning systems increasingly depend on pipelines of multiple algorithms to provide high quality and well structured predictions. This paper argues interaction effects between clustering and prediction (e.g. classification, regression) algorithms can cause subtle adverse behaviors during cross-validation that may not be initially apparent. In particular, we focus on the problem of estimating the out-of-cluster (OOC) prediction loss given an approximate clustering with probabilistic error rate $p_0$. Traditional cross-validation techniques exhibit significant empirical bias in this sett","authors_text":"Artur Dubrawski, Matt Barnes","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-18T00:13:31Z","title":"On the Interaction Effects Between Prediction and Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06713","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":"sha256:3aeeef14b8afa6d294b5ca81e0dee57e36851e24e62a55a8240249569dbffe80","target":"record","created_at":"2026-05-17T23:57:15Z","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":"7c578ff7b7c81c7f2198b8a2689b0cb9b4fab4bf39a4eda3f7ebc392a81e62c3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-18T00:13:31Z","title_canon_sha256":"04bc36d709d65049e7809b8fd5fc0604c9a019a770b7c4ed04eafa50742ee8d0"},"schema_version":"1.0","source":{"id":"1807.06713","kind":"arxiv","version":2}},"canonical_sha256":"850e1ce95b57f46920b6f2800577871c09e79b9f4dde3f11825a1d6ec4641cee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850e1ce95b57f46920b6f2800577871c09e79b9f4dde3f11825a1d6ec4641cee","first_computed_at":"2026-05-17T23:57:15.049802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:15.049802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jx6MNqM7k96ZdG7zdhG8MZ0iyMxJgr6v0RNSGhG9vMA+SEgSBiH6MvR0Hu+MAP94vLWCqrriXBCeuSR2/iQ7BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:15.050292Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.06713","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aeeef14b8afa6d294b5ca81e0dee57e36851e24e62a55a8240249569dbffe80","sha256:4635dadfa8b4bb8ec7460ccd8aae413566b6ffb352d67f06ee2403608e2e5a44"],"state_sha256":"23c576a55cd859bbca4382803991128ecb7af32fc33812be638833cc87ab5be9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sU/H6J5eKSqWyhbFV5FS4TkWfI8r0JgMd6bcnZBEMIBMqM9ux1Z7mXol3ayd1Cv3ICMw7I3+MdpPw/n9G7qoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:01:27.876390Z","bundle_sha256":"0fab176878ce2f2c05edadf58ad02b58eabec459f4e7a56b17c717dde9f5b9a1"}}