{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:P4PQIF2SIUHOIHVVSQH3JDZM6D","short_pith_number":"pith:P4PQIF2S","canonical_record":{"source":{"id":"2209.03346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-04T22:24:35Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"fe41a1cbe104f0f752d1649a37ab455abc91d1b75aebce970e407897a647fb62","abstract_canon_sha256":"0ae2bf4303e964ab4065e31ad45a703f6cd5bfbdb52b3ae6cc6f4ee615f51e96"},"schema_version":"1.0"},"canonical_sha256":"7f1f041752450ee41eb5940fb48f2cf0f0d8504fa734c7e794a9aafc48e5b3b2","source":{"kind":"arxiv","id":"2209.03346","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03346","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03346v1","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03346","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_12","alias_value":"P4PQIF2SIUHO","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_16","alias_value":"P4PQIF2SIUHOIHVV","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_8","alias_value":"P4PQIF2S","created_at":"2026-07-05T04:55:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:P4PQIF2SIUHOIHVVSQH3JDZM6D","target":"record","payload":{"canonical_record":{"source":{"id":"2209.03346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-04T22:24:35Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"fe41a1cbe104f0f752d1649a37ab455abc91d1b75aebce970e407897a647fb62","abstract_canon_sha256":"0ae2bf4303e964ab4065e31ad45a703f6cd5bfbdb52b3ae6cc6f4ee615f51e96"},"schema_version":"1.0"},"canonical_sha256":"7f1f041752450ee41eb5940fb48f2cf0f0d8504fa734c7e794a9aafc48e5b3b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:40.979291Z","signature_b64":"5UhgXAbr06dlLozApcICw35qsqGB23mZgChSPnDYbSQQWAsJSlHBSi6VGPtwquDXnPhqspYsNkYMO/QciNDcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1f041752450ee41eb5940fb48f2cf0f0d8504fa734c7e794a9aafc48e5b3b2","last_reissued_at":"2026-07-05T04:55:40.978942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:40.978942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.03346","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":"2026-07-05T04:55:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEKdY5p4zxKqyr9N3EIGYmQyuMYdgykJ10FNe/u4XGd3QzH4TV8cw72tehLLlNZDJ7EWu96A0L/OHbPWEMneCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:50:23.131198Z"},"content_sha256":"8ce7f20ce5cd4634fe3e8c084bf63cfce38b858870709fbc6deb153d634f7b70","schema_version":"1.0","event_id":"sha256:8ce7f20ce5cd4634fe3e8c084bf63cfce38b858870709fbc6deb153d634f7b70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:P4PQIF2SIUHOIHVVSQH3JDZM6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Random Split for Assessing Statistical Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Carlos Catania, Gabriel Caffaratti, Jorge Guerra, Juan Manuel Romero, Martin Marchetta","submitted_at":"2022-09-04T22:24:35Z","abstract_excerpt":"Even though a train/test split of the dataset randomly performed is a common practice, could not always be the best approach for estimating performance generalization under some scenarios. The fact is that the usual machine learning methodology can sometimes overestimate the generalization error when a dataset is not representative or when rare and elusive examples are a fundamental aspect of the detection problem. In the present work, we analyze strategies based on the predictors' variability to split in training and testing sets. Such strategies aim at guaranteeing the inclusion of rare or u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03346","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.03346/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":"2026-07-05T04:55:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FnI8GRuOT5n7qyoQTXdGUYBzh43/DTZwOb2ok2bWPAPNycmPn/0bypWsV2SNBbm6YlSe62E7NKpsUBOQC5BwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:50:23.131770Z"},"content_sha256":"32c9f75bc436402cf15b8d2c148a43aa11fff881692b4e0f333ce770325fd85d","schema_version":"1.0","event_id":"sha256:32c9f75bc436402cf15b8d2c148a43aa11fff881692b4e0f333ce770325fd85d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/bundle.json","state_url":"https://pith.science/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/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":"2026-08-08T22:50:23Z","links":{"resolver":"https://pith.science/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D","bundle":"https://pith.science/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/bundle.json","state":"https://pith.science/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4PQIF2SIUHOIHVVSQH3JDZM6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:P4PQIF2SIUHOIHVVSQH3JDZM6D","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":"0ae2bf4303e964ab4065e31ad45a703f6cd5bfbdb52b3ae6cc6f4ee615f51e96","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-04T22:24:35Z","title_canon_sha256":"fe41a1cbe104f0f752d1649a37ab455abc91d1b75aebce970e407897a647fb62"},"schema_version":"1.0","source":{"id":"2209.03346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.03346","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"arxiv_version","alias_value":"2209.03346v1","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.03346","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_12","alias_value":"P4PQIF2SIUHO","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_16","alias_value":"P4PQIF2SIUHOIHVV","created_at":"2026-07-05T04:55:40Z"},{"alias_kind":"pith_short_8","alias_value":"P4PQIF2S","created_at":"2026-07-05T04:55:40Z"}],"graph_snapshots":[{"event_id":"sha256:32c9f75bc436402cf15b8d2c148a43aa11fff881692b4e0f333ce770325fd85d","target":"graph","created_at":"2026-07-05T04:55:40Z","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/2209.03346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Even though a train/test split of the dataset randomly performed is a common practice, could not always be the best approach for estimating performance generalization under some scenarios. The fact is that the usual machine learning methodology can sometimes overestimate the generalization error when a dataset is not representative or when rare and elusive examples are a fundamental aspect of the detection problem. In the present work, we analyze strategies based on the predictors' variability to split in training and testing sets. Such strategies aim at guaranteeing the inclusion of rare or u","authors_text":"Carlos Catania, Gabriel Caffaratti, Jorge Guerra, Juan Manuel Romero, Martin Marchetta","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-04T22:24:35Z","title":"Beyond Random Split for Assessing Statistical Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.03346","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":"sha256:8ce7f20ce5cd4634fe3e8c084bf63cfce38b858870709fbc6deb153d634f7b70","target":"record","created_at":"2026-07-05T04:55:40Z","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":"0ae2bf4303e964ab4065e31ad45a703f6cd5bfbdb52b3ae6cc6f4ee615f51e96","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-04T22:24:35Z","title_canon_sha256":"fe41a1cbe104f0f752d1649a37ab455abc91d1b75aebce970e407897a647fb62"},"schema_version":"1.0","source":{"id":"2209.03346","kind":"arxiv","version":1}},"canonical_sha256":"7f1f041752450ee41eb5940fb48f2cf0f0d8504fa734c7e794a9aafc48e5b3b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f1f041752450ee41eb5940fb48f2cf0f0d8504fa734c7e794a9aafc48e5b3b2","first_computed_at":"2026-07-05T04:55:40.978942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:55:40.978942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5UhgXAbr06dlLozApcICw35qsqGB23mZgChSPnDYbSQQWAsJSlHBSi6VGPtwquDXnPhqspYsNkYMO/QciNDcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:55:40.979291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.03346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ce7f20ce5cd4634fe3e8c084bf63cfce38b858870709fbc6deb153d634f7b70","sha256:32c9f75bc436402cf15b8d2c148a43aa11fff881692b4e0f333ce770325fd85d"],"state_sha256":"150fc4fdd3af0502c396659b3ea83e5ec2a1555900597212374a3012adbe45b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eC72z4HurMcY2550wEIarNvBhv51rkvcYf/E/Uz1G711c1UvimxeAMja110NZfH6LeHEEIkdwPsCVovQfeQWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:50:23.136140Z","bundle_sha256":"8a409450f9f95fc8356352bfbae7314c87b11804259f7ace92f5122f3e2113e9"}}