{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VW2BENBMPCVIXHG3QO4JOEVAJR","short_pith_number":"pith:VW2BENBM","canonical_record":{"source":{"id":"2506.08548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-06-10T08:14:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e368468c0218fc91d2527eb2ef85d119f81c256ec53b50a59daa7a2b175ba664","abstract_canon_sha256":"d6bedfefe48d201ef963ffc735fda38a71203c20b5e0da9f3b58f3bf4fb618ab"},"schema_version":"1.0"},"canonical_sha256":"adb412342c78aa8b9cdb83b89712a04c50ff1b5bacb38439eedc40aa75835932","source":{"kind":"arxiv","id":"2506.08548","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08548","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08548v1","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08548","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"VW2BENBMPCVI","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"VW2BENBMPCVIXHG3","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"VW2BENBM","created_at":"2026-07-05T11:19:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VW2BENBMPCVIXHG3QO4JOEVAJR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-06-10T08:14:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e368468c0218fc91d2527eb2ef85d119f81c256ec53b50a59daa7a2b175ba664","abstract_canon_sha256":"d6bedfefe48d201ef963ffc735fda38a71203c20b5e0da9f3b58f3bf4fb618ab"},"schema_version":"1.0"},"canonical_sha256":"adb412342c78aa8b9cdb83b89712a04c50ff1b5bacb38439eedc40aa75835932","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:09.548295Z","signature_b64":"b6gjXarp/AEVrSWz+X3CjclHcgA77WDzG3QH+hvwHfmot0PMkaGLIvXFEgGlOLB8CpijSFHst5iIv5RPIqNlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adb412342c78aa8b9cdb83b89712a04c50ff1b5bacb38439eedc40aa75835932","last_reissued_at":"2026-07-05T11:19:09.547775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:09.547775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08548","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":"2026-07-05T11:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PGpRQaMolcS1hvSIytHSvItEge/Gm/rVUobsHTQ57/nWu0Q9ZCBN7kev54capTbp0wn6Gledr1+oXOhqWfbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:15.148903Z"},"content_sha256":"729bf4d832f420241071718f4492a5f0e1f9f4d5175dd063806303c0d559ae90","schema_version":"1.0","event_id":"sha256:729bf4d832f420241071718f4492a5f0e1f9f4d5175dd063806303c0d559ae90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VW2BENBMPCVIXHG3QO4JOEVAJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asymptotic Normality of Infinite Centered Random Forests -Application to Imbalanced Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Charles Tillier (LMV), Erwan Scornet (LPSM (UMR\\_8001)), Moria Mayala (LPSM (UMR\\_8001)), Olivier Wintenberger (LPSM (UMR\\_8001))","submitted_at":"2025-06-10T08:14:28Z","abstract_excerpt":"Many classification tasks involve imbalanced data, in which a class is largely underrepresented. Several techniques consists in creating a rebalanced dataset on which a classifier is trained. In this paper, we study theoretically such a procedure, when the classifier is a Centered Random Forests (CRF). We establish a Central Limit Theorem (CLT) on the infinite CRF with explicit rates and exact constant. We then prove that the CRF trained on the rebalanced dataset exhibits a bias, which can be removed with appropriate techniques. Based on an importance sampling (IS) approach, the resulting debi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08548","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/2506.08548/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":"2026-07-05T11:19:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sv0zG6HsK2GWuRruvBvYNB6ETWSs6SB4NfSKxZAke6K/XGF0F+yX/aGlPC4TQcrSCTlXWwkrjheO+UBag4VBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:17:15.149299Z"},"content_sha256":"2da7fe5cb84ec486c99f6ace106dcfc3bd64f977de0f232def4228d1204ae0c4","schema_version":"1.0","event_id":"sha256:2da7fe5cb84ec486c99f6ace106dcfc3bd64f977de0f232def4228d1204ae0c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/bundle.json","state_url":"https://pith.science/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/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":"2026-07-07T07:17:15Z","links":{"resolver":"https://pith.science/pith/VW2BENBMPCVIXHG3QO4JOEVAJR","bundle":"https://pith.science/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/bundle.json","state":"https://pith.science/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VW2BENBMPCVIXHG3QO4JOEVAJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VW2BENBMPCVIXHG3QO4JOEVAJR","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":"d6bedfefe48d201ef963ffc735fda38a71203c20b5e0da9f3b58f3bf4fb618ab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-06-10T08:14:28Z","title_canon_sha256":"e368468c0218fc91d2527eb2ef85d119f81c256ec53b50a59daa7a2b175ba664"},"schema_version":"1.0","source":{"id":"2506.08548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08548","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08548v1","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08548","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_12","alias_value":"VW2BENBMPCVI","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_16","alias_value":"VW2BENBMPCVIXHG3","created_at":"2026-07-05T11:19:09Z"},{"alias_kind":"pith_short_8","alias_value":"VW2BENBM","created_at":"2026-07-05T11:19:09Z"}],"graph_snapshots":[{"event_id":"sha256:2da7fe5cb84ec486c99f6ace106dcfc3bd64f977de0f232def4228d1204ae0c4","target":"graph","created_at":"2026-07-05T11:19:09Z","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/2506.08548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many classification tasks involve imbalanced data, in which a class is largely underrepresented. Several techniques consists in creating a rebalanced dataset on which a classifier is trained. In this paper, we study theoretically such a procedure, when the classifier is a Centered Random Forests (CRF). We establish a Central Limit Theorem (CLT) on the infinite CRF with explicit rates and exact constant. We then prove that the CRF trained on the rebalanced dataset exhibits a bias, which can be removed with appropriate techniques. Based on an importance sampling (IS) approach, the resulting debi","authors_text":"Charles Tillier (LMV), Erwan Scornet (LPSM (UMR\\_8001)), Moria Mayala (LPSM (UMR\\_8001)), Olivier Wintenberger (LPSM (UMR\\_8001))","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-06-10T08:14:28Z","title":"Asymptotic Normality of Infinite Centered Random Forests -Application to Imbalanced Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08548","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":"sha256:729bf4d832f420241071718f4492a5f0e1f9f4d5175dd063806303c0d559ae90","target":"record","created_at":"2026-07-05T11:19:09Z","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":"d6bedfefe48d201ef963ffc735fda38a71203c20b5e0da9f3b58f3bf4fb618ab","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-06-10T08:14:28Z","title_canon_sha256":"e368468c0218fc91d2527eb2ef85d119f81c256ec53b50a59daa7a2b175ba664"},"schema_version":"1.0","source":{"id":"2506.08548","kind":"arxiv","version":1}},"canonical_sha256":"adb412342c78aa8b9cdb83b89712a04c50ff1b5bacb38439eedc40aa75835932","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adb412342c78aa8b9cdb83b89712a04c50ff1b5bacb38439eedc40aa75835932","first_computed_at":"2026-07-05T11:19:09.547775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:09.547775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6gjXarp/AEVrSWz+X3CjclHcgA77WDzG3QH+hvwHfmot0PMkaGLIvXFEgGlOLB8CpijSFHst5iIv5RPIqNlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:09.548295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:729bf4d832f420241071718f4492a5f0e1f9f4d5175dd063806303c0d559ae90","sha256:2da7fe5cb84ec486c99f6ace106dcfc3bd64f977de0f232def4228d1204ae0c4"],"state_sha256":"95917dff3a9cbc97b28c73ce72b9831a616482a099784c86136abcf8a2a68b3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hF06/RcLgT66ce2Gw13ogUX3AQx/XYU0eUkifbKTym6zpE4sTaeZVy8L52SlCip0CdmXpfOmYOgFG8YFy/VJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:17:15.151737Z","bundle_sha256":"667fef16080c47925627feb0cf5d1b880f68605e8eeb53c755cc738b50a57c8b"}}