{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UE5DPBYJTZ36AAAWJLLJFOQWIH","short_pith_number":"pith:UE5DPBYJ","canonical_record":{"source":{"id":"2009.13447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T16:12:38Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"65ec90dce2a5e949c44129777a117d5f5731997f65107f2c7fa78b5fffd35dec","abstract_canon_sha256":"c5d9347a2a67dc7ddc39433172afcb0e15fb939fe00af51cfade1a104ec59efb"},"schema_version":"1.0"},"canonical_sha256":"a13a3787099e77e000164ad692ba1641db8b090a52cba18797e7a8956e035d5d","source":{"kind":"arxiv","id":"2009.13447","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13447","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13447v3","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13447","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"UE5DPBYJTZ36","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"UE5DPBYJTZ36AAAW","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"UE5DPBYJ","created_at":"2026-07-05T03:09:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UE5DPBYJTZ36AAAWJLLJFOQWIH","target":"record","payload":{"canonical_record":{"source":{"id":"2009.13447","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T16:12:38Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"65ec90dce2a5e949c44129777a117d5f5731997f65107f2c7fa78b5fffd35dec","abstract_canon_sha256":"c5d9347a2a67dc7ddc39433172afcb0e15fb939fe00af51cfade1a104ec59efb"},"schema_version":"1.0"},"canonical_sha256":"a13a3787099e77e000164ad692ba1641db8b090a52cba18797e7a8956e035d5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:15.998952Z","signature_b64":"zGb3C2g0DHwv8P3rWjzjGBFJ8VzhnaOAcvN/QEmp4h/7bbEjoh5WHZsf9m6LYezOPIyuxL+5LcKNM5L5pwlxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a13a3787099e77e000164ad692ba1641db8b090a52cba18797e7a8956e035d5d","last_reissued_at":"2026-07-05T03:09:15.998570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:15.998570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.13447","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVprhT72IYc7IaDszzqLUbc1RBmW1yUo7glfnmaKga8dQbJ33MrlyQlQScs5MeVEaHeaiFCTA/v6OLIt86UcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:54:15.052690Z"},"content_sha256":"a414d5369d8f543c7ffa051f5e0882aeb508fcc74361eba2f0bf38b4fb5b466d","schema_version":"1.0","event_id":"sha256:a414d5369d8f543c7ffa051f5e0882aeb508fcc74361eba2f0bf38b4fb5b466d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UE5DPBYJTZ36AAAWJLLJFOQWIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jing An, Lexing Ying, Yuhua Zhu","submitted_at":"2020-09-28T16:12:38Z","abstract_excerpt":"A data set sampled from a certain population is biased if the subgroups of the population are sampled at proportions that are significantly different from their underlying proportions. Training machine learning models on biased data sets requires correction techniques to compensate for the bias. We consider two commonly-used techniques, resampling and reweighting, that rebalance the proportions of the subgroups to maintain the desired objective function. Though statistically equivalent, it has been observed that resampling outperforms reweighting when combined with stochastic gradient algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13447","kind":"arxiv","version":3},"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/2009.13447/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":"2026-07-05T03:09:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2F4IngWfBPnk+av5ZMNF3/SztGiD7U9lGYbrYQ1FVZP4gU4T4BImxFGC6xMc9qi9g7E1UPF9327w1YrDHqZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:54:15.053251Z"},"content_sha256":"d1edfefa15b2cf6d31a6a257fbb8da6da7dd2bbff0e9c0ccff30ea736c806987","schema_version":"1.0","event_id":"sha256:d1edfefa15b2cf6d31a6a257fbb8da6da7dd2bbff0e9c0ccff30ea736c806987"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/bundle.json","state_url":"https://pith.science/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/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":"2026-08-09T10:54:15Z","links":{"resolver":"https://pith.science/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH","bundle":"https://pith.science/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/bundle.json","state":"https://pith.science/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UE5DPBYJTZ36AAAWJLLJFOQWIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UE5DPBYJTZ36AAAWJLLJFOQWIH","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":"c5d9347a2a67dc7ddc39433172afcb0e15fb939fe00af51cfade1a104ec59efb","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T16:12:38Z","title_canon_sha256":"65ec90dce2a5e949c44129777a117d5f5731997f65107f2c7fa78b5fffd35dec"},"schema_version":"1.0","source":{"id":"2009.13447","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13447","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13447v3","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13447","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"UE5DPBYJTZ36","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"UE5DPBYJTZ36AAAW","created_at":"2026-07-05T03:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"UE5DPBYJ","created_at":"2026-07-05T03:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:d1edfefa15b2cf6d31a6a257fbb8da6da7dd2bbff0e9c0ccff30ea736c806987","target":"graph","created_at":"2026-07-05T03:09:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.13447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A data set sampled from a certain population is biased if the subgroups of the population are sampled at proportions that are significantly different from their underlying proportions. Training machine learning models on biased data sets requires correction techniques to compensate for the bias. We consider two commonly-used techniques, resampling and reweighting, that rebalance the proportions of the subgroups to maintain the desired objective function. Though statistically equivalent, it has been observed that resampling outperforms reweighting when combined with stochastic gradient algorith","authors_text":"Jing An, Lexing Ying, Yuhua Zhu","cross_cats":["cs.NA","math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T16:12:38Z","title":"Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13447","kind":"arxiv","version":3},"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:a414d5369d8f543c7ffa051f5e0882aeb508fcc74361eba2f0bf38b4fb5b466d","target":"record","created_at":"2026-07-05T03:09:15Z","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":"c5d9347a2a67dc7ddc39433172afcb0e15fb939fe00af51cfade1a104ec59efb","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-28T16:12:38Z","title_canon_sha256":"65ec90dce2a5e949c44129777a117d5f5731997f65107f2c7fa78b5fffd35dec"},"schema_version":"1.0","source":{"id":"2009.13447","kind":"arxiv","version":3}},"canonical_sha256":"a13a3787099e77e000164ad692ba1641db8b090a52cba18797e7a8956e035d5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a13a3787099e77e000164ad692ba1641db8b090a52cba18797e7a8956e035d5d","first_computed_at":"2026-07-05T03:09:15.998570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:15.998570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zGb3C2g0DHwv8P3rWjzjGBFJ8VzhnaOAcvN/QEmp4h/7bbEjoh5WHZsf9m6LYezOPIyuxL+5LcKNM5L5pwlxAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:15.998952Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.13447","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a414d5369d8f543c7ffa051f5e0882aeb508fcc74361eba2f0bf38b4fb5b466d","sha256:d1edfefa15b2cf6d31a6a257fbb8da6da7dd2bbff0e9c0ccff30ea736c806987"],"state_sha256":"bc78ba5dba87af96d3a8966cc67ae2ea6ef108993010af2a2e896f9749a9b829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NXwMUhAGRM2hEx3RAVj+KE1aGmsrHo0f3JoVmuO8UPGJihToFREvLtLG6X2XRU7VAZLhbVWpHVdzDNanXT8CBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:54:15.057125Z","bundle_sha256":"bb964d0f1b837bae2f17e7f2b1df5be6b713534fd62feffd8c546cafdca2470b"}}