{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FWZX4VGRKMGSGCOXJ3BDHEKHD2","short_pith_number":"pith:FWZX4VGR","canonical_record":{"source":{"id":"2201.01212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T15:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"8b6e52ab94f6ddca99dc477edf8c008af4fcbef06f91cb84c77d7d32062a5559","abstract_canon_sha256":"b3ee3a739f57811abf9d1cb861bc2c682ff49e3a677a68787957daebcffa8fc1"},"schema_version":"1.0"},"canonical_sha256":"2db37e54d1530d2309d74ec23391471e96e12389dddc6d2023c0390325461420","source":{"kind":"arxiv","id":"2201.01212","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01212","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01212v1","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01212","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"FWZX4VGRKMGS","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"FWZX4VGRKMGSGCOX","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"FWZX4VGR","created_at":"2026-07-05T03:45:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FWZX4VGRKMGSGCOXJ3BDHEKHD2","target":"record","payload":{"canonical_record":{"source":{"id":"2201.01212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T15:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"8b6e52ab94f6ddca99dc477edf8c008af4fcbef06f91cb84c77d7d32062a5559","abstract_canon_sha256":"b3ee3a739f57811abf9d1cb861bc2c682ff49e3a677a68787957daebcffa8fc1"},"schema_version":"1.0"},"canonical_sha256":"2db37e54d1530d2309d74ec23391471e96e12389dddc6d2023c0390325461420","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:58.511435Z","signature_b64":"wyK0+sKDeR4gPZFxxK1KUH5jeWW8OiwVQhmdzvIsFWYSLYsQs7fu9uRftIoFWYWPl7P+yseGyrQ07cdLPk/HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2db37e54d1530d2309d74ec23391471e96e12389dddc6d2023c0390325461420","last_reissued_at":"2026-07-05T03:45:58.511072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:58.511072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.01212","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":"2026-07-05T03:45:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AnuEN1dq/aK+0ZfN7ja6OcLkxUUYe/j59RC8ESjtdcbLKpqBIBYRm5zXlhmYn/fQqr45jyIChpLqIYFs2yRcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:35:13.490713Z"},"content_sha256":"a31e1365f7d280e8f6229a9e09d8ae9865d2d33006fecd64d2bb771eec7a9a85","schema_version":"1.0","event_id":"sha256:a31e1365f7d280e8f6229a9e09d8ae9865d2d33006fecd64d2bb771eec7a9a85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FWZX4VGRKMGSGCOXJ3BDHEKHD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christos Thrampoulidis, Jiasi Chen, Mingchen Li, Samet Oymak, Xuechen Zhang","submitted_at":"2022-01-04T15:53:23Z","abstract_excerpt":"Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further exacerbated by the fact that large capacity deep nets can perfectly fit the training data and appear to achieve perfect accuracy and fairness during training, but perform poorly during test. To address these challenges, we propose AutoBalance, a bi-level optimization framework that automatically designs a training loss function to optimize a blend of accuracy and fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01212","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/2201.01212/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":"2026-07-05T03:45:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T6+AzHh8fS3etWK6Jz/XxZVJPUs7tUpC898pWsRPBMOi8MLMwrCtyFilkZ+gyLTt/Lt4oHv+ejiKZwvunpp+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:35:13.491346Z"},"content_sha256":"4d9f76adfe670fd29ce12c54f50ecbaf543636b56162f26a7ef072b9635c278f","schema_version":"1.0","event_id":"sha256:4d9f76adfe670fd29ce12c54f50ecbaf543636b56162f26a7ef072b9635c278f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/bundle.json","state_url":"https://pith.science/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/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":"2026-08-03T21:35:13Z","links":{"resolver":"https://pith.science/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2","bundle":"https://pith.science/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/bundle.json","state":"https://pith.science/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWZX4VGRKMGSGCOXJ3BDHEKHD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FWZX4VGRKMGSGCOXJ3BDHEKHD2","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":"b3ee3a739f57811abf9d1cb861bc2c682ff49e3a677a68787957daebcffa8fc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T15:53:23Z","title_canon_sha256":"8b6e52ab94f6ddca99dc477edf8c008af4fcbef06f91cb84c77d7d32062a5559"},"schema_version":"1.0","source":{"id":"2201.01212","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.01212","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2201.01212v1","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01212","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"FWZX4VGRKMGS","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"FWZX4VGRKMGSGCOX","created_at":"2026-07-05T03:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"FWZX4VGR","created_at":"2026-07-05T03:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:4d9f76adfe670fd29ce12c54f50ecbaf543636b56162f26a7ef072b9635c278f","target":"graph","created_at":"2026-07-05T03:45:58Z","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/2201.01212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further exacerbated by the fact that large capacity deep nets can perfectly fit the training data and appear to achieve perfect accuracy and fairness during training, but perform poorly during test. To address these challenges, we propose AutoBalance, a bi-level optimization framework that automatically designs a training loss function to optimize a blend of accuracy and fa","authors_text":"Christos Thrampoulidis, Jiasi Chen, Mingchen Li, Samet Oymak, Xuechen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T15:53:23Z","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01212","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:a31e1365f7d280e8f6229a9e09d8ae9865d2d33006fecd64d2bb771eec7a9a85","target":"record","created_at":"2026-07-05T03:45:58Z","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":"b3ee3a739f57811abf9d1cb861bc2c682ff49e3a677a68787957daebcffa8fc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-04T15:53:23Z","title_canon_sha256":"8b6e52ab94f6ddca99dc477edf8c008af4fcbef06f91cb84c77d7d32062a5559"},"schema_version":"1.0","source":{"id":"2201.01212","kind":"arxiv","version":1}},"canonical_sha256":"2db37e54d1530d2309d74ec23391471e96e12389dddc6d2023c0390325461420","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2db37e54d1530d2309d74ec23391471e96e12389dddc6d2023c0390325461420","first_computed_at":"2026-07-05T03:45:58.511072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:58.511072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wyK0+sKDeR4gPZFxxK1KUH5jeWW8OiwVQhmdzvIsFWYSLYsQs7fu9uRftIoFWYWPl7P+yseGyrQ07cdLPk/HBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:58.511435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.01212","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a31e1365f7d280e8f6229a9e09d8ae9865d2d33006fecd64d2bb771eec7a9a85","sha256:4d9f76adfe670fd29ce12c54f50ecbaf543636b56162f26a7ef072b9635c278f"],"state_sha256":"aa9648768dc4e76c4894f0c275ceb3acbe05f08629c430c488f1f4c6c9648808"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92VfedYqBxuJ1Qw+V/OlG7/3cL2KURbUNfnHRAzzmSOLbLCJB9OvlkrZ2POKeig1pIP1k+hy/ivyY4AHvPoIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:35:13.495165Z","bundle_sha256":"01f9fdf8730daf0d9ee8226e1ba49931d0ef1ad0b6340a2799bd31b447268673"}}