{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MP65VFF4OBILQLCSJMK3XN6FAY","short_pith_number":"pith:MP65VFF4","canonical_record":{"source":{"id":"2212.13827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T14:00:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f447db08be95ccb0624e768e75aad1f53aea6fe475209232a77dcad4e1b3ba33","abstract_canon_sha256":"3ccf75fef3a523e8416c7dcd8e41ef8fd657d4aaa22439438b8b8595071cbf60"},"schema_version":"1.0"},"canonical_sha256":"63fdda94bc7050b82c524b15bbb7c5062432e989de2ba03c56f9254767e99d37","source":{"kind":"arxiv","id":"2212.13827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.13827","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"arxiv_version","alias_value":"2212.13827v1","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13827","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_12","alias_value":"MP65VFF4OBIL","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_16","alias_value":"MP65VFF4OBILQLCS","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_8","alias_value":"MP65VFF4","created_at":"2026-07-05T05:28:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MP65VFF4OBILQLCSJMK3XN6FAY","target":"record","payload":{"canonical_record":{"source":{"id":"2212.13827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T14:00:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f447db08be95ccb0624e768e75aad1f53aea6fe475209232a77dcad4e1b3ba33","abstract_canon_sha256":"3ccf75fef3a523e8416c7dcd8e41ef8fd657d4aaa22439438b8b8595071cbf60"},"schema_version":"1.0"},"canonical_sha256":"63fdda94bc7050b82c524b15bbb7c5062432e989de2ba03c56f9254767e99d37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:55.439499Z","signature_b64":"Rolthdb/Dgvjji51WjFalg3GuXZHSuc6Gy6k9St+TJ+N/H+JLSRUc9kKNsRFmZhmEakJCARSSPOVQRev9qeRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63fdda94bc7050b82c524b15bbb7c5062432e989de2ba03c56f9254767e99d37","last_reissued_at":"2026-07-05T05:28:55.439137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:55.439137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.13827","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":"2026-07-05T05:28:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xA+/TcwQufQAWaAHQglefdA9BAWBPAlab7v6NDoyPm5/kheTrAsICawdGq29DcLEqhLVQMu6pscs8krMpLmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:50:23.304257Z"},"content_sha256":"5a14e710dc94f6c31aa047271d224dc3a87658c9f9496220f7cd8d8109d5f6cf","schema_version":"1.0","event_id":"sha256:5a14e710dc94f6c31aa047271d224dc3a87658c9f9496220f7cd8d8109d5f6cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MP65VFF4OBILQLCSJMK3XN6FAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Harsh Rangwani, Mayank Mishra, R. Venkatesh Babu, Sumukh K Aithal","submitted_at":"2022-12-28T14:00:44Z","abstract_excerpt":"Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In this work, we analyze the class-imbalanced learning problem by examining the loss landscape of neural networks trained with re-weighting and margin-based techniques. Specifically, we examine the spectral density of Hessian of class-wise loss, through which we observe that the network weights converge to a saddle point in the loss landscapes of minority classe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13827","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/2212.13827/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":"2026-07-05T05:28:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4i2W0ot3UcAe9xNN87kR1BkaEeb1ZCZIKnEuq/296SQ01UcxFSGZkaKUR0uxruqQNe21CMGODsLBJspmFWSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:50:23.304788Z"},"content_sha256":"b7f5d228126129c421353a9dfa228d55145d0dbad50af77427732cd11e487492","schema_version":"1.0","event_id":"sha256:b7f5d228126129c421353a9dfa228d55145d0dbad50af77427732cd11e487492"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MP65VFF4OBILQLCSJMK3XN6FAY/bundle.json","state_url":"https://pith.science/pith/MP65VFF4OBILQLCSJMK3XN6FAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MP65VFF4OBILQLCSJMK3XN6FAY/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":"2026-08-05T14:50:23Z","links":{"resolver":"https://pith.science/pith/MP65VFF4OBILQLCSJMK3XN6FAY","bundle":"https://pith.science/pith/MP65VFF4OBILQLCSJMK3XN6FAY/bundle.json","state":"https://pith.science/pith/MP65VFF4OBILQLCSJMK3XN6FAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MP65VFF4OBILQLCSJMK3XN6FAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MP65VFF4OBILQLCSJMK3XN6FAY","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":"3ccf75fef3a523e8416c7dcd8e41ef8fd657d4aaa22439438b8b8595071cbf60","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T14:00:44Z","title_canon_sha256":"f447db08be95ccb0624e768e75aad1f53aea6fe475209232a77dcad4e1b3ba33"},"schema_version":"1.0","source":{"id":"2212.13827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.13827","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"arxiv_version","alias_value":"2212.13827v1","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13827","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_12","alias_value":"MP65VFF4OBIL","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_16","alias_value":"MP65VFF4OBILQLCS","created_at":"2026-07-05T05:28:55Z"},{"alias_kind":"pith_short_8","alias_value":"MP65VFF4","created_at":"2026-07-05T05:28:55Z"}],"graph_snapshots":[{"event_id":"sha256:b7f5d228126129c421353a9dfa228d55145d0dbad50af77427732cd11e487492","target":"graph","created_at":"2026-07-05T05:28:55Z","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/2212.13827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performance of neural networks, particularly on minority classes. In this work, we analyze the class-imbalanced learning problem by examining the loss landscape of neural networks trained with re-weighting and margin-based techniques. Specifically, we examine the spectral density of Hessian of class-wise loss, through which we observe that the network weights converge to a saddle point in the loss landscapes of minority classe","authors_text":"Harsh Rangwani, Mayank Mishra, R. Venkatesh Babu, Sumukh K Aithal","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T14:00:44Z","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13827","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":"sha256:5a14e710dc94f6c31aa047271d224dc3a87658c9f9496220f7cd8d8109d5f6cf","target":"record","created_at":"2026-07-05T05:28:55Z","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":"3ccf75fef3a523e8416c7dcd8e41ef8fd657d4aaa22439438b8b8595071cbf60","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-28T14:00:44Z","title_canon_sha256":"f447db08be95ccb0624e768e75aad1f53aea6fe475209232a77dcad4e1b3ba33"},"schema_version":"1.0","source":{"id":"2212.13827","kind":"arxiv","version":1}},"canonical_sha256":"63fdda94bc7050b82c524b15bbb7c5062432e989de2ba03c56f9254767e99d37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63fdda94bc7050b82c524b15bbb7c5062432e989de2ba03c56f9254767e99d37","first_computed_at":"2026-07-05T05:28:55.439137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:55.439137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rolthdb/Dgvjji51WjFalg3GuXZHSuc6Gy6k9St+TJ+N/H+JLSRUc9kKNsRFmZhmEakJCARSSPOVQRev9qeRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:55.439499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.13827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a14e710dc94f6c31aa047271d224dc3a87658c9f9496220f7cd8d8109d5f6cf","sha256:b7f5d228126129c421353a9dfa228d55145d0dbad50af77427732cd11e487492"],"state_sha256":"c88694be4c8b1eacb50f9a9bbd1654335bf65f786fcda887dff6abad0b4f0c6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b4zL1Ambg7RxlRBdBK8BC5fJIp8nPV7HAAP+5t7aiLWUho4Wy3Jex+1hLWzfUGcHkizmYqjZeBfdJM/zkB0WBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:50:23.309131Z","bundle_sha256":"ac3b01c730ec2f4c79a932812ab92eab56c4d146cef15b8df8b7e9ef7432ab69"}}