{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IUYNM4B6U77L7F543VTE6RMMFO","short_pith_number":"pith:IUYNM4B6","canonical_record":{"source":{"id":"2206.15189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T11:04:51Z","cross_cats_sorted":[],"title_canon_sha256":"0cc44940d58ca76867f38764ff3cbc39618eaa6bbd536867d17a8e130967ebb1","abstract_canon_sha256":"e070d64563a6b752b297c8e188862cc3640ba4ab8420c7caa735ffbfce578b92"},"schema_version":"1.0"},"canonical_sha256":"4530d6703ea7febf97bcdd664f458c2b9f4a48b1bece79832820a2cce59a6d29","source":{"kind":"arxiv","id":"2206.15189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15189","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15189v1","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15189","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_12","alias_value":"IUYNM4B6U77L","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_16","alias_value":"IUYNM4B6U77L7F54","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_8","alias_value":"IUYNM4B6","created_at":"2026-07-05T04:39:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IUYNM4B6U77L7F543VTE6RMMFO","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T11:04:51Z","cross_cats_sorted":[],"title_canon_sha256":"0cc44940d58ca76867f38764ff3cbc39618eaa6bbd536867d17a8e130967ebb1","abstract_canon_sha256":"e070d64563a6b752b297c8e188862cc3640ba4ab8420c7caa735ffbfce578b92"},"schema_version":"1.0"},"canonical_sha256":"4530d6703ea7febf97bcdd664f458c2b9f4a48b1bece79832820a2cce59a6d29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:50.710932Z","signature_b64":"LipVPwFn6fbqZsIR79qLt1zz4dxcY/URfE/jcgJE09YcfA6Kw07n06JIZWqTBatUIjQeVHdqdnLRfT+gugJsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4530d6703ea7febf97bcdd664f458c2b9f4a48b1bece79832820a2cce59a6d29","last_reissued_at":"2026-07-05T04:39:50.710573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:50.710573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15189","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":"2026-07-05T04:39:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NwrpayxWW3Q/tvS6VwM4h1VBUF6GDFxEd88b9xz3nmVSiwmh0fkokTXOGdW/BTm++OCYlYQ0yqRwCBU79gJACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:45:23.563718Z"},"content_sha256":"bc558e92b2fcbe604e3673987abd79c95bae5f0bbf8dc226d60d8749ca81e550","schema_version":"1.0","event_id":"sha256:bc558e92b2fcbe604e3673987abd79c95bae5f0bbf8dc226d60d8749ca81e550"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IUYNM4B6U77L7F543VTE6RMMFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Granularity Regularized Re-Balancing for Class Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huitong Chen, Qinghua Hu, Yu Wang","submitted_at":"2022-06-30T11:04:51Z","abstract_excerpt":"Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to use a few exemplars to avoid forgetting old knowledge. In such a scenario, data imbalance between old and new classes is a key issue that leads to performance degradation of the model. Several strategies have been designed to rectify the bias towards the new classes due to data imbalance. However, they heavily rely on the assumptions of the bias relation betw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15189","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/2206.15189/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":"2026-07-05T04:39:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6glEDDbFR3+XVjKCNX0ThXxVzmCBw8N3N8M91sZKNQ6jkNWd0YkOUG6uWWtXMCoQ1IVebnTZxPwoTAgw/YXNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:45:23.564657Z"},"content_sha256":"4fcbc78a79777a156986a314f58d71b5017e6efd6dd2b33fe604482387bfd0c1","schema_version":"1.0","event_id":"sha256:4fcbc78a79777a156986a314f58d71b5017e6efd6dd2b33fe604482387bfd0c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUYNM4B6U77L7F543VTE6RMMFO/bundle.json","state_url":"https://pith.science/pith/IUYNM4B6U77L7F543VTE6RMMFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUYNM4B6U77L7F543VTE6RMMFO/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":"2026-08-06T04:45:23Z","links":{"resolver":"https://pith.science/pith/IUYNM4B6U77L7F543VTE6RMMFO","bundle":"https://pith.science/pith/IUYNM4B6U77L7F543VTE6RMMFO/bundle.json","state":"https://pith.science/pith/IUYNM4B6U77L7F543VTE6RMMFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUYNM4B6U77L7F543VTE6RMMFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IUYNM4B6U77L7F543VTE6RMMFO","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":"e070d64563a6b752b297c8e188862cc3640ba4ab8420c7caa735ffbfce578b92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T11:04:51Z","title_canon_sha256":"0cc44940d58ca76867f38764ff3cbc39618eaa6bbd536867d17a8e130967ebb1"},"schema_version":"1.0","source":{"id":"2206.15189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15189","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15189v1","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15189","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_12","alias_value":"IUYNM4B6U77L","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_16","alias_value":"IUYNM4B6U77L7F54","created_at":"2026-07-05T04:39:50Z"},{"alias_kind":"pith_short_8","alias_value":"IUYNM4B6","created_at":"2026-07-05T04:39:50Z"}],"graph_snapshots":[{"event_id":"sha256:4fcbc78a79777a156986a314f58d71b5017e6efd6dd2b33fe604482387bfd0c1","target":"graph","created_at":"2026-07-05T04:39:50Z","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/2206.15189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to use a few exemplars to avoid forgetting old knowledge. In such a scenario, data imbalance between old and new classes is a key issue that leads to performance degradation of the model. Several strategies have been designed to rectify the bias towards the new classes due to data imbalance. However, they heavily rely on the assumptions of the bias relation betw","authors_text":"Huitong Chen, Qinghua Hu, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T11:04:51Z","title":"Multi-Granularity Regularized Re-Balancing for Class Incremental Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15189","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:bc558e92b2fcbe604e3673987abd79c95bae5f0bbf8dc226d60d8749ca81e550","target":"record","created_at":"2026-07-05T04:39:50Z","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":"e070d64563a6b752b297c8e188862cc3640ba4ab8420c7caa735ffbfce578b92","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T11:04:51Z","title_canon_sha256":"0cc44940d58ca76867f38764ff3cbc39618eaa6bbd536867d17a8e130967ebb1"},"schema_version":"1.0","source":{"id":"2206.15189","kind":"arxiv","version":1}},"canonical_sha256":"4530d6703ea7febf97bcdd664f458c2b9f4a48b1bece79832820a2cce59a6d29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4530d6703ea7febf97bcdd664f458c2b9f4a48b1bece79832820a2cce59a6d29","first_computed_at":"2026-07-05T04:39:50.710573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:50.710573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LipVPwFn6fbqZsIR79qLt1zz4dxcY/URfE/jcgJE09YcfA6Kw07n06JIZWqTBatUIjQeVHdqdnLRfT+gugJsDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:50.710932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc558e92b2fcbe604e3673987abd79c95bae5f0bbf8dc226d60d8749ca81e550","sha256:4fcbc78a79777a156986a314f58d71b5017e6efd6dd2b33fe604482387bfd0c1"],"state_sha256":"aed4eac779905da38ffc1aa8025a59e072942fbfeb50940d8a60bba8f0c7b8f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlJwhGFoE/BAGRbdL6t9lqvPHqHv8U4AUMlam6TtK/rzypc/cjIrYtUQ8dmBcaCdiFAc6TB5ZBAmf3cf65KTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:45:23.571723Z","bundle_sha256":"4e9f426e024fe8ce96bef4584556b499b560478c80a041bab7ec7a438f85c743"}}