{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:QO6WTIAWKZLPSIP65IW2ZBF4CQ","short_pith_number":"pith:QO6WTIAW","canonical_record":{"source":{"id":"2003.13191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T02:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"c6e84daa94d8464b4788bb2bc861eb1f8c44565fe699f340dbeaa59d3536040d","abstract_canon_sha256":"38de60a52a8124ed809ff0613b5604fda50f5b6fa6d23ead9d925b1865130149"},"schema_version":"1.0"},"canonical_sha256":"83bd69a0165656f921feea2dac84bc142fa12d352a6220204fa9f753bf6a5090","source":{"kind":"arxiv","id":"2003.13191","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13191","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13191v2","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13191","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"QO6WTIAWKZLP","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"QO6WTIAWKZLPSIP6","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"QO6WTIAW","created_at":"2026-07-05T02:32:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:QO6WTIAWKZLPSIP65IW2ZBF4CQ","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T02:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"c6e84daa94d8464b4788bb2bc861eb1f8c44565fe699f340dbeaa59d3536040d","abstract_canon_sha256":"38de60a52a8124ed809ff0613b5604fda50f5b6fa6d23ead9d925b1865130149"},"schema_version":"1.0"},"canonical_sha256":"83bd69a0165656f921feea2dac84bc142fa12d352a6220204fa9f753bf6a5090","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:44.697405Z","signature_b64":"MysgMHn7SZBnsVJQBgZYWXZuw3a831aICjVTnN/rZdkh3JLE00lR5G7BEnp/tBOmdj2QTHWKQZiE6EV6M6EoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83bd69a0165656f921feea2dac84bc142fa12d352a6220204fa9f753bf6a5090","last_reissued_at":"2026-07-05T02:32:44.696920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:44.696920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13191","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtqBUMiUyMtvHxiF+Lcip2ZWewK+MjkBZ6eREaFF3u6UxObOxHCEg8WsfSELvPbxsA5TwXbW6T4TWKNL4es7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:14:31.540584Z"},"content_sha256":"35fc3f4032389e11cbacfa94a0d706ce130702f996c25d3a66743c3054aee4d0","schema_version":"1.0","event_id":"sha256:35fc3f4032389e11cbacfa94a0d706ce130702f996c25d3a66743c3054aee4d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:QO6WTIAWKZLPSIP65IW2ZBF4CQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incremental Learning In Online Scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengqing Zhu, Jiangpeng He, Runyu Mao, Zeman Shao","submitted_at":"2020-03-30T02:24:26Z","abstract_excerpt":"Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life applications: (1) Learning new classes makes the trained model quickly forget old classes knowledge, which is referred to as catastrophic forgetting. (2) As new observations of old classes come sequentially over time, the distribution may change in unforeseen way, making the performance degrade dramatically on future data, which is referred to as concept drift. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13191","kind":"arxiv","version":2},"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/2003.13191/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":"2026-07-05T02:32:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hD/jqoQSXnRgAdpQDoXEtsRoBzsjQCzcug53uIpvm9WO76Lv2bBaxCXCkTvifs2p3b1O2uNTj4CKQhMthVNyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:14:31.541139Z"},"content_sha256":"908039ca75e6323339e59f845e5b2689c59c56fa4d39db99ede2b5e520b1476a","schema_version":"1.0","event_id":"sha256:908039ca75e6323339e59f845e5b2689c59c56fa4d39db99ede2b5e520b1476a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/bundle.json","state_url":"https://pith.science/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/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":"2026-08-08T13:14:31Z","links":{"resolver":"https://pith.science/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ","bundle":"https://pith.science/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/bundle.json","state":"https://pith.science/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QO6WTIAWKZLPSIP65IW2ZBF4CQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QO6WTIAWKZLPSIP65IW2ZBF4CQ","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":"38de60a52a8124ed809ff0613b5604fda50f5b6fa6d23ead9d925b1865130149","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T02:24:26Z","title_canon_sha256":"c6e84daa94d8464b4788bb2bc861eb1f8c44565fe699f340dbeaa59d3536040d"},"schema_version":"1.0","source":{"id":"2003.13191","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13191","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13191v2","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13191","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_12","alias_value":"QO6WTIAWKZLP","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_16","alias_value":"QO6WTIAWKZLPSIP6","created_at":"2026-07-05T02:32:44Z"},{"alias_kind":"pith_short_8","alias_value":"QO6WTIAW","created_at":"2026-07-05T02:32:44Z"}],"graph_snapshots":[{"event_id":"sha256:908039ca75e6323339e59f845e5b2689c59c56fa4d39db99ede2b5e520b1476a","target":"graph","created_at":"2026-07-05T02:32:44Z","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/2003.13191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning approaches have achieved great success in many vision applications by training a model using all available task-specific data. However, there are two major obstacles making it challenging to implement for real life applications: (1) Learning new classes makes the trained model quickly forget old classes knowledge, which is referred to as catastrophic forgetting. (2) As new observations of old classes come sequentially over time, the distribution may change in unforeseen way, making the performance degrade dramatically on future data, which is referred to as concept drift. ","authors_text":"Fengqing Zhu, Jiangpeng He, Runyu Mao, Zeman Shao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T02:24:26Z","title":"Incremental Learning In Online Scenario"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13191","kind":"arxiv","version":2},"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":"sha256:35fc3f4032389e11cbacfa94a0d706ce130702f996c25d3a66743c3054aee4d0","target":"record","created_at":"2026-07-05T02:32:44Z","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":"38de60a52a8124ed809ff0613b5604fda50f5b6fa6d23ead9d925b1865130149","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-30T02:24:26Z","title_canon_sha256":"c6e84daa94d8464b4788bb2bc861eb1f8c44565fe699f340dbeaa59d3536040d"},"schema_version":"1.0","source":{"id":"2003.13191","kind":"arxiv","version":2}},"canonical_sha256":"83bd69a0165656f921feea2dac84bc142fa12d352a6220204fa9f753bf6a5090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83bd69a0165656f921feea2dac84bc142fa12d352a6220204fa9f753bf6a5090","first_computed_at":"2026-07-05T02:32:44.696920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:44.696920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MysgMHn7SZBnsVJQBgZYWXZuw3a831aICjVTnN/rZdkh3JLE00lR5G7BEnp/tBOmdj2QTHWKQZiE6EV6M6EoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:44.697405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13191","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35fc3f4032389e11cbacfa94a0d706ce130702f996c25d3a66743c3054aee4d0","sha256:908039ca75e6323339e59f845e5b2689c59c56fa4d39db99ede2b5e520b1476a"],"state_sha256":"c30c5c5949f28b808f3c8967666a7084612ac7439a1cdf852c0c8f59b1639185"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Js5M/6GvgKeF/3jmt2gFa62IY80U3tMAvYIm/qAt3NC2upVEff4EJpdniKXG6WDOuNhedoxD17uaOhqJEqJBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:14:31.545794Z","bundle_sha256":"dc1ed2b7e3cecf42fe9da65e0113ba54cb9ee7b8bab3851bd75b018627d85a6f"}}