{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SXQYONST5L3BAT3J6TI4MKUE4A","short_pith_number":"pith:SXQYONST","canonical_record":{"source":{"id":"1806.08568","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T09:22:42Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"cd458ecf9162d9939f3f30312b3c4a217538551f5a9809f5edfa2eeffb6b40fd","abstract_canon_sha256":"cc6319ced1e0023ea9fb920c4793a16d4789ec7cd51e64f4b75365885f213f18"},"schema_version":"1.0"},"canonical_sha256":"95e1873653eaf6104f69f4d1c62a84e02ff8d742e6f2b925404666b5bd8e5892","source":{"kind":"arxiv","id":"1806.08568","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08568","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08568v3","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08568","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"SXQYONST5L3B","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SXQYONST5L3BAT3J","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SXQYONST","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SXQYONST5L3BAT3J6TI4MKUE4A","target":"record","payload":{"canonical_record":{"source":{"id":"1806.08568","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T09:22:42Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"cd458ecf9162d9939f3f30312b3c4a217538551f5a9809f5edfa2eeffb6b40fd","abstract_canon_sha256":"cc6319ced1e0023ea9fb920c4793a16d4789ec7cd51e64f4b75365885f213f18"},"schema_version":"1.0"},"canonical_sha256":"95e1873653eaf6104f69f4d1c62a84e02ff8d742e6f2b925404666b5bd8e5892","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:42.750983Z","signature_b64":"T3bqU30ZfYbT4ZapvbRzw4OXhQnTR84mfLkVPFKEyvPqFft0DPVSZT6QrBn+3oYdogV5RTrdvzw4wl6JFrQQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95e1873653eaf6104f69f4d1c62a84e02ff8d742e6f2b925404666b5bd8e5892","last_reissued_at":"2026-05-17T23:55:42.750370Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:42.750370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.08568","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":"2026-05-17T23:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sbw4aUam3JVPbCjZLqdsjEkfDV11MUECYDs36yLYmpRJngSc3CUhurg6mOUSH1M1ryIyYJn5RS3pvUDDoC9NDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:10:39.016787Z"},"content_sha256":"9bdcaf9d2461a61ed1e23280f527aca8a26d7acfce5e8c488ccfd112598bfa42","schema_version":"1.0","event_id":"sha256:9bdcaf9d2461a61ed1e23280f527aca8a26d7acfce5e8c488ccfd112598bfa42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SXQYONST5L3BAT3J6TI4MKUE4A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continuous Learning in Single-Incremental-Task Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Davide Maltoni, Vincenzo Lomonaco","submitted_at":"2018-06-22T09:22:42Z","abstract_excerpt":"It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LWF, EWC and SI are not ideal for incremental task scenarios. A new approach, denoted as A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08568","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":""},"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":"2026-05-17T23:55:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uuHpFr4Frh2bdDlfaKtNTquHT+juDJhgkyp8WXmB70qS5ZyhikFoHrdXVXvzMoIserQoVUDZDMn2+pyYTUuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:10:39.017405Z"},"content_sha256":"e86ac77a9b50d62118581582d121ab50802e798ebcc6e9b3c630542d42728a59","schema_version":"1.0","event_id":"sha256:e86ac77a9b50d62118581582d121ab50802e798ebcc6e9b3c630542d42728a59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXQYONST5L3BAT3J6TI4MKUE4A/bundle.json","state_url":"https://pith.science/pith/SXQYONST5L3BAT3J6TI4MKUE4A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXQYONST5L3BAT3J6TI4MKUE4A/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":"2026-05-27T14:10:39Z","links":{"resolver":"https://pith.science/pith/SXQYONST5L3BAT3J6TI4MKUE4A","bundle":"https://pith.science/pith/SXQYONST5L3BAT3J6TI4MKUE4A/bundle.json","state":"https://pith.science/pith/SXQYONST5L3BAT3J6TI4MKUE4A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXQYONST5L3BAT3J6TI4MKUE4A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SXQYONST5L3BAT3J6TI4MKUE4A","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":"cc6319ced1e0023ea9fb920c4793a16d4789ec7cd51e64f4b75365885f213f18","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T09:22:42Z","title_canon_sha256":"cd458ecf9162d9939f3f30312b3c4a217538551f5a9809f5edfa2eeffb6b40fd"},"schema_version":"1.0","source":{"id":"1806.08568","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.08568","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.08568v3","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08568","created_at":"2026-05-17T23:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"SXQYONST5L3B","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SXQYONST5L3BAT3J","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SXQYONST","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:e86ac77a9b50d62118581582d121ab50802e798ebcc6e9b3c630542d42728a59","target":"graph","created_at":"2026-05-17T23:55:42Z","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"},"paper":{"abstract_excerpt":"It was recently shown that architectural, regularization and rehearsal strategies can be used to train deep models sequentially on a number of disjoint tasks without forgetting previously acquired knowledge. However, these strategies are still unsatisfactory if the tasks are not disjoint but constitute a single incremental task (e.g., class-incremental learning). In this paper we point out the differences between multi-task and single-incremental-task scenarios and show that well-known approaches such as LWF, EWC and SI are not ideal for incremental task scenarios. A new approach, denoted as A","authors_text":"Davide Maltoni, Vincenzo Lomonaco","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T09:22:42Z","title":"Continuous Learning in Single-Incremental-Task Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08568","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":"sha256:9bdcaf9d2461a61ed1e23280f527aca8a26d7acfce5e8c488ccfd112598bfa42","target":"record","created_at":"2026-05-17T23:55:42Z","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":"cc6319ced1e0023ea9fb920c4793a16d4789ec7cd51e64f4b75365885f213f18","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-22T09:22:42Z","title_canon_sha256":"cd458ecf9162d9939f3f30312b3c4a217538551f5a9809f5edfa2eeffb6b40fd"},"schema_version":"1.0","source":{"id":"1806.08568","kind":"arxiv","version":3}},"canonical_sha256":"95e1873653eaf6104f69f4d1c62a84e02ff8d742e6f2b925404666b5bd8e5892","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95e1873653eaf6104f69f4d1c62a84e02ff8d742e6f2b925404666b5bd8e5892","first_computed_at":"2026-05-17T23:55:42.750370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:42.750370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T3bqU30ZfYbT4ZapvbRzw4OXhQnTR84mfLkVPFKEyvPqFft0DPVSZT6QrBn+3oYdogV5RTrdvzw4wl6JFrQQBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:42.750983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.08568","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bdcaf9d2461a61ed1e23280f527aca8a26d7acfce5e8c488ccfd112598bfa42","sha256:e86ac77a9b50d62118581582d121ab50802e798ebcc6e9b3c630542d42728a59"],"state_sha256":"e7c612b6b44ecd0f0eb6288dd773f700051b590797e12eb3a7a935f30bd43a24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M8vuP49c1wvo/UdN/INSG3IEBP/bgvPpJUoUGStJbJoHHLJZEIDs+I72xCoBFjnAmgBTd1LzxW/YcmQajLR2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:10:39.021352Z","bundle_sha256":"b06b4545ca03b750390c030c80c56b4dc27a0c2198abd0a918762fe6a701c2ca"}}