{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NLHXVGNPFUHE2UK2W53D2KFV7B","short_pith_number":"pith:NLHXVGNP","schema_version":"1.0","canonical_sha256":"6acf7a99af2d0e4d515ab7763d28b5f86135fb302c3ce582f7317f5b64bdd7ff","source":{"kind":"arxiv","id":"1812.09111","version":1},"attestation_state":"computed","paper":{"title":"Generative Models from the perspective of Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrei Stoian, David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz, Timoth\\'ee Lesort","submitted_at":"2018-12-21T13:35:32Z","abstract_excerpt":"Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We used two quantitative metrics to estimate the generation quality and memory ability. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10). We found that among all models, the original GAN performs be"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.09111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-21T13:35:32Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2077bc663565b3148f16f81c63e7d1d232b527276a612ed61cab4180167e4117","abstract_canon_sha256":"dcb3237f7f6547af3a89ea77937f406b16ba58519c620d3875606ce4a8da5edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:45.378985Z","signature_b64":"XgicavK9/wKFGy5BOWxggDDUas+En9WRrZoGw6p7EQBI4/Kj8uk6dq022l8na3/BlpRIgT/3iHwX6MebGoPgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6acf7a99af2d0e4d515ab7763d28b5f86135fb302c3ce582f7317f5b64bdd7ff","last_reissued_at":"2026-05-17T23:57:45.378400Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:45.378400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Models from the perspective of Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Andrei Stoian, David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz, Timoth\\'ee Lesort","submitted_at":"2018-12-21T13:35:32Z","abstract_excerpt":"Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We used two quantitative metrics to estimate the generation quality and memory ability. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10). We found that among all models, the original GAN performs be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09111","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.09111","created_at":"2026-05-17T23:57:45.378498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09111v1","created_at":"2026-05-17T23:57:45.378498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09111","created_at":"2026-05-17T23:57:45.378498+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLHXVGNPFUHE","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLHXVGNPFUHE2UK2","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLHXVGNP","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B","json":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B.json","graph_json":"https://pith.science/api/pith-number/NLHXVGNPFUHE2UK2W53D2KFV7B/graph.json","events_json":"https://pith.science/api/pith-number/NLHXVGNPFUHE2UK2W53D2KFV7B/events.json","paper":"https://pith.science/paper/NLHXVGNP"},"agent_actions":{"view_html":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B","download_json":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B.json","view_paper":"https://pith.science/paper/NLHXVGNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09111&json=true","fetch_graph":"https://pith.science/api/pith-number/NLHXVGNPFUHE2UK2W53D2KFV7B/graph.json","fetch_events":"https://pith.science/api/pith-number/NLHXVGNPFUHE2UK2W53D2KFV7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B/action/storage_attestation","attest_author":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B/action/author_attestation","sign_citation":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B/action/citation_signature","submit_replication":"https://pith.science/pith/NLHXVGNPFUHE2UK2W53D2KFV7B/action/replication_record"}},"created_at":"2026-05-17T23:57:45.378498+00:00","updated_at":"2026-05-17T23:57:45.378498+00:00"}