{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3LFSYMLJU5AGI25OYZAE2Q4WDO","short_pith_number":"pith:3LFSYMLJ","schema_version":"1.0","canonical_sha256":"dacb2c3169a740646baec6404d43961ba3094253ec998c14a372848159448097","source":{"kind":"arxiv","id":"2104.01678","version":2},"attestation_state":"computed","paper":{"title":"Understanding Continual Learning Settings with Data Distribution Drift Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irina Rish, Massimo Caccia, Timoth\\'ee Lesort","submitted_at":"2021-04-04T19:48:16Z","abstract_excerpt":"Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this assumption is relaxed, i.e. where the data distribution is non-stationary and changes over time. This paper represents the state of data distribution by a context variable $c$. A drift in $c$ leads to a data distribution drift.\n  A context drift may change the target distribution, the input distribution, or both. Moreover, distribution drifts might be abrupt or gradual. In cont"},"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":"2104.01678","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-04T19:48:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff92db4b51c18079942c5fd0bbc495ab72a023559e2907ffcfa4bcfbdd1b6ac4","abstract_canon_sha256":"ba4dc0680398df00ee69b84e16b1a3f876516d8ecd182d0e418ac5fa4ff02908"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:42.358657Z","signature_b64":"EfMmFl4+6o8GgblocIGenetJH8M+rCZ3vRSpRa1J7JcC73PFxH56St/oYbbEkUGUGYeJ3vkNarrhLFC+05MlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dacb2c3169a740646baec6404d43961ba3094253ec998c14a372848159448097","last_reissued_at":"2026-07-05T04:38:42.358224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:42.358224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Continual Learning Settings with Data Distribution Drift Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irina Rish, Massimo Caccia, Timoth\\'ee Lesort","submitted_at":"2021-04-04T19:48:16Z","abstract_excerpt":"Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this assumption is relaxed, i.e. where the data distribution is non-stationary and changes over time. This paper represents the state of data distribution by a context variable $c$. A drift in $c$ leads to a data distribution drift.\n  A context drift may change the target distribution, the input distribution, or both. Moreover, distribution drifts might be abrupt or gradual. In cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01678","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/2104.01678/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.01678","created_at":"2026-07-05T04:38:42.358277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01678v2","created_at":"2026-07-05T04:38:42.358277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01678","created_at":"2026-07-05T04:38:42.358277+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LFSYMLJU5AG","created_at":"2026-07-05T04:38:42.358277+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LFSYMLJU5AGI25O","created_at":"2026-07-05T04:38:42.358277+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LFSYMLJ","created_at":"2026-07-05T04:38:42.358277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04020","citing_title":"Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO","json":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO.json","graph_json":"https://pith.science/api/pith-number/3LFSYMLJU5AGI25OYZAE2Q4WDO/graph.json","events_json":"https://pith.science/api/pith-number/3LFSYMLJU5AGI25OYZAE2Q4WDO/events.json","paper":"https://pith.science/paper/3LFSYMLJ"},"agent_actions":{"view_html":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO","download_json":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO.json","view_paper":"https://pith.science/paper/3LFSYMLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01678&json=true","fetch_graph":"https://pith.science/api/pith-number/3LFSYMLJU5AGI25OYZAE2Q4WDO/graph.json","fetch_events":"https://pith.science/api/pith-number/3LFSYMLJU5AGI25OYZAE2Q4WDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO/action/storage_attestation","attest_author":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO/action/author_attestation","sign_citation":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO/action/citation_signature","submit_replication":"https://pith.science/pith/3LFSYMLJU5AGI25OYZAE2Q4WDO/action/replication_record"}},"created_at":"2026-07-05T04:38:42.358277+00:00","updated_at":"2026-07-05T04:38:42.358277+00:00"}