{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YPB2GQDVJRKGJL4MGNUEP7IUTB","short_pith_number":"pith:YPB2GQDV","schema_version":"1.0","canonical_sha256":"c3c3a340754c5464af8c336847fd149867da5bf2400f9097fe6f69c878a4430c","source":{"kind":"arxiv","id":"2210.14797","version":1},"attestation_state":"computed","paper":{"title":"Is Multi-Task Learning an Upper Bound for Continual Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hamed Pirsiavash, Huy Tran, Soheil Kolouri, Zihao Wu","submitted_at":"2022-10-26T15:45:11Z","abstract_excerpt":"Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a sensible performance upper bound for various continual learning algorithms. While this assumption is empirically verified for different continual learning benchmarks, it is not rigorously justified. Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting. In contrast, continual"},"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":"2210.14797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-26T15:45:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fcde9f6666569be02f42caaf47435b07bbb6282a01532d74a4e02d1520fefa14","abstract_canon_sha256":"1e0677ea556cdbf7adf6652a3355fbc788e93b9d2d11f8276e8727031069b253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:49.858563Z","signature_b64":"mHAHRHgfF1AOp6DK56Rvgjuz9fV1vFvsnWj1fKX5h/kqEEbqi7dwVhPuuLMiQsA/kLU3VlY6xrkgV1sRsSzjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3c3a340754c5464af8c336847fd149867da5bf2400f9097fe6f69c878a4430c","last_reissued_at":"2026-07-05T05:10:49.858215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:49.858215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Multi-Task Learning an Upper Bound for Continual Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hamed Pirsiavash, Huy Tran, Soheil Kolouri, Zihao Wu","submitted_at":"2022-10-26T15:45:11Z","abstract_excerpt":"Continual and multi-task learning are common machine learning approaches to learning from multiple tasks. The existing works in the literature often assume multi-task learning as a sensible performance upper bound for various continual learning algorithms. While this assumption is empirically verified for different continual learning benchmarks, it is not rigorously justified. Moreover, it is imaginable that when learning from multiple tasks, a small subset of these tasks could behave as adversarial tasks reducing the overall learning performance in a multi-task setting. In contrast, continual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14797","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/2210.14797/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":"2210.14797","created_at":"2026-07-05T05:10:49.858271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14797v1","created_at":"2026-07-05T05:10:49.858271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14797","created_at":"2026-07-05T05:10:49.858271+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPB2GQDVJRKG","created_at":"2026-07-05T05:10:49.858271+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPB2GQDVJRKGJL4M","created_at":"2026-07-05T05:10:49.858271+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPB2GQDV","created_at":"2026-07-05T05:10:49.858271+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/YPB2GQDVJRKGJL4MGNUEP7IUTB","json":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB.json","graph_json":"https://pith.science/api/pith-number/YPB2GQDVJRKGJL4MGNUEP7IUTB/graph.json","events_json":"https://pith.science/api/pith-number/YPB2GQDVJRKGJL4MGNUEP7IUTB/events.json","paper":"https://pith.science/paper/YPB2GQDV"},"agent_actions":{"view_html":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB","download_json":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB.json","view_paper":"https://pith.science/paper/YPB2GQDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14797&json=true","fetch_graph":"https://pith.science/api/pith-number/YPB2GQDVJRKGJL4MGNUEP7IUTB/graph.json","fetch_events":"https://pith.science/api/pith-number/YPB2GQDVJRKGJL4MGNUEP7IUTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB/action/storage_attestation","attest_author":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB/action/author_attestation","sign_citation":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB/action/citation_signature","submit_replication":"https://pith.science/pith/YPB2GQDVJRKGJL4MGNUEP7IUTB/action/replication_record"}},"created_at":"2026-07-05T05:10:49.858271+00:00","updated_at":"2026-07-05T05:10:49.858271+00:00"}