{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QVOUXMUUSPGMF3RUKESSQR5D7M","short_pith_number":"pith:QVOUXMUU","schema_version":"1.0","canonical_sha256":"855d4bb29493ccc2ee3451252847a3fb0b1cb431e935b2b9c4d266de60d6b2a6","source":{"kind":"arxiv","id":"2210.00044","version":2},"attestation_state":"computed","paper":{"title":"Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Suglia, Ioannis Konstas, Lu Yu, Mavina Nikandrou, Verena Rieser","submitted_at":"2022-09-30T19:12:58Z","abstract_excerpt":"Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not that straightforward, as settings can be parameterized in multiple ways according to their input modalities. In this paper, we present a detailed study of how different settings affect performance for Visual Question Answering. We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms. We"},"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":"2210.00044","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T19:12:58Z","cross_cats_sorted":[],"title_canon_sha256":"a298ad1770d2c1a710de9d20a735ce4a0c98e2c789ba8a348299b19e9f5ab041","abstract_canon_sha256":"1b46173566685832e5acb95586c7152bc9b46650247df2f687fcedaf99ea1e62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:35.345660Z","signature_b64":"8VZE7ayhKOpac1vlFM6+m7eR/R69hFFK1XDYm2FRThjidMO2uHJS+AF1eYZBx1cIcMDsOpXvVRofvU8meEnxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"855d4bb29493ccc2ee3451252847a3fb0b1cb431e935b2b9c4d266de60d6b2a6","last_reissued_at":"2026-07-05T07:35:35.345224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:35.345224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Suglia, Ioannis Konstas, Lu Yu, Mavina Nikandrou, Verena Rieser","submitted_at":"2022-09-30T19:12:58Z","abstract_excerpt":"Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not that straightforward, as settings can be parameterized in multiple ways according to their input modalities. In this paper, we present a detailed study of how different settings affect performance for Visual Question Answering. We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00044","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/2210.00044/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":"2210.00044","created_at":"2026-07-05T07:35:35.345284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00044v2","created_at":"2026-07-05T07:35:35.345284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00044","created_at":"2026-07-05T07:35:35.345284+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVOUXMUUSPGM","created_at":"2026-07-05T07:35:35.345284+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVOUXMUUSPGMF3RU","created_at":"2026-07-05T07:35:35.345284+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVOUXMUU","created_at":"2026-07-05T07:35:35.345284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04469","citing_title":"Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M","json":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M.json","graph_json":"https://pith.science/api/pith-number/QVOUXMUUSPGMF3RUKESSQR5D7M/graph.json","events_json":"https://pith.science/api/pith-number/QVOUXMUUSPGMF3RUKESSQR5D7M/events.json","paper":"https://pith.science/paper/QVOUXMUU"},"agent_actions":{"view_html":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M","download_json":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M.json","view_paper":"https://pith.science/paper/QVOUXMUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00044&json=true","fetch_graph":"https://pith.science/api/pith-number/QVOUXMUUSPGMF3RUKESSQR5D7M/graph.json","fetch_events":"https://pith.science/api/pith-number/QVOUXMUUSPGMF3RUKESSQR5D7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M/action/storage_attestation","attest_author":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M/action/author_attestation","sign_citation":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M/action/citation_signature","submit_replication":"https://pith.science/pith/QVOUXMUUSPGMF3RUKESSQR5D7M/action/replication_record"}},"created_at":"2026-07-05T07:35:35.345284+00:00","updated_at":"2026-07-05T07:35:35.345284+00:00"}