{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LA2KRWBZAXGEMLUA4SZDYA256S","short_pith_number":"pith:LA2KRWBZ","schema_version":"1.0","canonical_sha256":"5834a8d83905cc462e80e4b23c035df4a0c917cf1641631d7cd3deb748439b16","source":{"kind":"arxiv","id":"2303.14423","version":1},"attestation_state":"computed","paper":{"title":"Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jesse Thomason, Mohammad Rostami, Yuliang Cai","submitted_at":"2023-03-25T10:16:53Z","abstract_excerpt":"The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy through enabling knowledge-transfer across sequentially arriving tasks which relaxes the need to fine-tune all network weights from scratch. However, existing CL algorithms primarily consider learning unimodal vision-only or language-only tasks. We develop a transformer-based CL architecture for learning bimodal vision-and-language tasks based on increasing the number of the le"},"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":"2303.14423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-25T10:16:53Z","cross_cats_sorted":[],"title_canon_sha256":"e334efbc27f8c66090101f99d9513708f617e95e1ab4dbb104c3b8d4e64fefcd","abstract_canon_sha256":"226ff1cf7983aa347b85bdc0af0a61b40aebed942ba502bc0d1fb64a5a06522b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:41.411278Z","signature_b64":"iareYg52OI93JVHDBhOIGvlaxfbAyVHHfmtuDLG0ODIZ5OXahHIMRgxM/UVba2e1oqncZGILUJYcyZTg/rrUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5834a8d83905cc462e80e4b23c035df4a0c917cf1641631d7cd3deb748439b16","last_reissued_at":"2026-07-05T05:54:41.410859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:41.410859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Attentive Transformer Architecture for Continual Learning of Vision-and-Language Tasks Using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jesse Thomason, Mohammad Rostami, Yuliang Cai","submitted_at":"2023-03-25T10:16:53Z","abstract_excerpt":"The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy through enabling knowledge-transfer across sequentially arriving tasks which relaxes the need to fine-tune all network weights from scratch. However, existing CL algorithms primarily consider learning unimodal vision-only or language-only tasks. We develop a transformer-based CL architecture for learning bimodal vision-and-language tasks based on increasing the number of the le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14423","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/2303.14423/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":"2303.14423","created_at":"2026-07-05T05:54:41.410916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14423v1","created_at":"2026-07-05T05:54:41.410916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14423","created_at":"2026-07-05T05:54:41.410916+00:00"},{"alias_kind":"pith_short_12","alias_value":"LA2KRWBZAXGE","created_at":"2026-07-05T05:54:41.410916+00:00"},{"alias_kind":"pith_short_16","alias_value":"LA2KRWBZAXGEMLUA","created_at":"2026-07-05T05:54:41.410916+00:00"},{"alias_kind":"pith_short_8","alias_value":"LA2KRWBZ","created_at":"2026-07-05T05:54:41.410916+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/LA2KRWBZAXGEMLUA4SZDYA256S","json":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S.json","graph_json":"https://pith.science/api/pith-number/LA2KRWBZAXGEMLUA4SZDYA256S/graph.json","events_json":"https://pith.science/api/pith-number/LA2KRWBZAXGEMLUA4SZDYA256S/events.json","paper":"https://pith.science/paper/LA2KRWBZ"},"agent_actions":{"view_html":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S","download_json":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S.json","view_paper":"https://pith.science/paper/LA2KRWBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14423&json=true","fetch_graph":"https://pith.science/api/pith-number/LA2KRWBZAXGEMLUA4SZDYA256S/graph.json","fetch_events":"https://pith.science/api/pith-number/LA2KRWBZAXGEMLUA4SZDYA256S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S/action/storage_attestation","attest_author":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S/action/author_attestation","sign_citation":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S/action/citation_signature","submit_replication":"https://pith.science/pith/LA2KRWBZAXGEMLUA4SZDYA256S/action/replication_record"}},"created_at":"2026-07-05T05:54:41.410916+00:00","updated_at":"2026-07-05T05:54:41.410916+00:00"}