{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YMTD3GGPDAMX2ZVENVNXRSBGJZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d9679144d90ce262fddf8633d647442465fe37bf9d94294ae18bdbc29a92c517","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T10:45:03Z","title_canon_sha256":"1a77b14946c98c9a51bab92fe921624035b9854248cbb87d35c05fe20917c8d5"},"schema_version":"1.0","source":{"id":"2310.20348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20348","created_at":"2026-07-05T07:07:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20348v1","created_at":"2026-07-05T07:07:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20348","created_at":"2026-07-05T07:07:28Z"},{"alias_kind":"pith_short_12","alias_value":"YMTD3GGPDAMX","created_at":"2026-07-05T07:07:28Z"},{"alias_kind":"pith_short_16","alias_value":"YMTD3GGPDAMX2ZVE","created_at":"2026-07-05T07:07:28Z"},{"alias_kind":"pith_short_8","alias_value":"YMTD3GGP","created_at":"2026-07-05T07:07:28Z"}],"graph_snapshots":[{"event_id":"sha256:43f525f59f6a75579d691e44e5b6504c5d92ac25df895f16157a10e45e194b78","target":"graph","created_at":"2026-07-05T07:07:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.20348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown.\n  In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation instead of only using zero-shot learning of new tasks. We augment a pre-trained CLIP model with additional layers after the Image Encoder or before the Text Encoder. We investigate three different strategies: a Linear Adapter, a Self-attention Adapter, each operating on the image embedding, and Prompt Tuning which instead modifie","authors_text":"Andrew D. Bagdanov, Haori Lu, Jia-Wen Xiao, Ming-Ming Cheng, Xialei Liu, Xusheng Cao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T10:45:03Z","title":"Class Incremental Learning with Pre-trained Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20348","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a485830fc2a12a014fd094d80001d132b9a5765392bb296b06a84c38580bc7a","target":"record","created_at":"2026-07-05T07:07:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d9679144d90ce262fddf8633d647442465fe37bf9d94294ae18bdbc29a92c517","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-31T10:45:03Z","title_canon_sha256":"1a77b14946c98c9a51bab92fe921624035b9854248cbb87d35c05fe20917c8d5"},"schema_version":"1.0","source":{"id":"2310.20348","kind":"arxiv","version":1}},"canonical_sha256":"c3263d98cf18197d66a46d5b78c8264e4a4f917b618ee81a624a7b644e4be9fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3263d98cf18197d66a46d5b78c8264e4a4f917b618ee81a624a7b644e4be9fc","first_computed_at":"2026-07-05T07:07:28.881250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:28.881250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JYdJRwkfrvNYsdK6W0EtK74EtRQ/0HjqmDOXpjKdvWL5zdL70kMOMynssIBskGPt68xVW8y3sni3QpBaOMKnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:28.881737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a485830fc2a12a014fd094d80001d132b9a5765392bb296b06a84c38580bc7a","sha256:43f525f59f6a75579d691e44e5b6504c5d92ac25df895f16157a10e45e194b78"],"state_sha256":"53b12866f1030571d5212d202a67275520e9673b7e02048bf12c806013b453e3"}