{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZBEJ4UYPBVVIH4OIP5SSJUPOWO","short_pith_number":"pith:ZBEJ4UYP","schema_version":"1.0","canonical_sha256":"c8489e530f0d6a83f1c87f6524d1eeb38cd5bad4ceaa57d92ff08d52d716c598","source":{"kind":"arxiv","id":"2503.20612","version":2},"attestation_state":"computed","paper":{"title":"IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Hanbin Zhao, Hao Fu, Henghui Ding, Hui Qian, Jiahua Dong","submitted_at":"2025-03-26T14:59:23Z","abstract_excerpt":"Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to previously seen tasks and unseen tasks, memory-constrained MTIL suffers from forward and backward forgetting. To alleviate the above challenges, parameter-efficient fine-tuning techniques (PEFT), such as prompt tuning, are employed to adapt the PT-VLM to the diverse incrementally learned tasks. To achieve effective new task adaptation, existing methods only conside"},"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":"2503.20612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-26T14:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"a60ba129d16fbd25b68b516a8d308c0e007a627a59f2bf46a2d76ff81a3d30e1","abstract_canon_sha256":"da1d2c875fa0c13c869ddb30dbd68fa47c2b128ab90c8b7fcbc80108b4291c39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:44.507884Z","signature_b64":"sRjMRiKQheAifB2XP6pIXhy9ANs7NpNH2O+UwcCtIEzv1/iOR7Sghxv7rgcA34F6+zojtFag8yde+m85mmPGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8489e530f0d6a83f1c87f6524d1eeb38cd5bad4ceaa57d92ff08d52d716c598","last_reissued_at":"2026-07-05T11:31:44.507383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:44.507383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhang, Hanbin Zhao, Hao Fu, Henghui Ding, Hui Qian, Jiahua Dong","submitted_at":"2025-03-26T14:59:23Z","abstract_excerpt":"Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to previously seen tasks and unseen tasks, memory-constrained MTIL suffers from forward and backward forgetting. To alleviate the above challenges, parameter-efficient fine-tuning techniques (PEFT), such as prompt tuning, are employed to adapt the PT-VLM to the diverse incrementally learned tasks. To achieve effective new task adaptation, existing methods only conside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20612","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/2503.20612/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":"2503.20612","created_at":"2026-07-05T11:31:44.507443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20612v2","created_at":"2026-07-05T11:31:44.507443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20612","created_at":"2026-07-05T11:31:44.507443+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBEJ4UYPBVVI","created_at":"2026-07-05T11:31:44.507443+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBEJ4UYPBVVIH4OI","created_at":"2026-07-05T11:31:44.507443+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBEJ4UYP","created_at":"2026-07-05T11:31:44.507443+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/ZBEJ4UYPBVVIH4OIP5SSJUPOWO","json":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO.json","graph_json":"https://pith.science/api/pith-number/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/graph.json","events_json":"https://pith.science/api/pith-number/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/events.json","paper":"https://pith.science/paper/ZBEJ4UYP"},"agent_actions":{"view_html":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO","download_json":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO.json","view_paper":"https://pith.science/paper/ZBEJ4UYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20612&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/action/storage_attestation","attest_author":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/action/author_attestation","sign_citation":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/action/citation_signature","submit_replication":"https://pith.science/pith/ZBEJ4UYPBVVIH4OIP5SSJUPOWO/action/replication_record"}},"created_at":"2026-07-05T11:31:44.507443+00:00","updated_at":"2026-07-05T11:31:44.507443+00:00"}