{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NMCISW3CNABZGFGLISNJGUBA4G","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":"444df681f3ed21868407c7f22b9378650d07f8a02f0cb10f7e1e2bc4a7eeb8a4","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-13T17:35:26Z","title_canon_sha256":"ca7809fbb6036c695a69205da35bee9bb821d9ef8473d1800141b60dea3873e8"},"schema_version":"1.0","source":{"id":"2112.06825","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.06825","created_at":"2026-07-05T04:08:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.06825v2","created_at":"2026-07-05T04:08:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06825","created_at":"2026-07-05T04:08:17Z"},{"alias_kind":"pith_short_12","alias_value":"NMCISW3CNABZ","created_at":"2026-07-05T04:08:17Z"},{"alias_kind":"pith_short_16","alias_value":"NMCISW3CNABZGFGL","created_at":"2026-07-05T04:08:17Z"},{"alias_kind":"pith_short_8","alias_value":"NMCISW3C","created_at":"2026-07-05T04:08:17Z"}],"graph_snapshots":[{"event_id":"sha256:ca1325bed6bacf300ae3023a839aa558ba3d7550c55578a9af62b91cdd35b7d1","target":"graph","created_at":"2026-07-05T04:08:17Z","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/2112.06825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained models becomes impractical since the model size is growing rapidly. Hence, in this paper, we introduce adapter-based parameter-efficient transfer learning techniques to V&L models such as VL-BART and VLT5. We evaluate our methods in a unified multi-task setup on both image-text and video-text benchmarks. For the image-text tasks, we use four diverse V&L datasets:","authors_text":"Jaemin Cho, Mohit Bansal, Yi-Lin Sung","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-13T17:35:26Z","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06825","kind":"arxiv","version":2},"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":"sha256:4856f0fb2680816ff285c818533344d229d0f700d19ce5062afa68630e3979eb","target":"record","created_at":"2026-07-05T04:08:17Z","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":"444df681f3ed21868407c7f22b9378650d07f8a02f0cb10f7e1e2bc4a7eeb8a4","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-13T17:35:26Z","title_canon_sha256":"ca7809fbb6036c695a69205da35bee9bb821d9ef8473d1800141b60dea3873e8"},"schema_version":"1.0","source":{"id":"2112.06825","kind":"arxiv","version":2}},"canonical_sha256":"6b04895b6268039314cb449a935020e1a964c29eeedc2e2ff7d6bc638dc7734d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b04895b6268039314cb449a935020e1a964c29eeedc2e2ff7d6bc638dc7734d","first_computed_at":"2026-07-05T04:08:17.389008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:17.389008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LvkFeL8XbaSZefHo+1yly8E6GtiwAvD5kvchwsWIUS+evVVuBw+7PvT5+MljjqvWLYbFZ+u4GnNignqwIe9dBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:17.389440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.06825","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4856f0fb2680816ff285c818533344d229d0f700d19ce5062afa68630e3979eb","sha256:ca1325bed6bacf300ae3023a839aa558ba3d7550c55578a9af62b91cdd35b7d1"],"state_sha256":"733ecd47bd28c2d08e4a49b8771c3cb1405cf9bacc2ad63955f2e689e256c984"}