{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AXZMJVULAWD32ITFG76W5ATZC4","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":"6dc2e32c8d5c7ff21671e9c9ae3d824b6c935cdd1eed77997252349229d2fde4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T16:15:30Z","title_canon_sha256":"192d0cc969c69ddf2f89df5becda016b9b1bdd77919decbd00cf3d8e1d54f37c"},"schema_version":"1.0","source":{"id":"2211.09623","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09623","created_at":"2026-07-05T12:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09623v2","created_at":"2026-07-05T12:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09623","created_at":"2026-07-05T12:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"AXZMJVULAWD3","created_at":"2026-07-05T12:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"AXZMJVULAWD32ITF","created_at":"2026-07-05T12:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"AXZMJVUL","created_at":"2026-07-05T12:01:51Z"}],"graph_snapshots":[{"event_id":"sha256:62b8d4f73c16177b9b508de54f75c641b86cf014ce96a7dae6d6ae9d3bc1d30b","target":"graph","created_at":"2026-07-05T12:01:51Z","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/2211.09623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval tasks. However, as pre-trained models are scaling up, fully fine-tuning them on donwstream retrieval datasets has a high risk of overfitting. Moreover, in practice, it would be costly to train and store a large model for each task. To overcome the above issues, we present a novel Cross-Modal Adapter for parameter-efficient transfer learning. Inspired by adapter-b","authors_text":"Chunjiang Ge, Gao Huang, Haojun Jiang, Jianke Zhang, Rui Huang, Shiji Song, Zanlin Ni","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T16:15:30Z","title":"Cross-Modal Adapter for Vision-Language Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09623","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":"sha256:080076bd66a7c9e9d08857e8baadb1be275d3eeb263d22981f1134dbfc02c059","target":"record","created_at":"2026-07-05T12:01:51Z","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":"6dc2e32c8d5c7ff21671e9c9ae3d824b6c935cdd1eed77997252349229d2fde4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T16:15:30Z","title_canon_sha256":"192d0cc969c69ddf2f89df5becda016b9b1bdd77919decbd00cf3d8e1d54f37c"},"schema_version":"1.0","source":{"id":"2211.09623","kind":"arxiv","version":2}},"canonical_sha256":"05f2c4d68b0587bd226537fd6e827917344f4e1c96e097acb2a104be3fb10658","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05f2c4d68b0587bd226537fd6e827917344f4e1c96e097acb2a104be3fb10658","first_computed_at":"2026-07-05T12:01:51.817505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:51.817505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u7vZO0mI45tLV3P3OdgCjUCKEvpMScSu1LRCmBdfSO0E5AqbvZPMOFUSQtw0Ah3mY4fQMGC4KL5eK7KF5kl3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:51.817977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09623","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:080076bd66a7c9e9d08857e8baadb1be275d3eeb263d22981f1134dbfc02c059","sha256:62b8d4f73c16177b9b508de54f75c641b86cf014ce96a7dae6d6ae9d3bc1d30b"],"state_sha256":"a9d0d2efad6e20d4843a71a98ad7c204b92c4cc64485bddeeaf6c99d50f3e107"}