{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R7P6SNKTOWMFA4QZWHD5BVOXXZ","short_pith_number":"pith:R7P6SNKT","schema_version":"1.0","canonical_sha256":"8fdfe935537598507219b1c7d0d5d7be4657d266bb2d33e37d27c67c91a843a6","source":{"kind":"arxiv","id":"2210.03794","version":1},"attestation_state":"computed","paper":{"title":"SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gabriel Brostow, Kate Jones, Oisin Mac Aodha, Omiros Pantazis","submitted_at":"2022-10-07T19:35:08Z","abstract_excerpt":"Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their size, fine-tuning these models on new datasets can be prohibitively expensive, both in terms of the supervision and compute required. To combat this, a series of light-weight adaptation methods have been proposed to efficiently adapt such models when limited supervision is available. In this work, we show that while effective on internet-style datasets, even th"},"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":"2210.03794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-07T19:35:08Z","cross_cats_sorted":[],"title_canon_sha256":"016c01555f39e29b1d5cabe12fc7e57aca49b6fae9aed82a9c00a79e005cc7ce","abstract_canon_sha256":"55610b26ba87c5a27a4816ef813b9fc13283cb690283e986728b9790d664654b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:32.300829Z","signature_b64":"axrwOlJOCnwGuAYehcUJBanFRPScrtXA15lmdsVuHN8yUDNBsRDZ9wsmuDlUSmdqHoNVqok0Jkkukc8bdPfPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fdfe935537598507219b1c7d0d5d7be4657d266bb2d33e37d27c67c91a843a6","last_reissued_at":"2026-07-05T05:04:32.300390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:32.300390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gabriel Brostow, Kate Jones, Oisin Mac Aodha, Omiros Pantazis","submitted_at":"2022-10-07T19:35:08Z","abstract_excerpt":"Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their size, fine-tuning these models on new datasets can be prohibitively expensive, both in terms of the supervision and compute required. To combat this, a series of light-weight adaptation methods have been proposed to efficiently adapt such models when limited supervision is available. In this work, we show that while effective on internet-style datasets, even th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03794","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/2210.03794/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":"2210.03794","created_at":"2026-07-05T05:04:32.300445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03794v1","created_at":"2026-07-05T05:04:32.300445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03794","created_at":"2026-07-05T05:04:32.300445+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7P6SNKTOWMF","created_at":"2026-07-05T05:04:32.300445+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7P6SNKTOWMFA4QZ","created_at":"2026-07-05T05:04:32.300445+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7P6SNKT","created_at":"2026-07-05T05:04:32.300445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19346","citing_title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ","json":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ.json","graph_json":"https://pith.science/api/pith-number/R7P6SNKTOWMFA4QZWHD5BVOXXZ/graph.json","events_json":"https://pith.science/api/pith-number/R7P6SNKTOWMFA4QZWHD5BVOXXZ/events.json","paper":"https://pith.science/paper/R7P6SNKT"},"agent_actions":{"view_html":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ","download_json":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ.json","view_paper":"https://pith.science/paper/R7P6SNKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03794&json=true","fetch_graph":"https://pith.science/api/pith-number/R7P6SNKTOWMFA4QZWHD5BVOXXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/R7P6SNKTOWMFA4QZWHD5BVOXXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ/action/storage_attestation","attest_author":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ/action/author_attestation","sign_citation":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ/action/citation_signature","submit_replication":"https://pith.science/pith/R7P6SNKTOWMFA4QZWHD5BVOXXZ/action/replication_record"}},"created_at":"2026-07-05T05:04:32.300445+00:00","updated_at":"2026-07-05T05:04:32.300445+00:00"}