{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:65OEXJD763SHTRMMXEMTGFIF47","short_pith_number":"pith:65OEXJD7","schema_version":"1.0","canonical_sha256":"f75c4ba47ff6e479c58cb919331505e7cefea9a33cda3d85775ba59680eeb299","source":{"kind":"arxiv","id":"2412.16777","version":1},"attestation_state":"computed","paper":{"title":"HyperCLIP: Adapting Vision-Language models with Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Bair, Devin Willmott, J. Zico Kolter, Madan Ravi Ganesh, Mohammad Sadegh Norouzzadeh, Victor Akinwande","submitted_at":"2024-12-21T21:19:08Z","abstract_excerpt":"Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to train them, but they require correspondingly large vision components to properly learn powerful and general representations from such a broad data domain. This poses a challenge for deploying large vision-language models, especially in resource-constrained environments. To address this, we propose an alternate vision-language architecture, called HyperCLIP, tha"},"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":"2412.16777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-21T21:19:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"79d95dc02e208c3086d2eb56ca77cb736767f95bd056b58ca8c1c287d26b11e1","abstract_canon_sha256":"ff373137285c38ba234828998b6a067d120bde5902c9aa199b4134f2b4d4d213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:12.992915Z","signature_b64":"yYT6NurAMqljt8Sl1az8haAqOjUG5qXHzv3kARdfT75b/xu+cgmedu3Mh1jeW6sUY5LwjcQZnJHVTL2mWz+oBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f75c4ba47ff6e479c58cb919331505e7cefea9a33cda3d85775ba59680eeb299","last_reissued_at":"2026-07-05T09:53:12.992468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:12.992468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperCLIP: Adapting Vision-Language models with Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Bair, Devin Willmott, J. Zico Kolter, Madan Ravi Ganesh, Mohammad Sadegh Norouzzadeh, Victor Akinwande","submitted_at":"2024-12-21T21:19:08Z","abstract_excerpt":"Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a direct consequence of the huge web-scale datasets used to train them, but they require correspondingly large vision components to properly learn powerful and general representations from such a broad data domain. This poses a challenge for deploying large vision-language models, especially in resource-constrained environments. To address this, we propose an alternate vision-language architecture, called HyperCLIP, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16777","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/2412.16777/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":"2412.16777","created_at":"2026-07-05T09:53:12.992526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.16777v1","created_at":"2026-07-05T09:53:12.992526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16777","created_at":"2026-07-05T09:53:12.992526+00:00"},{"alias_kind":"pith_short_12","alias_value":"65OEXJD763SH","created_at":"2026-07-05T09:53:12.992526+00:00"},{"alias_kind":"pith_short_16","alias_value":"65OEXJD763SHTRMM","created_at":"2026-07-05T09:53:12.992526+00:00"},{"alias_kind":"pith_short_8","alias_value":"65OEXJD7","created_at":"2026-07-05T09:53:12.992526+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/65OEXJD763SHTRMMXEMTGFIF47","json":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47.json","graph_json":"https://pith.science/api/pith-number/65OEXJD763SHTRMMXEMTGFIF47/graph.json","events_json":"https://pith.science/api/pith-number/65OEXJD763SHTRMMXEMTGFIF47/events.json","paper":"https://pith.science/paper/65OEXJD7"},"agent_actions":{"view_html":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47","download_json":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47.json","view_paper":"https://pith.science/paper/65OEXJD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.16777&json=true","fetch_graph":"https://pith.science/api/pith-number/65OEXJD763SHTRMMXEMTGFIF47/graph.json","fetch_events":"https://pith.science/api/pith-number/65OEXJD763SHTRMMXEMTGFIF47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47/action/storage_attestation","attest_author":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47/action/author_attestation","sign_citation":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47/action/citation_signature","submit_replication":"https://pith.science/pith/65OEXJD763SHTRMMXEMTGFIF47/action/replication_record"}},"created_at":"2026-07-05T09:53:12.992526+00:00","updated_at":"2026-07-05T09:53:12.992526+00:00"}