{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3W3UL66BMW3LIORLEB34GG5TBM","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":"6e977b0adbc233658fe39d449cd8170b8d74530057fa11e61031f237998462a1","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-04T01:42:09Z","title_canon_sha256":"7e285d0b01f1f49f73d31e21259f1debd17a8caac414260361be818ff714e671"},"schema_version":"1.0","source":{"id":"2312.01564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.01564","created_at":"2026-07-05T07:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"2312.01564v1","created_at":"2026-07-05T07:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01564","created_at":"2026-07-05T07:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"3W3UL66BMW3L","created_at":"2026-07-05T07:19:56Z"},{"alias_kind":"pith_short_16","alias_value":"3W3UL66BMW3LIORL","created_at":"2026-07-05T07:19:56Z"},{"alias_kind":"pith_short_8","alias_value":"3W3UL66B","created_at":"2026-07-05T07:19:56Z"}],"graph_snapshots":[{"event_id":"sha256:64debcfca0cd239c8363be14084510d93103b9312f0a2af075c6cc8fc93799d8","target":"graph","created_at":"2026-07-05T07:19:56Z","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/2312.01564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The choice of input text prompt plays a critical role in the performance of Vision-Language Pretrained (VLP) models such as CLIP. We present APoLLo, a unified multi-modal approach that combines Adapter and Prompt learning for Vision-Language models. Our method is designed to substantially improve the generalization capabilities of VLP models when they are fine-tuned in a few-shot setting. We introduce trainable cross-attention-based adapter layers in conjunction with vision and language encoders to strengthen the alignment between the two modalities. We enforce consistency between the respecti","authors_text":"Dinesh Manocha, Sanjoy Chowdhury, Sayan Nag","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-04T01:42:09Z","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01564","kind":"arxiv","version":1},"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":"sha256:19b1eab69265d0fa9f7ba32719312cd82c78bf602d9fea6625a1b772eec8e6ed","target":"record","created_at":"2026-07-05T07:19:56Z","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":"6e977b0adbc233658fe39d449cd8170b8d74530057fa11e61031f237998462a1","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-04T01:42:09Z","title_canon_sha256":"7e285d0b01f1f49f73d31e21259f1debd17a8caac414260361be818ff714e671"},"schema_version":"1.0","source":{"id":"2312.01564","kind":"arxiv","version":1}},"canonical_sha256":"ddb745fbc165b6b43a2b2077c31bb30b038b85fc940b96217dc0356d6d09f2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddb745fbc165b6b43a2b2077c31bb30b038b85fc940b96217dc0356d6d09f2c7","first_computed_at":"2026-07-05T07:19:56.714966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:56.714966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ef5XToETN5sFTcu7C/rRW3tm8MyJy40/AnyGrztwdinpy8FF7yw0NlsrrdvxijCuSLcK8vMqGWAdMn3w+sJDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:56.715335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.01564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19b1eab69265d0fa9f7ba32719312cd82c78bf602d9fea6625a1b772eec8e6ed","sha256:64debcfca0cd239c8363be14084510d93103b9312f0a2af075c6cc8fc93799d8"],"state_sha256":"6bf27f81e08e390282ebef292c4db54c75ef1badc26e5c509d0b85249bd4521c"}