{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:452RKRRE54DD4T2OMDH65DDQX6","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":"4a937ac5d6777c16dc3f74426a27a95bd2e2c3c91d3705838a88a266cb035c13","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T09:03:22Z","title_canon_sha256":"7a4a0712f599adc7bb3d68a170e7277211c67196d8f31dd592e707c35fcfdb20"},"schema_version":"1.0","source":{"id":"2209.15323","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15323","created_at":"2026-07-05T05:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15323v2","created_at":"2026-07-05T05:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15323","created_at":"2026-07-05T05:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"452RKRRE54DD","created_at":"2026-07-05T05:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"452RKRRE54DD4T2O","created_at":"2026-07-05T05:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"452RKRRE","created_at":"2026-07-05T05:55:59Z"}],"graph_snapshots":[{"event_id":"sha256:92c49ff0713cf44849d81c826e2fa003fa635bd937927cef67f41963cf51421e","target":"graph","created_at":"2026-07-05T05:55:59Z","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/2209.15323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption conditioned on an input image and related captions retrieved from a datastore. Our model is lightweight and fast to train, as the only learned parameters are in newly introduced cross-attention layers between a pre-trained CLIP encoder and GPT-2 decoder. SmallCap can transfer to new domains without additional finetuning and can exploit large-scale data in a trainin","authors_text":"Bruno Martins, Desmond Elliott, Rita Ramos, Yova Kementchedjhieva","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T09:03:22Z","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15323","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:cd31cf25001e37009220df92f4ed218aa369c8d68eefeb77bed87ea69e8805fa","target":"record","created_at":"2026-07-05T05:55:59Z","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":"4a937ac5d6777c16dc3f74426a27a95bd2e2c3c91d3705838a88a266cb035c13","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T09:03:22Z","title_canon_sha256":"7a4a0712f599adc7bb3d68a170e7277211c67196d8f31dd592e707c35fcfdb20"},"schema_version":"1.0","source":{"id":"2209.15323","kind":"arxiv","version":2}},"canonical_sha256":"e775154624ef063e4f4e60cfee8c70bf84042133b92733370703392b91781014","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e775154624ef063e4f4e60cfee8c70bf84042133b92733370703392b91781014","first_computed_at":"2026-07-05T05:55:59.525814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:55:59.525814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWIpggO4QcAvV751ecuH57ynfl2rDJ40Yqx5fJ6iGkY2r2tmDjvdyU2bq/nLN9LEkxWKNZAIYYU3oO2KvYhIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:55:59.526331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15323","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd31cf25001e37009220df92f4ed218aa369c8d68eefeb77bed87ea69e8805fa","sha256:92c49ff0713cf44849d81c826e2fa003fa635bd937927cef67f41963cf51421e"],"state_sha256":"6c966611e40d70831e6ad79c07d7b33c04fc3f5f249d6060a83807c885eac0a0"}