{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JCDTTYJMGGCR24ELTUSKQO2PL7","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":"f0db282ba7caf77d5bb1cff1357adcde44ac2b71370c53f716da54055de0cb0d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T12:41:54Z","title_canon_sha256":"962d539725e114341168e6cc6a6e5644089b7e23b418a3a2f2db9165dea591e7"},"schema_version":"1.0","source":{"id":"2406.02265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02265","created_at":"2026-07-05T08:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02265v3","created_at":"2026-07-05T08:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02265","created_at":"2026-07-05T08:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"JCDTTYJMGGCR","created_at":"2026-07-05T08:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"JCDTTYJMGGCR24EL","created_at":"2026-07-05T08:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"JCDTTYJM","created_at":"2026-07-05T08:52:33Z"}],"graph_snapshots":[{"event_id":"sha256:5bf8d186efa8d76c257ccd061591685c53a5ebee90b858532902236d62dfbff7","target":"graph","created_at":"2026-07-05T08:52:33Z","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/2406.02265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in retrieval-augmented models for image captioning highlight the benefit of retrieving related captions for efficient, lightweight models with strong domain-transfer capabilities. While these models demonstrate the success of retrieval augmentation, retrieval models are still far from perfect in practice: the retrieved information can sometimes mislead the model, resulting in incorrect generation and worse performance. In this paper, we analyze the robustness of a retrieval-augmented captioning model SmallCap. Our analysis shows that the model is sensitive to tokens that appear","authors_text":"Desmond Elliott, Jiaang Li, Raphael Tang, Rita Ramos, Wenyan Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T12:41:54Z","title":"Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02265","kind":"arxiv","version":3},"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:c13bb9c0ed1beeb3c3a2a0aa3be8b844a578d8f7a90503388b2a3ea6c3eaceec","target":"record","created_at":"2026-07-05T08:52:33Z","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":"f0db282ba7caf77d5bb1cff1357adcde44ac2b71370c53f716da54055de0cb0d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T12:41:54Z","title_canon_sha256":"962d539725e114341168e6cc6a6e5644089b7e23b418a3a2f2db9165dea591e7"},"schema_version":"1.0","source":{"id":"2406.02265","kind":"arxiv","version":3}},"canonical_sha256":"488739e12c31851d708b9d24a83b4f5fea8204991ab3a3646f5991a34c2df4b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"488739e12c31851d708b9d24a83b4f5fea8204991ab3a3646f5991a34c2df4b7","first_computed_at":"2026-07-05T08:52:33.657871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:33.657871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6J51U723AAWsMDWRIxmoisFQsOado52dMrBfP6RYEMcYIWT/ZlKBXcE3cOUU7seMV4vGAGAzwUGKhLOgztwdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:33.658364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c13bb9c0ed1beeb3c3a2a0aa3be8b844a578d8f7a90503388b2a3ea6c3eaceec","sha256:5bf8d186efa8d76c257ccd061591685c53a5ebee90b858532902236d62dfbff7"],"state_sha256":"3c02fbc46596970531060aa085133c1400b2d65928fe0999657f52cf7eeb2357"}