{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NHSIAQ4IWMPBHCPNIFJ6FBTPNF","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":"10179a815e639c7d936b8daaf4ad062fd0333976c292c6fc51fd8b06a2c76d5f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T15:16:07Z","title_canon_sha256":"527c9519111e9c273bf5c03dc06614fd2d781fb4df87201bad82c148319c6cb3"},"schema_version":"1.0","source":{"id":"2305.03610","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03610","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03610v2","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03610","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_12","alias_value":"NHSIAQ4IWMPB","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_16","alias_value":"NHSIAQ4IWMPBHCPN","created_at":"2026-07-05T07:40:40Z"},{"alias_kind":"pith_short_8","alias_value":"NHSIAQ4I","created_at":"2026-07-05T07:40:40Z"}],"graph_snapshots":[{"event_id":"sha256:7b9ebe882e99e42b68a750790e5c4c54636f4d9da5a67d4056ad8c80cc607a4b","target":"graph","created_at":"2026-07-05T07:40:40Z","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/2305.03610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning models are typically trained by treating all samples equally, neglecting to account for mismatched or otherwise difficult data points. In contrast, recent work has shown the effectiveness of training models by scheduling the data using curriculum learning strategies. This paper contributes to this direction by actively curating difficult samples in datasets without increasing the total number of samples. We explore the effect of using three data curation methods within the training process: complete removal of an sample, caption replacement, or image replacement via a text-to-","authors_text":"Chen Qiu, Desmond Elliott, Jonas F. Lotz, Wenyan Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T15:16:07Z","title":"The Role of Data Curation in Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03610","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":"sha256:759da76d416b4f525ac96ebdb6f36b568022998543bdb9c4cab69c382f939bb8","target":"record","created_at":"2026-07-05T07:40:40Z","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":"10179a815e639c7d936b8daaf4ad062fd0333976c292c6fc51fd8b06a2c76d5f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T15:16:07Z","title_canon_sha256":"527c9519111e9c273bf5c03dc06614fd2d781fb4df87201bad82c148319c6cb3"},"schema_version":"1.0","source":{"id":"2305.03610","kind":"arxiv","version":2}},"canonical_sha256":"69e4804388b31e1389ed4153e2866f6968e55240345d395ea7c0eb7e94bc805f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69e4804388b31e1389ed4153e2866f6968e55240345d395ea7c0eb7e94bc805f","first_computed_at":"2026-07-05T07:40:40.500628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:40.500628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"55m4/OhyHLvx25APOjGNb2XUH3yzVhLOncBx7iOrVJBnHILyNhLOVxt9/gVJmZE15fFPwXvPKpzsmPnNQ5jBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:40.501177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03610","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:759da76d416b4f525ac96ebdb6f36b568022998543bdb9c4cab69c382f939bb8","sha256:7b9ebe882e99e42b68a750790e5c4c54636f4d9da5a67d4056ad8c80cc607a4b"],"state_sha256":"814a52aa59a082e32ac3610a347477924cbc359388a860b59ed707579d55f2ee"}