{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3L6JZPW6Z7FAWYTBDR77WZDDVE","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":"5cf91d4ea60c50a069a9dc65ca9a12e85800b95859135ebeaf0287921aa5a74a","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T19:00:05Z","title_canon_sha256":"d94d4a5eff6d858d6b259d339d50e5eac7398cd1f75db534c538311e32a88acf"},"schema_version":"1.0","source":{"id":"2111.12727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12727","created_at":"2026-07-05T07:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12727v3","created_at":"2026-07-05T07:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12727","created_at":"2026-07-05T07:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"3L6JZPW6Z7FA","created_at":"2026-07-05T07:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"3L6JZPW6Z7FAWYTB","created_at":"2026-07-05T07:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"3L6JZPW6","created_at":"2026-07-05T07:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:9a0fe2e9f6795a362f89420e50d8de24473d96a1fb5f54876c0a7c13dc56f461","target":"graph","created_at":"2026-07-05T07:18:22Z","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/2111.12727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources, containing both human-annotated and web-collected captions. Large-scale datasets with noisy image-text pairs, indeed, provide a sub-optimal source of supervision because of their low-quality descriptive style, while human-annotated datasets are cleaner but smaller in scale. To get the best of both worlds, we propose to leverage and separate semantics and descriptive style through the incorporation of a style token and keywords extracted through a retrieval component. The pr","authors_text":"Giuseppe Fiameni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","cross_cats":["cs.AI","cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T19:00:05Z","title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12727","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":"sha256:0c40813a690cd9dfc5ac0ac8c60348b14d08d79341e8c7d759e222fea375c800","target":"record","created_at":"2026-07-05T07:18:22Z","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":"5cf91d4ea60c50a069a9dc65ca9a12e85800b95859135ebeaf0287921aa5a74a","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T19:00:05Z","title_canon_sha256":"d94d4a5eff6d858d6b259d339d50e5eac7398cd1f75db534c538311e32a88acf"},"schema_version":"1.0","source":{"id":"2111.12727","kind":"arxiv","version":3}},"canonical_sha256":"dafc9cbedecfca0b62611c7ffb6463a9294892daf7881099d9bbbb0d19ee779b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dafc9cbedecfca0b62611c7ffb6463a9294892daf7881099d9bbbb0d19ee779b","first_computed_at":"2026-07-05T07:18:22.409499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:22.409499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vshiVF6fJbGhFCZNxbXn5dE+S0kTLnAuLmpe/cOLWaKKt02SfrVx+Ik2VQZfjBMx8TCYMNJDiycQ7rBhbYMJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:22.410029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c40813a690cd9dfc5ac0ac8c60348b14d08d79341e8c7d759e222fea375c800","sha256:9a0fe2e9f6795a362f89420e50d8de24473d96a1fb5f54876c0a7c13dc56f461"],"state_sha256":"e1e099e71ca273c8cf03ad159d1fa04c3f2b8fa338140513aac3d1e575093815"}