{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3L6JZPW6Z7FAWYTBDR77WZDDVE","short_pith_number":"pith:3L6JZPW6","schema_version":"1.0","canonical_sha256":"dafc9cbedecfca0b62611c7ffb6463a9294892daf7881099d9bbbb0d19ee779b","source":{"kind":"arxiv","id":"2111.12727","version":3},"attestation_state":"computed","paper":{"title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Giuseppe Fiameni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","submitted_at":"2021-11-24T19:00:05Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.12727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T19:00:05Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM"],"title_canon_sha256":"d94d4a5eff6d858d6b259d339d50e5eac7398cd1f75db534c538311e32a88acf","abstract_canon_sha256":"5cf91d4ea60c50a069a9dc65ca9a12e85800b95859135ebeaf0287921aa5a74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:22.410029Z","signature_b64":"vshiVF6fJbGhFCZNxbXn5dE+S0kTLnAuLmpe/cOLWaKKt02SfrVx+Ik2VQZfjBMx8TCYMNJDiycQ7rBhbYMJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dafc9cbedecfca0b62611c7ffb6463a9294892daf7881099d9bbbb0d19ee779b","last_reissued_at":"2026-07-05T07:18:22.409499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:22.409499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Giuseppe Fiameni, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","submitted_at":"2021-11-24T19:00:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12727","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.12727/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.12727","created_at":"2026-07-05T07:18:22.409561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12727v3","created_at":"2026-07-05T07:18:22.409561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12727","created_at":"2026-07-05T07:18:22.409561+00:00"},{"alias_kind":"pith_short_12","alias_value":"3L6JZPW6Z7FA","created_at":"2026-07-05T07:18:22.409561+00:00"},{"alias_kind":"pith_short_16","alias_value":"3L6JZPW6Z7FAWYTB","created_at":"2026-07-05T07:18:22.409561+00:00"},{"alias_kind":"pith_short_8","alias_value":"3L6JZPW6","created_at":"2026-07-05T07:18:22.409561+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2311.03079","citing_title":"CogVLM: Visual Expert for Pretrained Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE","json":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE.json","graph_json":"https://pith.science/api/pith-number/3L6JZPW6Z7FAWYTBDR77WZDDVE/graph.json","events_json":"https://pith.science/api/pith-number/3L6JZPW6Z7FAWYTBDR77WZDDVE/events.json","paper":"https://pith.science/paper/3L6JZPW6"},"agent_actions":{"view_html":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE","download_json":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE.json","view_paper":"https://pith.science/paper/3L6JZPW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12727&json=true","fetch_graph":"https://pith.science/api/pith-number/3L6JZPW6Z7FAWYTBDR77WZDDVE/graph.json","fetch_events":"https://pith.science/api/pith-number/3L6JZPW6Z7FAWYTBDR77WZDDVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE/action/storage_attestation","attest_author":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE/action/author_attestation","sign_citation":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE/action/citation_signature","submit_replication":"https://pith.science/pith/3L6JZPW6Z7FAWYTBDR77WZDDVE/action/replication_record"}},"created_at":"2026-07-05T07:18:22.409561+00:00","updated_at":"2026-07-05T07:18:22.409561+00:00"}