{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HADIURP6JIXS4LZNOU62IAD6GE","short_pith_number":"pith:HADIURP6","schema_version":"1.0","canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","source":{"kind":"arxiv","id":"1811.10652","version":3},"attestation_state":"computed","paper":{"title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","submitted_at":"2018-11-26T19:23:33Z","abstract_excerpt":"Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the correspondi"},"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":"1811.10652","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-26T19:23:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f9b966812cbef5bf97a493bebb151a4c7e7254a0cbc4068dbd57af44d44e80cd","abstract_canon_sha256":"ba5fa7262a4c1b980f9236b6eed0a9762f4e3e79cf7c61522ab80e9d0f95957f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:41.323844Z","signature_b64":"x2oU7rnrwUGEX0DCHyWN21gLTTN2Zq0eZ9IYGbGBJ65r/YoUqhS0qfHQ5XDoim4dIK+EVHdH/LgC3BSF4UBeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","last_reissued_at":"2026-05-17T23:46:41.323052Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:41.323052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","submitted_at":"2018-11-26T19:23:33Z","abstract_excerpt":"Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the correspondi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10652","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":""},"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":"1811.10652","created_at":"2026-05-17T23:46:41.323179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.10652v3","created_at":"2026-05-17T23:46:41.323179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10652","created_at":"2026-05-17T23:46:41.323179+00:00"},{"alias_kind":"pith_short_12","alias_value":"HADIURP6JIXS","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HADIURP6JIXS4LZN","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HADIURP6","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE","json":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE.json","graph_json":"https://pith.science/api/pith-number/HADIURP6JIXS4LZNOU62IAD6GE/graph.json","events_json":"https://pith.science/api/pith-number/HADIURP6JIXS4LZNOU62IAD6GE/events.json","paper":"https://pith.science/paper/HADIURP6"},"agent_actions":{"view_html":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE","download_json":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE.json","view_paper":"https://pith.science/paper/HADIURP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.10652&json=true","fetch_graph":"https://pith.science/api/pith-number/HADIURP6JIXS4LZNOU62IAD6GE/graph.json","fetch_events":"https://pith.science/api/pith-number/HADIURP6JIXS4LZNOU62IAD6GE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/action/storage_attestation","attest_author":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/action/author_attestation","sign_citation":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/action/citation_signature","submit_replication":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/action/replication_record"}},"created_at":"2026-05-17T23:46:41.323179+00:00","updated_at":"2026-05-17T23:46:41.323179+00:00"}