{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HADIURP6JIXS4LZNOU62IAD6GE","short_pith_number":"pith:HADIURP6","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"},"canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","source":{"kind":"arxiv","id":"1811.10652","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10652","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10652v3","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10652","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"HADIURP6JIXS","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HADIURP6JIXS4LZN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HADIURP6","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HADIURP6JIXS4LZNOU62IAD6GE","target":"record","payload":{"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"},"canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","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"},"source_kind":"arxiv","source_id":"1811.10652","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zs+GIDsD5+m8HiKadTDEYnrO6rPCEism5peBmm8c2qIEgV9tKdYcbERw4Lc/eLmAOOZaqWJbrNKWsLF238FiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:15:49.256534Z"},"content_sha256":"5adcbd287ee35443f158abd8cc485d475feb5b5faff1614d22ea037770a9ce31","schema_version":"1.0","event_id":"sha256:5adcbd287ee35443f158abd8cc485d475feb5b5faff1614d22ea037770a9ce31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HADIURP6JIXS4LZNOU62IAD6GE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O71vcV53TNtZhoGEhQSLSU/bL3coEFShjoTQdlxc0yLzbgtIcFnziboyCOZX+aBc3XZ5E1Z9e5I+ppkaRxgjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:15:49.256886Z"},"content_sha256":"f9aa5d419c8abb319c6467333cffba3d9cefb575614613eaeb45114c30b4f7de","schema_version":"1.0","event_id":"sha256:f9aa5d419c8abb319c6467333cffba3d9cefb575614613eaeb45114c30b4f7de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/bundle.json","state_url":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HADIURP6JIXS4LZNOU62IAD6GE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T18:15:49Z","links":{"resolver":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE","bundle":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/bundle.json","state":"https://pith.science/pith/HADIURP6JIXS4LZNOU62IAD6GE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HADIURP6JIXS4LZNOU62IAD6GE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HADIURP6JIXS4LZNOU62IAD6GE","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":"ba5fa7262a4c1b980f9236b6eed0a9762f4e3e79cf7c61522ab80e9d0f95957f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-26T19:23:33Z","title_canon_sha256":"f9b966812cbef5bf97a493bebb151a4c7e7254a0cbc4068dbd57af44d44e80cd"},"schema_version":"1.0","source":{"id":"1811.10652","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.10652","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.10652v3","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.10652","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"HADIURP6JIXS","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HADIURP6JIXS4LZN","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HADIURP6","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:f9aa5d419c8abb319c6467333cffba3d9cefb575614613eaeb45114c30b4f7de","target":"graph","created_at":"2026-05-17T23:46:41Z","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"},"paper":{"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","authors_text":"Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-26T19:23:33Z","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.10652","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":"sha256:5adcbd287ee35443f158abd8cc485d475feb5b5faff1614d22ea037770a9ce31","target":"record","created_at":"2026-05-17T23:46:41Z","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":"ba5fa7262a4c1b980f9236b6eed0a9762f4e3e79cf7c61522ab80e9d0f95957f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-26T19:23:33Z","title_canon_sha256":"f9b966812cbef5bf97a493bebb151a4c7e7254a0cbc4068dbd57af44d44e80cd"},"schema_version":"1.0","source":{"id":"1811.10652","kind":"arxiv","version":3}},"canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38068a45fe4a2f2e2f2d753da4007e3118c10d22bf0a706f430455e4bb1e7a92","first_computed_at":"2026-05-17T23:46:41.323052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:41.323052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2oU7rnrwUGEX0DCHyWN21gLTTN2Zq0eZ9IYGbGBJ65r/YoUqhS0qfHQ5XDoim4dIK+EVHdH/LgC3BSF4UBeBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:41.323844Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.10652","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5adcbd287ee35443f158abd8cc485d475feb5b5faff1614d22ea037770a9ce31","sha256:f9aa5d419c8abb319c6467333cffba3d9cefb575614613eaeb45114c30b4f7de"],"state_sha256":"ce53dbadec7fcb0cdb817857769c33eaa3f140e5a761e15d08d660c877b9a336"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3/F3iLZBFaeMJALfDm53B7Q2IAyyjQaU/9ZZ3Z/BtbihNWpCkRqk/R5j+ZTbTwucGscHVdzQD7ClHzksA5TCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:15:49.259010Z","bundle_sha256":"323f65ddaede1926fe712be48b7813e1ef21037c37afee2317b150ed627c29f0"}}