{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DPRSL5DDIFJDNHCHJACMOE3HEU","short_pith_number":"pith:DPRSL5DD","canonical_record":{"source":{"id":"2407.11393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T05:26:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"f751b47e328d59e9cff81a7b36bcfcbfc027071af7f47f0d0e4ef4b33548f996","abstract_canon_sha256":"d04705b6d210116b1201e0f45712d8d6202826e9c6991f5ccf36c795f248897f"},"schema_version":"1.0"},"canonical_sha256":"1be325f4634152369c474804c713672516f13946679a727e27547a315c9435a7","source":{"kind":"arxiv","id":"2407.11393","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11393","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11393v2","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11393","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_12","alias_value":"DPRSL5DDIFJD","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_16","alias_value":"DPRSL5DDIFJDNHCH","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_8","alias_value":"DPRSL5DD","created_at":"2026-07-05T08:44:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DPRSL5DDIFJDNHCHJACMOE3HEU","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11393","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T05:26:12Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"f751b47e328d59e9cff81a7b36bcfcbfc027071af7f47f0d0e4ef4b33548f996","abstract_canon_sha256":"d04705b6d210116b1201e0f45712d8d6202826e9c6991f5ccf36c795f248897f"},"schema_version":"1.0"},"canonical_sha256":"1be325f4634152369c474804c713672516f13946679a727e27547a315c9435a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:57.535530Z","signature_b64":"SsCra0NL6qr16XkbrcNJ7lnrXi1wRAOjfoahgv8z7qx2jhltKVDOMv+TmvnM3SokOAoudvWgQ8D0Ag6+SoeFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be325f4634152369c474804c713672516f13946679a727e27547a315c9435a7","last_reissued_at":"2026-07-05T08:44:57.535048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:57.535048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11393","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+21DJMyAigdUJZFhsiYzeChtJkyWP8+tvaSM9dC7v27VR+esvjAt2m3/Or3+u5RNbvcHiZhRgtjnndCPV4QBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:40:41.603601Z"},"content_sha256":"8f20842bb266daee6ce49ed593e06e586815bb030ad255566573b9f9e82f92fc","schema_version":"1.0","event_id":"sha256:8f20842bb266daee6ce49ed593e06e586815bb030ad255566573b9f9e82f92fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DPRSL5DDIFJDNHCHJACMOE3HEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Afsaneh Fazly, Federico Fancellu, Kalliopi Basioti, Mohamed A. Abdelsalam, Vladimir Pavlovic","submitted_at":"2024-07-16T05:26:12Z","abstract_excerpt":"Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets mainly contain captions that describe the entirety of an image, making them ineffective for training CIC models that can potentially attend to any subset of regions or relationships. To tackle this challenge, we propose a novel, fully automatic method to sample additional focused and visually grounded captions using a unified structured semantic representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11393","kind":"arxiv","version":2},"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/2407.11393/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U3ydQheNXUxB7Uxmpl8+4k09JDSroONoaqxPMI/QIOr41Z6hq0V9fLhdyACBWPrg39gJXo0f22SfORozy3BhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:40:41.604529Z"},"content_sha256":"cc0a2a967fa1e0c300de19df395dc7a5b2955e2b0c801f0a3155a9019ca5175d","schema_version":"1.0","event_id":"sha256:cc0a2a967fa1e0c300de19df395dc7a5b2955e2b0c801f0a3155a9019ca5175d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/bundle.json","state_url":"https://pith.science/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/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":"2026-08-10T20:40:41Z","links":{"resolver":"https://pith.science/pith/DPRSL5DDIFJDNHCHJACMOE3HEU","bundle":"https://pith.science/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/bundle.json","state":"https://pith.science/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPRSL5DDIFJDNHCHJACMOE3HEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DPRSL5DDIFJDNHCHJACMOE3HEU","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":"d04705b6d210116b1201e0f45712d8d6202826e9c6991f5ccf36c795f248897f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T05:26:12Z","title_canon_sha256":"f751b47e328d59e9cff81a7b36bcfcbfc027071af7f47f0d0e4ef4b33548f996"},"schema_version":"1.0","source":{"id":"2407.11393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11393","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11393v2","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11393","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_12","alias_value":"DPRSL5DDIFJD","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_16","alias_value":"DPRSL5DDIFJDNHCH","created_at":"2026-07-05T08:44:57Z"},{"alias_kind":"pith_short_8","alias_value":"DPRSL5DD","created_at":"2026-07-05T08:44:57Z"}],"graph_snapshots":[{"event_id":"sha256:cc0a2a967fa1e0c300de19df395dc7a5b2955e2b0c801f0a3155a9019ca5175d","target":"graph","created_at":"2026-07-05T08:44:57Z","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/2407.11393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Controllable Image Captioning (CIC) aims at generating natural language descriptions for an image, conditioned on information provided by end users, e.g., regions, entities or events of interest. However, available image-language datasets mainly contain captions that describe the entirety of an image, making them ineffective for training CIC models that can potentially attend to any subset of regions or relationships. To tackle this challenge, we propose a novel, fully automatic method to sample additional focused and visually grounded captions using a unified structured semantic representatio","authors_text":"Afsaneh Fazly, Federico Fancellu, Kalliopi Basioti, Mohamed A. Abdelsalam, Vladimir Pavlovic","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T05:26:12Z","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11393","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":"sha256:8f20842bb266daee6ce49ed593e06e586815bb030ad255566573b9f9e82f92fc","target":"record","created_at":"2026-07-05T08:44:57Z","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":"d04705b6d210116b1201e0f45712d8d6202826e9c6991f5ccf36c795f248897f","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T05:26:12Z","title_canon_sha256":"f751b47e328d59e9cff81a7b36bcfcbfc027071af7f47f0d0e4ef4b33548f996"},"schema_version":"1.0","source":{"id":"2407.11393","kind":"arxiv","version":2}},"canonical_sha256":"1be325f4634152369c474804c713672516f13946679a727e27547a315c9435a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1be325f4634152369c474804c713672516f13946679a727e27547a315c9435a7","first_computed_at":"2026-07-05T08:44:57.535048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:57.535048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsCra0NL6qr16XkbrcNJ7lnrXi1wRAOjfoahgv8z7qx2jhltKVDOMv+TmvnM3SokOAoudvWgQ8D0Ag6+SoeFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:57.535530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f20842bb266daee6ce49ed593e06e586815bb030ad255566573b9f9e82f92fc","sha256:cc0a2a967fa1e0c300de19df395dc7a5b2955e2b0c801f0a3155a9019ca5175d"],"state_sha256":"ece07fc094036431580295b3b7e969c7a94ffb3ee12e32c932d924e68799e5a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9RQ6B6M29dHQ6WRypvu3oQdX8A5Nyz4O9p425UcXRV/Cs1Zzk5CbA5Jo+e9Bl+rd8tcBDg8T53JjkociW2zfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:40:41.610826Z","bundle_sha256":"a675c5c6cde6d9abcb9ed0619f5f51a69180c11c9290e9b4af0e46d8b63cdf0f"}}